{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/form/papers/2","list_of":"/task/form","task":"Form","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":17,"rows_per_page":100,"rows":[101,200],"of":1618,"counts":{"archive_papers_tagged":1618,"with_a_code_link":436,"where_syntology_ran_a_sample":111,"not_listed_spam_title":0,"listed":1618,"listed_where_code_ran":111,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":93,"every_run_a_failure_of_syntologys_instrument":18,"listed_with_a_run_with_no_instrument_failure":93,"listed_every_run_a_failure_of_syntologys_instrument":18,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/form","prev":"/task/form","next":"/task/form/papers/3","papers":[{"url":"/paper/the-meta-representation-hypothesis","slug":"the-meta-representation-hypothesis","title":"Representation Convergence: Mutual Distillation is Secretly a Form of Regularization","date":"2025-01-05","arxiv_id":"2501.02481","repositories_listed":1,"syntology":null},{"url":"/paper/rapid-learning-in-constrained-minimax-games","slug":"rapid-learning-in-constrained-minimax-games","title":"Rapid Learning in Constrained Minimax Games with Negative Momentum","date":"2024-12-31","arxiv_id":"2501.00533","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-context-gaps-enhancing-comprehension","slug":"bridging-context-gaps-enhancing-comprehension","title":"Bridging Context Gaps: Enhancing Comprehension in Long-Form Social Conversations Through Contextualized Excerpts","date":"2024-12-28","arxiv_id":"2412.19966","repositories_listed":1,"syntology":null},{"url":"/paper/long-form-speech-generation-with-spoken","slug":"long-form-speech-generation-with-spoken","title":"Long-Form Speech Generation with Spoken Language Models","date":"2024-12-24","arxiv_id":"2412.18603","repositories_listed":1,"syntology":null},{"url":"/paper/dragonverseqa-open-domain-long-form-context","slug":"dragonverseqa-open-domain-long-form-context","title":"DragonVerseQA: Open-Domain Long-Form Context-Aware Question-Answering","date":"2024-12-21","arxiv_id":"2412.16694","repositories_listed":1,"syntology":null},{"url":"/paper/fine-tuning-whisper-on-low-resource-languages","slug":"fine-tuning-whisper-on-low-resource-languages","title":"Fine-tuning Whisper on Low-Resource Languages for Real-World Applications","date":"2024-12-20","arxiv_id":"2412.15726","repositories_listed":1,"syntology":null},{"url":"/paper/phenotype-structuring-of-non-local-kinetic","slug":"phenotype-structuring-of-non-local-kinetic","title":"Phenotype-structuring of non-local kinetic models of cell migration driven by environmental sensing","date":"2024-12-20","arxiv_id":"2412.16258","repositories_listed":1,"syntology":null},{"url":"/paper/generating-long-form-story-using-dynamic","slug":"generating-long-form-story-using-dynamic","title":"Generating Long-form Story Using Dynamic Hierarchical Outlining with Memory-Enhancement","date":"2024-12-18","arxiv_id":"2412.13575","repositories_listed":1,"syntology":null},{"url":"/paper/chatdit-a-training-free-baseline-for-task","slug":"chatdit-a-training-free-baseline-for-task","title":"ChatDiT: A Training-Free Baseline for Task-Agnostic Free-Form Chatting with Diffusion Transformers","date":"2024-12-17","arxiv_id":"2412.12571","repositories_listed":1,"syntology":null},{"url":"/paper/dndscore-decontextualization-and","slug":"dndscore-decontextualization-and","title":"DnDScore: Decontextualization and Decomposition for Factuality Verification in Long-Form Text Generation","date":"2024-12-17","arxiv_id":"2412.13175","repositories_listed":1,"syntology":null},{"url":"/paper/tilted-quantile-gradient-updates-for-quantile","slug":"tilted-quantile-gradient-updates-for-quantile","title":"Tilted Quantile Gradient Updates for Quantile-Constrained Reinforcement Learning","date":"2024-12-17","arxiv_id":"2412.13184","repositories_listed":1,"syntology":null},{"url":"/paper/speechprune-context-aware-token-pruning-for","slug":"speechprune-context-aware-token-pruning-for","title":"SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval","date":"2024-12-16","arxiv_id":"2412.12009","repositories_listed":1,"syntology":null},{"url":"/paper/survbeta-ensemble-based-survival-models-using","slug":"survbeta-ensemble-based-survival-models-using","title":"SurvBETA: Ensemble-Based Survival Models Using Beran Estimators and Several Attention Mechanisms","date":"2024-12-10","arxiv_id":"2412.07638","repositories_listed":1,"syntology":null},{"url":"/paper/loss-terms-and-operator-forms-of-koopman","slug":"loss-terms-and-operator-forms-of-koopman","title":"Loss Terms and Operator Forms of Koopman Autoencoders","date":"2024-12-05","arxiv_id":"2412.04578","repositories_listed":1,"syntology":null},{"url":"/paper/symbolfit-automatic-parametric-modeling-with","slug":"symbolfit-automatic-parametric-modeling-with","title":"SymbolFit: Automatic Parametric Modeling with Symbolic Regression","date":"2024-11-15","arxiv_id":"2411.09851","repositories_listed":1,"syntology":null},{"url":"/paper/dahl-domain-specific-automated-hallucination","slug":"dahl-domain-specific-automated-hallucination","title":"DAHL: Domain-specific Automated Hallucination Evaluation of Long-Form Text through a Benchmark Dataset in Biomedicine","date":"2024-11-14","arxiv_id":"2411.09255","repositories_listed":1,"syntology":null},{"url":"/paper/measuring-short-form-factuality-in-large","slug":"measuring-short-form-factuality-in-large","title":"Measuring short-form factuality in large language models","date":"2024-11-07","arxiv_id":"2411.04368","repositories_listed":1,"syntology":null},{"url":"/paper/long-form-text-to-music-generation-with","slug":"long-form-text-to-music-generation-with","title":"Long-Form Text-to-Music Generation with Adaptive Prompts: A Case Study in Tabletop Role-Playing Games Soundtracks","date":"2024-11-06","arxiv_id":"2411.03948","repositories_listed":1,"syntology":null},{"url":"/paper/volatility-parametrizations-with-random","slug":"volatility-parametrizations-with-random","title":"Volatility Parametrizations with Random Coefficients: Analytic Flexibility for Implied Volatility Surfaces","date":"2024-11-06","arxiv_id":"2411.04041","repositories_listed":1,"syntology":null},{"url":"/paper/on-positional-bias-of-faithfulness-for-long","slug":"on-positional-bias-of-faithfulness-for-long","title":"On Positional Bias of Faithfulness for Long-form Summarization","date":"2024-10-31","arxiv_id":"2410.23609","repositories_listed":1,"syntology":null},{"url":"/paper/graph-based-uncertainty-metrics-for-long-form","slug":"graph-based-uncertainty-metrics-for-long-form","title":"Graph-based Uncertainty Metrics for Long-form Language Model Outputs","date":"2024-10-28","arxiv_id":"2410.20783","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/graph-based-uncertainty-metrics-for-long-form#ran","syntology_url":"https://syntology.ai/paper/2410.20783","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20783"}},"official":{"repos":["mingjianjiang-1/graph-based-uncertainty"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/uncovering-autoregressive-llm-knowledge-of","slug":"uncovering-autoregressive-llm-knowledge-of","title":"Uncovering Autoregressive LLM Knowledge of Thematic Fit in Event Representation","date":"2024-10-19","arxiv_id":"2410.15173","repositories_listed":1,"syntology":null},{"url":"/paper/logu-long-form-generation-with-uncertainty","slug":"logu-long-form-generation-with-uncertainty","title":"LoGU: Long-form Generation with Uncertainty Expressions","date":"2024-10-18","arxiv_id":"2410.14309","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/logu-long-form-generation-with-uncertainty#ran","syntology_url":"https://syntology.ai/paper/2410.14309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14309"}},"official":{"repos":["rhyang2021/logu"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/atomic-calibration-of-llms-in-long-form","slug":"atomic-calibration-of-llms-in-long-form","title":"Atomic Calibration of LLMs in Long-Form Generations","date":"2024-10-17","arxiv_id":"2410.13246","repositories_listed":1,"syntology":null},{"url":"/paper/measuring-free-form-decision-making","slug":"measuring-free-form-decision-making","title":"Measuring Free-Form Decision-Making Inconsistency of Language Models in Military Crisis Simulations","date":"2024-10-17","arxiv_id":"2410.13204","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/measuring-free-form-decision-making#ran","syntology_url":"https://syntology.ai/paper/2410.13204","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13204"}},"official":{"repos":["aashrivastava/llmwargaminginconsistency"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-claim-decomposition-benchmark-for-long-form","slug":"a-claim-decomposition-benchmark-for-long-form","title":"A Claim Decomposition Benchmark for Long-form Answer Verification","date":"2024-10-16","arxiv_id":"2410.12558","repositories_listed":1,"syntology":null},{"url":"/paper/ls-eend-long-form-streaming-end-to-end-neural","slug":"ls-eend-long-form-streaming-end-to-end-neural","title":"LS-EEND: Long-Form Streaming End-to-End Neural Diarization with Online Attractor Extraction","date":"2024-10-09","arxiv_id":"2410.06670","repositories_listed":1,"syntology":null},{"url":"/paper/riemann-sum-optimization-for-accurate","slug":"riemann-sum-optimization-for-accurate","title":"Riemann Sum Optimization for Accurate Integrated Gradients Computation","date":"2024-10-05","arxiv_id":"2410.04118","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/riemann-sum-optimization-for-accurate#ran","syntology_url":"https://syntology.ai/paper/2410.04118","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04118"}},"official":{"repos":["ShreeSinghi/RiemannOpt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/factalign-long-form-factuality-alignment-of","slug":"factalign-long-form-factuality-alignment-of","title":"FactAlign: Long-form Factuality Alignment of Large Language Models","date":"2024-10-02","arxiv_id":"2410.01691","repositories_listed":1,"syntology":null},{"url":"/paper/segment-as-you-wish-free-form-language-based","slug":"segment-as-you-wish-free-form-language-based","title":"Segment as You Wish -- Free-Form Language-Based Segmentation for Medical Images","date":"2024-10-02","arxiv_id":"2410.12831","repositories_listed":1,"syntology":null},{"url":"/paper/input-to-state-stable-coupled-oscillator","slug":"input-to-state-stable-coupled-oscillator","title":"Input-to-State Stable Coupled Oscillator Networks for Closed-form Model-based Control in Latent Space","date":"2024-09-13","arxiv_id":"2409.08439","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/input-to-state-stable-coupled-oscillator#ran","syntology_url":"https://syntology.ai/paper/2409.08439","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.08439"}},"official":{"repos":["tud-phi/uncovering-iss-coupled-oscillator-networks-from-pixels"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-patronizing-and-condescending","slug":"towards-patronizing-and-condescending","title":"Towards Patronizing and Condescending Language in Chinese Videos: A Multimodal Dataset and Detector","date":"2024-09-08","arxiv_id":"2409.05005","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-episodes-and-semantics-a-novel","slug":"bridging-episodes-and-semantics-a-novel","title":"HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics","date":"2024-08-30","arxiv_id":"2408.17443","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/bridging-episodes-and-semantics-a-novel#ran","syntology_url":"https://syntology.ai/paper/2408.17443","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.17443"}},"official":{"repos":["joslefaure/HERMES"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/near-optimal-policy-identification-in-robust","slug":"near-optimal-policy-identification-in-robust","title":"Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form","date":"2024-08-29","arxiv_id":"2408.16286","repositories_listed":1,"syntology":null},{"url":"/paper/grounded-multi-hop-videoqa-in-long-form","slug":"grounded-multi-hop-videoqa-in-long-form","title":"Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos","date":"2024-08-26","arxiv_id":"2408.14469","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/grounded-multi-hop-videoqa-in-long-form#ran","syntology_url":"https://syntology.ai/paper/2408.14469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.14469"}},"official":null}},{"url":"/paper/liteefg-an-efficient-python-library-for","slug":"liteefg-an-efficient-python-library-for","title":"LiteEFG: An Efficient Python Library for Solving Extensive-form Games","date":"2024-07-29","arxiv_id":"2407.20351","repositories_listed":1,"syntology":null},{"url":"/paper/rag-qa-arena-evaluating-domain-robustness-for","slug":"rag-qa-arena-evaluating-domain-robustness-for","title":"RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering","date":"2024-07-19","arxiv_id":"2407.13998","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rag-qa-arena-evaluating-domain-robustness-for#ran","syntology_url":"https://syntology.ai/paper/2407.13998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13998"}},"official":{"repos":["awslabs/rag-qa-arena"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/fine-grained-hallucination-detection-and-1","slug":"fine-grained-hallucination-detection-and-1","title":"Localizing and Mitigating Errors in Long-form Question Answering","date":"2024-07-16","arxiv_id":"2407.11930","repositories_listed":1,"syntology":null},{"url":"/paper/controlling-whisper-universal-acoustic","slug":"controlling-whisper-universal-acoustic","title":"Controlling Whisper: Universal Acoustic Adversarial Attacks to Control Speech Foundation Models","date":"2024-07-05","arxiv_id":"2407.04482","repositories_listed":1,"syntology":null},{"url":"/paper/integrate-the-essence-and-eliminate-the-dross","slug":"integrate-the-essence-and-eliminate-the-dross","title":"Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation","date":"2024-07-02","arxiv_id":"2407.02056","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/integrate-the-essence-and-eliminate-the-dross#ran","syntology_url":"https://syntology.ai/paper/2407.02056","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02056"}},"official":{"repos":["WangXinglin/FSC"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/sonnet-or-not-bot-poetry-evaluation-for-large","slug":"sonnet-or-not-bot-poetry-evaluation-for-large","title":"Sonnet or Not, Bot? Poetry Evaluation for Large Models and Datasets","date":"2024-06-27","arxiv_id":"2406.18906","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sonnet-or-not-bot-poetry-evaluation-for-large#ran","syntology_url":"https://syntology.ai/paper/2406.18906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18906"}},"official":{"repos":["maria-antoniak/poetry-eval"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/suri-multi-constraint-instruction-following","slug":"suri-multi-constraint-instruction-following","title":"Suri: Multi-constraint Instruction Following for Long-form Text Generation","date":"2024-06-27","arxiv_id":"2406.19371","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":11,"n_pointer_only":15,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/suri-multi-constraint-instruction-following#ran","syntology_url":"https://syntology.ai/paper/2406.19371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19371"}},"official":{"repos":["chtmp223/suri"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/veriscore-evaluating-the-factuality-of","slug":"veriscore-evaluating-the-factuality-of","title":"VERISCORE: Evaluating the factuality of verifiable claims in long-form text generation","date":"2024-06-27","arxiv_id":"2406.19276","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/veriscore-evaluating-the-factuality-of#ran","syntology_url":"https://syntology.ai/paper/2406.19276","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19276"}},"official":{"repos":["Yixiao-Song/VeriScore"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/calmqa-exploring-culturally-specific-long","slug":"calmqa-exploring-culturally-specific-long","title":"CaLMQA: Exploring culturally specific long-form question answering across 23 languages","date":"2024-06-25","arxiv_id":"2406.17761","repositories_listed":1,"syntology":null},{"url":"/paper/lumberchunker-long-form-narrative-document","slug":"lumberchunker-long-form-narrative-document","title":"LumberChunker: Long-Form Narrative Document Segmentation","date":"2024-06-25","arxiv_id":"2406.17526","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lumberchunker-long-form-narrative-document#ran","syntology_url":"https://syntology.ai/paper/2406.17526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17526"}},"official":{"repos":["joaodsmarques/lumberchunker"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/homomorphisms-and-embeddings-of-strips","slug":"homomorphisms-and-embeddings-of-strips","title":"Homomorphisms and Embeddings of STRIPS Planning Models","date":"2024-06-24","arxiv_id":"2406.16555","repositories_listed":1,"syntology":null},{"url":"/paper/mmbench-video-a-long-form-multi-shot","slug":"mmbench-video-a-long-form-multi-shot","title":"MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding","date":"2024-06-20","arxiv_id":"2406.14515","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mmbench-video-a-long-form-multi-shot#ran","syntology_url":"https://syntology.ai/paper/2406.14515","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14515"}},"official":{"repos":["open-compass/vlmevalkit"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/analyzing-key-neurons-in-large-language","slug":"analyzing-key-neurons-in-large-language","title":"Identifying Query-Relevant Neurons in Large Language Models for Long-Form Texts","date":"2024-06-16","arxiv_id":"2406.10868","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/analyzing-key-neurons-in-large-language#ran","syntology_url":"https://syntology.ai/paper/2406.10868","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10868"}},"official":{"repos":["tigerchen52/qrneuron"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/kolmogorov-arnold-informed-neural-network-a","slug":"kolmogorov-arnold-informed-neural-network-a","title":"Kolmogorov Arnold Informed neural network: A physics-informed deep learning framework for solving forward and inverse problems based on Kolmogorov Arnold Networks","date":"2024-06-16","arxiv_id":"2406.11045","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/kolmogorov-arnold-informed-neural-network-a#ran","syntology_url":"https://syntology.ai/paper/2406.11045","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11045"}},"official":{"repos":["yizheng-wang/research-on-solving-partial-differential-equations-of-solid-mechanics-based-on-pinn"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/chiron-rich-character-representations-in-long","slug":"chiron-rich-character-representations-in-long","title":"CHIRON: Rich Character Representations in Long-Form Narratives","date":"2024-06-14","arxiv_id":"2406.10190","repositories_listed":1,"syntology":null},{"url":"/paper/rapport-driven-virtual-agent-rapport-building","slug":"rapport-driven-virtual-agent-rapport-building","title":"Rapport-Driven Virtual Agent: Rapport Building Dialogue Strategy for Improving User Experience at First Meeting","date":"2024-06-14","arxiv_id":"2406.09839","repositories_listed":1,"syntology":null},{"url":"/paper/too-many-frames-not-all-useful-efficient","slug":"too-many-frames-not-all-useful-efficient","title":"Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA","date":"2024-06-13","arxiv_id":"2406.09396","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/too-many-frames-not-all-useful-efficient#ran","syntology_url":"https://syntology.ai/paper/2406.09396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09396"}},"official":{"repos":["jongwoopark7978/LVNet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/encoding-and-controlling-global-semantics-for","slug":"encoding-and-controlling-global-semantics-for","title":"Encoding and Controlling Global Semantics for Long-form Video Question Answering","date":"2024-05-30","arxiv_id":"2405.19723","repositories_listed":1,"syntology":null},{"url":"/paper/toward-conversational-agents-with-context-and","slug":"toward-conversational-agents-with-context-and","title":"Toward Conversational Agents with Context and Time Sensitive Long-term Memory","date":"2024-05-29","arxiv_id":"2406.00057","repositories_listed":1,"syntology":null},{"url":"/paper/olaph-improving-factuality-in-biomedical-long","slug":"olaph-improving-factuality-in-biomedical-long","title":"OLAPH: Improving Factuality in Biomedical Long-form Question Answering","date":"2024-05-21","arxiv_id":"2405.12701","repositories_listed":1,"syntology":null},{"url":"/paper/throne-an-object-based-hallucination","slug":"throne-an-object-based-hallucination","title":"THRONE: An Object-based Hallucination Benchmark for the Free-form Generations of Large Vision-Language Models","date":"2024-05-08","arxiv_id":"2405.05256","repositories_listed":1,"syntology":null},{"url":"/paper/geometry-aware-framework-for-deep-energy","slug":"geometry-aware-framework-for-deep-energy","title":"Geometry-aware framework for deep energy method: an application to structural mechanics with hyperelastic materials","date":"2024-05-06","arxiv_id":"2405.03427","repositories_listed":1,"syntology":null},{"url":"/paper/learning-long-form-video-prior-via-generative","slug":"learning-long-form-video-prior-via-generative","title":"Learning Long-form Video Prior via Generative Pre-Training","date":"2024-04-24","arxiv_id":"2404.15909","repositories_listed":1,"syntology":null},{"url":"/paper/from-form-s-to-meaning-probing-the-semantic","slug":"from-form-s-to-meaning-probing-the-semantic","title":"From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistency","date":"2024-04-18","arxiv_id":"2404.12145","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/from-form-s-to-meaning-probing-the-semantic#ran","syntology_url":"https://syntology.ai/paper/2404.12145","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12145"}},"official":{"repos":["facebookresearch/multisense_consistency"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/ntire-2024-challenge-on-short-form-ugc-video","slug":"ntire-2024-challenge-on-short-form-ugc-video","title":"NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results","date":"2024-04-17","arxiv_id":"2404.11313","repositories_listed":1,"syntology":null},{"url":"/paper/paraphrase-and-solve-exploring-and-exploiting","slug":"paraphrase-and-solve-exploring-and-exploiting","title":"Paraphrase and Solve: Exploring and Exploiting the Impact of Surface Form on Mathematical Reasoning in Large Language Models","date":"2024-04-17","arxiv_id":"2404.11500","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/paraphrase-and-solve-exploring-and-exploiting#ran","syntology_url":"https://syntology.ai/paper/2404.11500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.11500"}},"official":{"repos":["yue-llm-pit/scop"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/long-form-music-generation-with-latent","slug":"long-form-music-generation-with-latent","title":"Long-form music generation with latent diffusion","date":"2024-04-16","arxiv_id":"2404.10301","repositories_listed":1,"syntology":null},{"url":"/paper/shape-arithmetic-expressions-advancing","slug":"shape-arithmetic-expressions-advancing","title":"Shape Arithmetic Expressions: Advancing Scientific Discovery Beyond Closed-Form Equations","date":"2024-04-15","arxiv_id":"2404.09788","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/shape-arithmetic-expressions-advancing#ran","syntology_url":"https://syntology.ai/paper/2404.09788","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09788"}},"official":{"repos":["krzysztof-kacprzyk/shares"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-solution-for-the-mean-parametrization-of","slug":"a-solution-for-the-mean-parametrization-of","title":"A solution for the mean parametrization of the von Mises-Fisher distribution","date":"2024-04-10","arxiv_id":"2404.07358","repositories_listed":1,"syntology":null},{"url":"/paper/knowhalu-hallucination-detection-via-multi","slug":"knowhalu-hallucination-detection-via-multi","title":"KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking","date":"2024-04-03","arxiv_id":"2404.02935","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/knowhalu-hallucination-detection-via-multi#ran","syntology_url":"https://syntology.ai/paper/2404.02935","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02935"}},"official":{"repos":["javyduck/knowhalu"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/clapnq-cohesive-long-form-answers-from","slug":"clapnq-cohesive-long-form-answers-from","title":"CLAPNQ: Cohesive Long-form Answers from Passages in Natural Questions for RAG systems","date":"2024-04-02","arxiv_id":"2404.02103","repositories_listed":1,"syntology":null},{"url":"/paper/linguistic-calibration-of-language-models","slug":"linguistic-calibration-of-language-models","title":"Linguistic Calibration of Long-Form Generations","date":"2024-03-30","arxiv_id":"2404.00474","repositories_listed":1,"syntology":null},{"url":"/paper/an-execution-time-certified-qp-algorithm-for","slug":"an-execution-time-certified-qp-algorithm-for","title":"A Parallel Vector-form $LDL^\\top$ Decomposition for Accelerating Execution-time-certified $\\ell_1$-penalty Soft-constrained MPC","date":"2024-03-27","arxiv_id":"2403.18235","repositories_listed":1,"syntology":null},{"url":"/paper/do-deep-neural-network-solutions-form-a-star","slug":"do-deep-neural-network-solutions-form-a-star","title":"Do Deep Neural Network Solutions Form a Star Domain?","date":"2024-03-12","arxiv_id":"2403.07968","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/do-deep-neural-network-solutions-form-a-star#ran","syntology_url":"https://syntology.ai/paper/2403.07968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07968"}},"official":{"repos":["aktsonthalia/starlight"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/evidence-focused-fact-summarization-for","slug":"evidence-focused-fact-summarization-for","title":"Evidence-Focused Fact Summarization for Knowledge-Augmented Zero-Shot Question Answering","date":"2024-03-05","arxiv_id":"2403.02966","repositories_listed":1,"syntology":{"n":16,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":16,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/evidence-focused-fact-summarization-for#ran","syntology_url":"https://syntology.ai/paper/2403.02966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02966"}},"official":{"repos":["anon809/efsum"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/m3-vrd-multimodal-multi-task-multi-teacher","slug":"m3-vrd-multimodal-multi-task-multi-teacher","title":"3MVRD: Multimodal Multi-task Multi-teacher Visually-Rich Form Document Understanding","date":"2024-02-28","arxiv_id":"2402.17983","repositories_listed":1,"syntology":null},{"url":"/paper/multi-fact-assessing-multilingual-llms-multi","slug":"multi-fact-assessing-multilingual-llms-multi","title":"Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore","date":"2024-02-28","arxiv_id":"2402.18045","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":6,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multi-fact-assessing-multilingual-llms-multi#ran","syntology_url":"https://syntology.ai/paper/2402.18045","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18045"}},"official":{"repos":["sheikhshafayat/multi-fact"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/retrievalqa-assessing-adaptive-retrieval","slug":"retrievalqa-assessing-adaptive-retrieval","title":"RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering","date":"2024-02-26","arxiv_id":"2402.16457","repositories_listed":1,"syntology":null},{"url":"/paper/pqa-zero-shot-protein-question-answering-for","slug":"pqa-zero-shot-protein-question-answering-for","title":"PQA: Zero-shot Protein Question Answering for Free-form Scientific Enquiry with Large Language Models","date":"2024-02-21","arxiv_id":"2402.13653","repositories_listed":1,"syntology":null},{"url":"/paper/fipo-free-form-instruction-oriented-prompt","slug":"fipo-free-form-instruction-oriented-prompt","title":"FIPO: Free-form Instruction-oriented Prompt Optimization with Preference Dataset and Modular Fine-tuning Schema","date":"2024-02-19","arxiv_id":"2402.11811","repositories_listed":1,"syntology":null},{"url":"/paper/panda-pedantic-answer-correctness","slug":"panda-pedantic-answer-correctness","title":"PEDANTS: Cheap but Effective and Interpretable Answer Equivalence","date":"2024-02-17","arxiv_id":"2402.11161","repositories_listed":1,"syntology":null},{"url":"/paper/unlocking-structure-measuring-introducing-pdd","slug":"unlocking-structure-measuring-introducing-pdd","title":"Unlocking Structure Measuring: Introducing PDD, an Automatic Metric for Positional Discourse Coherence","date":"2024-02-15","arxiv_id":"2402.10175","repositories_listed":1,"syntology":null},{"url":"/paper/comment-aided-video-language-alignment-via","slug":"comment-aided-video-language-alignment-via","title":"Comment-aided Video-Language Alignment via Contrastive Pre-training for Short-form Video Humor Detection","date":"2024-02-14","arxiv_id":"2402.09055","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/comment-aided-video-language-alignment-via#ran","syntology_url":"https://syntology.ai/paper/2402.09055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09055"}},"official":{"repos":["yliu-cs/cvla"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/long-form-evaluation-of-model-editing","slug":"long-form-evaluation-of-model-editing","title":"Long-form evaluation of model editing","date":"2024-02-14","arxiv_id":"2402.09394","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/long-form-evaluation-of-model-editing#ran","syntology_url":"https://syntology.ai/paper/2402.09394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09394"}},"official":{"repos":["domenicrosati/longform-evaluation-model-editing"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/gradient-flow-adaptive-importance-sampling","slug":"gradient-flow-adaptive-importance-sampling","title":"Perturbative partial moment matching and gradient-flow adaptive importance sampling transformations for Bayesian leave one out cross-validation","date":"2024-02-13","arxiv_id":"2402.08151","repositories_listed":1,"syntology":null},{"url":"/paper/kvq-kaleidoscope-video-quality-assessment-for","slug":"kvq-kaleidoscope-video-quality-assessment-for","title":"KVQ: Kwai Video Quality Assessment for Short-form Videos","date":"2024-02-11","arxiv_id":"2402.07220","repositories_listed":1,"syntology":{"n":28,"n_ran":22,"n_constructed":10,"n_ran_checked":15,"n_instrument":7,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":14,"n_pointer_only":28,"phrase":"22 ran (of which 10 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 0 violated, 14 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/kvq-kaleidoscope-video-quality-assessment-for#ran","syntology_url":"https://syntology.ai/paper/2402.07220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07220"}},"official":null}},{"url":"/paper/calibrating-long-form-generations-from-large","slug":"calibrating-long-form-generations-from-large","title":"Calibrating Long-form Generations from Large Language Models","date":"2024-02-09","arxiv_id":"2402.06544","repositories_listed":1,"syntology":null},{"url":"/paper/merging-facts-crafting-fallacies-evaluating","slug":"merging-facts-crafting-fallacies-evaluating","title":"Merging Facts, Crafting Fallacies: Evaluating the Contradictory Nature of Aggregated Factual Claims in Long-Form Generations","date":"2024-02-08","arxiv_id":"2402.05629","repositories_listed":1,"syntology":null},{"url":"/paper/internlm-xcomposer2-mastering-free-form-text","slug":"internlm-xcomposer2-mastering-free-form-text","title":"InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model","date":"2024-01-29","arxiv_id":"2401.16420","repositories_listed":1,"syntology":null},{"url":"/paper/chemdfm-dialogue-foundation-model-for","slug":"chemdfm-dialogue-foundation-model-for","title":"ChemDFM: A Large Language Foundation Model for Chemistry","date":"2024-01-26","arxiv_id":"2401.14818","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/chemdfm-dialogue-foundation-model-for#ran","syntology_url":"https://syntology.ai/paper/2401.14818","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.14818"}},"official":null}},{"url":"/paper/proxyqa-an-alternative-framework-for","slug":"proxyqa-an-alternative-framework-for","title":"PROXYQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models","date":"2024-01-26","arxiv_id":"2401.15042","repositories_listed":1,"syntology":null},{"url":"/paper/linear-alignment-a-closed-form-solution-for","slug":"linear-alignment-a-closed-form-solution-for","title":"Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback","date":"2024-01-21","arxiv_id":"2401.11458","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/linear-alignment-a-closed-form-solution-for#ran","syntology_url":"https://syntology.ai/paper/2401.11458","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.11458"}},"official":{"repos":["wizardcoast/linear_alignment"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/closed-form-interpretation-of-neural-network","slug":"closed-form-interpretation-of-neural-network","title":"Closed-Form Interpretation of Neural Network Classifiers with Symbolic Gradients","date":"2024-01-10","arxiv_id":"2401.04978","repositories_listed":1,"syntology":null},{"url":"/paper/families-of-costs-with-zero-and-nonnegative","slug":"families-of-costs-with-zero-and-nonnegative","title":"Families of costs with zero and nonnegative MTW tensor in optimal transport","date":"2024-01-01","arxiv_id":"2401.00953","repositories_listed":1,"syntology":null},{"url":"/paper/detecting-anxiety-from-short-clips-of-free","slug":"detecting-anxiety-from-short-clips-of-free","title":"Detecting anxiety from short clips of free-form speech","date":"2023-12-23","arxiv_id":"2312.15272","repositories_listed":1,"syntology":null},{"url":"/paper/reducing-shape-radiance-ambiguity-in-radiance-1","slug":"reducing-shape-radiance-ambiguity-in-radiance-1","title":"Reducing Shape-Radiance Ambiguity in Radiance Fields with a Closed-Form Color Estimation Method","date":"2023-12-20","arxiv_id":"2312.12726","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/reducing-shape-radiance-ambiguity-in-radiance-1#ran","syntology_url":"https://syntology.ai/paper/2312.12726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12726"}},"official":{"repos":["qihanggh/closed-form-color-field"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-distributions-on-manifolds-with-free","slug":"learning-distributions-on-manifolds-with-free","title":"Learning Distributions on Manifolds with Free-Form Flows","date":"2023-12-15","arxiv_id":"2312.09852","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-distributions-on-manifolds-with-free#ran","syntology_url":"https://syntology.ai/paper/2312.09852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09852"}},"official":{"repos":["vislearn/fff"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/lifelongmemory-leveraging-llms-for-answering","slug":"lifelongmemory-leveraging-llms-for-answering","title":"LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos","date":"2023-12-07","arxiv_id":"2312.05269","repositories_listed":1,"syntology":null},{"url":"/paper/action-scene-graphs-for-long-form","slug":"action-scene-graphs-for-long-form","title":"Action Scene Graphs for Long-Form Understanding of Egocentric Videos","date":"2023-12-06","arxiv_id":"2312.03391","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/action-scene-graphs-for-long-form#ran","syntology_url":"https://syntology.ai/paper/2312.03391","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03391"}},"official":{"repos":["fpv-iplab/easg"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/emotions-a-large-scale-dataset-for-emotion","slug":"emotions-a-large-scale-dataset-for-emotion","title":"Towards Emotion Analysis in Short-form Videos: A Large-Scale Dataset and Baseline","date":"2023-11-29","arxiv_id":"2311.17335","repositories_listed":1,"syntology":null},{"url":"/paper/performance-trade-offs-of-watermarking-large","slug":"performance-trade-offs-of-watermarking-large","title":"Downstream Trade-offs of a Family of Text Watermarks","date":"2023-11-16","arxiv_id":"2311.09816","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/performance-trade-offs-of-watermarking-large#ran","syntology_url":"https://syntology.ai/paper/2311.09816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09816"}},"official":{"repos":["flair-iisc/watermark_tradeoffs"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-pacing-in-long-form-story-planning","slug":"improving-pacing-in-long-form-story-planning","title":"Improving Pacing in Long-Form Story Planning","date":"2023-11-08","arxiv_id":"2311.04459","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":17,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/improving-pacing-in-long-form-story-planning#ran","syntology_url":"https://syntology.ai/paper/2311.04459","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.04459"}},"official":{"repos":["yichenzw/pacing"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/the-effect-of-scaling-retrieval-augmentation","slug":"the-effect-of-scaling-retrieval-augmentation","title":"The Effect of Scaling, Retrieval Augmentation and Form on the Factual Consistency of Language Models","date":"2023-11-02","arxiv_id":"2311.01307","repositories_listed":1,"syntology":null},{"url":"/paper/robust-and-conjugate-gaussian-process","slug":"robust-and-conjugate-gaussian-process","title":"Robust and Conjugate Gaussian Process Regression","date":"2023-11-01","arxiv_id":"2311.00463","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/robust-and-conjugate-gaussian-process#ran","syntology_url":"https://syntology.ai/paper/2311.00463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.00463"}},"official":{"repos":["maltamiranomontero/RCGP"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/litcab-lightweight-calibration-of-language","slug":"litcab-lightweight-calibration-of-language","title":"LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses","date":"2023-10-30","arxiv_id":"2310.19208","repositories_listed":1,"syntology":null}],"record_sha256":"e0f5e1210984c78e007698f3acdde0037193f49bdc2831bf6549bf3e37ce981b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}