{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/code/summarize","entry":"summarize","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":36,"n_papers_ran":17,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":38,"n_samples_ran":18,"n_samples_fingerprinted":3,"n_places":38,"n_places_pointer_only":10,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":15,"unverified":20},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2609.15657","paper":"/paper/arxiv-2609-15657","title":"Predictive Likelihood Ratios for Language Model Watermark Detection","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"MaStatLab/PLRWatermark","path":"code/check_delta_learning.py","file_url":"https://github.com/MaStatLab/PLRWatermark/blob/HEAD/code/check_delta_learning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"030536d64258273e","mcp_get_code":{"code_sha256":"030536d64258273e"}},{"arxiv_id":"2609.00275","paper":"/paper/arxiv-2609-00275","title":"The Irreversibility Budget: Fleet-Level Risk Accounting and Admission Control for Agent Operating Systems","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"mpi-dsg/irreversibility-budget","path":"sim/bench.py","file_url":"https://github.com/mpi-dsg/irreversibility-budget/blob/HEAD/sim/bench.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0bea42f07041d51a","mcp_get_code":{"code_sha256":"0bea42f07041d51a"}},{"arxiv_id":"2608.24229","paper":"/paper/arxiv-2608-24229","title":"A Theory of Finite-Noise Optima and Generalization in Quantum Machine Learning","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"dongsnaq/Finite-Noise-Generalization-QML","path":"code/plot_figures.py","file_url":"https://github.com/dongsnaq/Finite-Noise-Generalization-QML/blob/HEAD/code/plot_figures.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bf0c07b92ddcb985","mcp_get_code":{"code_sha256":"bf0c07b92ddcb985"}},{"arxiv_id":"2608.23468","paper":"/paper/arxiv-2608-23468","title":"RAD: Rule-Augmented Relational Anomaly Detection","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"noahd15/RAD_RelationalAnomalyDetection","path":"lanl/run_lanl_six_ablations.py","file_url":"https://github.com/noahd15/RAD_RelationalAnomalyDetection/blob/HEAD/lanl/run_lanl_six_ablations.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e9da42fee1d55f3a","mcp_get_code":{"code_sha256":"e9da42fee1d55f3a"}},{"arxiv_id":"2608.15286","paper":"/paper/arxiv-2608-15286","title":"No Task Fails Every Time: Why One-Shot Audits Are Structurally Blind to Agent Damage","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"shivenkk/agentrelbench","path":"src/agentrelbench/labeler.py","file_url":"https://github.com/shivenkk/agentrelbench/blob/HEAD/src/agentrelbench/labeler.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d88835e538dad227","mcp_get_code":{"code_sha256":"d88835e538dad227"}},{"arxiv_id":"2608.13329","paper":"/paper/arxiv-2608-13329","title":"A Probe Direction Is a Property of Its Prompt","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"vcnoel/probe-direction","path":"src/eval_awareness_spectral/freq_decomp.py","file_url":"https://github.com/vcnoel/probe-direction/blob/HEAD/src/eval_awareness_spectral/freq_decomp.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"code_sha256_prefix":"40f69d5078efb5e3","mcp_get_code":{"code_sha256":"40f69d5078efb5e3"}},{"arxiv_id":"2608.09988","paper":"/paper/arxiv-2608-09988","title":"OpenPM: Auditable Point-in-Time Evaluation for LLM Portfolio-Management Agents","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"aslcai/OpenPM-Bench","path":"agents/feature_validation.py","file_url":"https://github.com/aslcai/OpenPM-Bench/blob/HEAD/agents/feature_validation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c03077de44bf2a39","mcp_get_code":{"code_sha256":"c03077de44bf2a39"}},{"arxiv_id":"2608.06305","paper":"/paper/arxiv-2608-06305","title":"Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"twospoon/READ","path":"read_eval/provenance.py","file_url":"https://github.com/twospoon/READ/blob/HEAD/read_eval/provenance.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6a7e660ff0f3240d","mcp_get_code":{"code_sha256":"6a7e660ff0f3240d"}},{"arxiv_id":"2606.28572","paper":"/paper/arxiv-2606-28572","title":"Geometric Measurements of the Axiom of Choice in Neural Proof Embeddings","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"rodrgo/geometric-axiom-of-choice","path":"experiments/anomaly_auc_bootstrap.py","file_url":"https://github.com/rodrgo/geometric-axiom-of-choice/blob/HEAD/experiments/anomaly_auc_bootstrap.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"647a50dc109d100a","mcp_get_code":{"code_sha256":"647a50dc109d100a"}},{"arxiv_id":"2606.19605","paper":"/paper/arxiv-2606-19605","title":"FAPO: Fully Automated Prompt Optimization of Multi-Step LLM Pipelines","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"cisco-foundation-ai/fully-automated-prompt-optimization","path":"src/hephaestus/analysis/step_attribution.py","file_url":"https://github.com/cisco-foundation-ai/fully-automated-prompt-optimization/blob/HEAD/src/hephaestus/analysis/step_attribution.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1c1c3a0f184a196d","mcp_get_code":{"code_sha256":"1c1c3a0f184a196d"}},{"arxiv_id":"2605.25816","paper":"/paper/arxiv-2605-25816","title":"Fine-Tuning Over Architectural Complexity: Broad-Coverage PII Detection on PIIBench with DeBERTa","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"pritesh-2711/pii-bench","path":"create_evaluation_subset.py","file_url":"https://github.com/pritesh-2711/pii-bench/blob/HEAD/create_evaluation_subset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8684c083b2001da7","mcp_get_code":{"code_sha256":"8684c083b2001da7"}},{"arxiv_id":"2605.25663","paper":"/paper/arxiv-2605-25663","title":"Opportunistic Target Selection: Early Directional Commitment for Query-Efficient Black-Box Adversarial Attacks","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Tariolle/opportunistic-target-selection","path":"analysis/analyze_oracle_beat.py","file_url":"https://github.com/Tariolle/opportunistic-target-selection/blob/HEAD/analysis/analyze_oracle_beat.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f765883ce1ccc896","mcp_get_code":{"code_sha256":"f765883ce1ccc896"}},{"arxiv_id":"2605.21325","paper":"/paper/arxiv-2605-21325","title":"Fast and Stable Triangular Inversion for Delta-Rule Linear Transformers","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"huawei-csl/pto-kernels","path":".skills/testing-pto-kernels/reference/dynamic_multi_core/a2a3/benchmark.py","file_url":"https://github.com/huawei-csl/pto-kernels/blob/HEAD/.skills/testing-pto-kernels/reference/dynamic_multi_core/a2a3/benchmark.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause-Clear","inline_ok":false,"code_sha256_prefix":"7140e33bf7bef21f","mcp_get_code":{"code_sha256":"7140e33bf7bef21f"}},{"arxiv_id":"2605.14066","paper":"/paper/arxiv-2605-14066","title":"A Benchmark for Early-stage Parkinson's Disease Detection from Speech","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"terryyizhongru/B-EarlyPD-Speech","path":"preprocess_scripts/compare_wavs.py","file_url":"https://github.com/terryyizhongru/B-EarlyPD-Speech/blob/HEAD/preprocess_scripts/compare_wavs.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"aa682e0bdcadde07","mcp_get_code":{"code_sha256":"aa682e0bdcadde07"}},{"arxiv_id":"2605.09285","paper":"/paper/arxiv-2605-09285","title":"BetaEdit: Null-Space Constrained Sequential Model Editing","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"lbq8942/BetaEdit","path":"BetaEdit/evals/counterfact.py","file_url":"https://github.com/lbq8942/BetaEdit/blob/HEAD/BetaEdit/evals/counterfact.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4dd1d94c025b582c","mcp_get_code":{"code_sha256":"4dd1d94c025b582c"}},{"arxiv_id":"2605.09285","paper":"/paper/arxiv-2605-09285","title":"BetaEdit: Null-Space Constrained Sequential Model Editing","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"lbq8942/BetaEdit","path":"BetaEdit/evals/lbqeval.py","file_url":"https://github.com/lbq8942/BetaEdit/blob/HEAD/BetaEdit/evals/lbqeval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f6c253651c4634e7","mcp_get_code":{"code_sha256":"f6c253651c4634e7"}},{"arxiv_id":"2605.01336","paper":"/paper/arxiv-2605-01336","title":"A Multi-View Media Profiling Suite: Resources, Evaluation, and Analysis","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"codelucas/newspaper","path":"newspaper/nlp.py","file_url":"https://github.com/codelucas/newspaper/blob/HEAD/newspaper/nlp.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7809cbc4a95980a1","mcp_get_code":{"code_sha256":"7809cbc4a95980a1"}},{"arxiv_id":"2604.19457","paper":"/paper/arxiv-2604-19457","title":"Four-Axis Decision Alignment for Long-Horizon Enterprise AI Agents","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"vasundras/decision-alignment-long-horizon-agents","path":"pilot/run_pilot.py","file_url":"https://github.com/vasundras/decision-alignment-long-horizon-agents/blob/HEAD/pilot/run_pilot.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"02064d48663ddd5d","mcp_get_code":{"code_sha256":"02064d48663ddd5d"}},{"arxiv_id":"2604.18293","paper":"/paper/arxiv-2604-18293","title":"An Existence Proof for Neural Language Models That Can Explain Garden-Path Effects via Surprisal","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"osekilab/RE-GPE","path":"src/reverse_engineering/aggregate_blimp.py","file_url":"https://github.com/osekilab/RE-GPE/blob/HEAD/src/reverse_engineering/aggregate_blimp.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f9a7217d1b729cae","mcp_get_code":{"code_sha256":"f9a7217d1b729cae"}},{"arxiv_id":"2602.17975","paper":"/paper/arxiv-2602-17975","title":"Generating adversarial inputs for a graph neural network model of AC power flow","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Robbybp/pfdelta","path":"evaluate_adversarial_loss.py","file_url":"https://github.com/Robbybp/pfdelta/blob/HEAD/evaluate_adversarial_loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e4056ac646c29277","mcp_get_code":{"code_sha256":"e4056ac646c29277"}},{"arxiv_id":"2508.20718","paper":"/paper/arxiv-2508-20718","title":"Addressing Tokenization Inconsistency in Steganography and Watermarking Based on Large Language Models","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"ryehr/Consistency","path":"src/tokenization_consistency/investigation.py","file_url":"https://github.com/ryehr/Consistency/blob/HEAD/src/tokenization_consistency/investigation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b4e26afc7a14e237","mcp_get_code":{"code_sha256":"b4e26afc7a14e237"}},{"arxiv_id":"2412.09529","paper":"/paper/can-modern-llms-act-as-agent-cores-in","title":"Can Modern LLMs Act as Agent Cores in Radiology Environments?","date":"2024-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"magic-ai4med/radabench","path":"EvalPlat/AutoTB/protocol.py","file_url":"https://github.com/magic-ai4med/radabench/blob/HEAD/EvalPlat/AutoTB/protocol.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"36c920d5aee9be07","mcp_get_code":{"code_sha256":"36c920d5aee9be07"}},{"arxiv_id":"2410.20600","paper":"/paper/implementation-and-application-of-an","title":"Implementation and Application of an Intelligibility Protocol for Interaction with an LLM","date":"2024-10-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"karannb/interact","path":"src/utils.py","file_url":"https://github.com/karannb/interact/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5939f41f939a5624","mcp_get_code":{"code_sha256":"5939f41f939a5624"}},{"arxiv_id":"2410.02355","paper":"/paper/alphaedit-null-space-constrained-knowledge","title":"AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jianghoucheng/alphaedit","path":"experiments/summarize.py","file_url":"https://github.com/jianghoucheng/alphaedit/blob/HEAD/experiments/summarize.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"28017f0785c37c4d","mcp_get_code":{"code_sha256":"28017f0785c37c4d"}},{"arxiv_id":"2311.11177","paper":"/paper/assessing-the-security-of-github-copilot","title":"Assessing the Security of GitHub Copilot Generated Code -- A Targeted Replication Study","date":null,"month_inferred_from_arxiv_id":"2023-11","title_source":"archive","repo":"commissarsilver/cvt","path":"pycode_similar.py","file_url":"https://github.com/commissarsilver/cvt/blob/HEAD/pycode_similar.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a89e11279a4b75a7","mcp_get_code":{"code_sha256":"a89e11279a4b75a7"}},{"arxiv_id":"2309.05794","paper":"/paper/diffusion-based-adversarial-purification-for","title":"Robust Physics-based Deep MRI Reconstruction Via Diffusion Purification","date":"2023-09-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sjames40/adversarial-purification-for-mri","path":"evaluate_modl.py","file_url":"https://github.com/sjames40/adversarial-purification-for-mri/blob/HEAD/evaluate_modl.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"093d804309b5a998","mcp_get_code":{"code_sha256":"093d804309b5a998"}},{"arxiv_id":"2305.09955","paper":"/paper/cook-empowering-general-purpose-language","title":"Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models","date":"2023-05-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bunsenfeng/knowledge_card","path":"pruning.py","file_url":"https://github.com/bunsenfeng/knowledge_card/blob/HEAD/pruning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"94ba717ec9375d06","mcp_get_code":{"code_sha256":"94ba717ec9375d06"}},{"arxiv_id":"2210.17327","paper":"/paper/diffusion-based-generative-speech-source","title":"Diffusion-based Generative Speech Source Separation","date":"2022-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fakufaku/diffusion-separation","path":"evaluate.py","file_url":"https://github.com/fakufaku/diffusion-separation/blob/HEAD/evaluate.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3f0ed50b8555a67e","mcp_get_code":{"code_sha256":"3f0ed50b8555a67e"}},{"arxiv_id":"2210.17327","paper":"/paper/diffusion-based-generative-speech-source","title":"Diffusion-based Generative Speech Source Separation","date":"2022-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fakufaku/diffusion-separation","path":"evaluate.py","file_url":"https://github.com/fakufaku/diffusion-separation/blob/HEAD/evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0186314b1cbf6dc5","mcp_get_code":{"code_sha256":"0186314b1cbf6dc5"}},{"arxiv_id":"2207.08143","paper":"/paper/can-large-language-models-reason-about","title":"Can large language models reason about medical questions?","date":"2022-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vlievin/medical-reasoning","path":"medical_reasoning/datasets/stats.py","file_url":"https://github.com/vlievin/medical-reasoning/blob/HEAD/medical_reasoning/datasets/stats.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"58f5668b6dbca399","mcp_get_code":{"code_sha256":"58f5668b6dbca399"}},{"arxiv_id":"2206.03065","paper":"/paper/universal-speech-enhancement-with-score-based","title":"Universal Speech Enhancement with Score-based Diffusion","date":"2022-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"line/open-universe","path":"open_universe/bin/eval_metrics.py","file_url":"https://github.com/line/open-universe/blob/HEAD/open_universe/bin/eval_metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fc7210125c834983","mcp_get_code":{"code_sha256":"fc7210125c834983"}},{"arxiv_id":"1912.06218","paper":"/paper/yolact-better-real-time-instance-segmentation","title":"YOLACT++: Better Real-time Instance Segmentation","date":"2019-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bihanli/yolactBH","path":"run_coco_eval.py","file_url":"https://github.com/bihanli/yolactBH/blob/HEAD/run_coco_eval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2f9a6d5ca1bc906a","mcp_get_code":{"code_sha256":"2f9a6d5ca1bc906a"}},{"arxiv_id":"1906.08226","paper":"/paper/unsupervised-state-representation-learning-in","title":"Unsupervised State Representation Learning in Atari","date":"2019-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mengli11235/mst_dim","path":"visualize.py","file_url":"https://github.com/mengli11235/mst_dim/blob/HEAD/visualize.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c0759e56e428dd0","mcp_get_code":{"code_sha256":"8c0759e56e428dd0"}},{"arxiv_id":"1701.02426","paper":"/paper/scene-graph-generation-by-iterative-message","title":"Scene Graph Generation by Iterative Message Passing","date":"2017-01-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"joshuafeinglass/vl-detector-eval","path":"detector_benchmark/modified_coco_eval_summarize.py","file_url":"https://github.com/joshuafeinglass/vl-detector-eval/blob/HEAD/detector_benchmark/modified_coco_eval_summarize.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d206668e99641ddb","mcp_get_code":{"code_sha256":"d206668e99641ddb"}},{"arxiv_id":"1602.03606","paper":"/paper/variations-of-the-similarity-function-of","title":"Variations of the Similarity Function of TextRank for Automated Summarization","date":"2016-02-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"summanlp/textrank","path":"summa/summarizer.py","file_url":"https://github.com/summanlp/textrank/blob/HEAD/summa/summarizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ecc34edea14228d3","mcp_get_code":{"code_sha256":"ecc34edea14228d3"}},{"arxiv_id":"aaai_32078","paper":null,"title":"arXiv:aaai_32078","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"YifanZhang-git/SKAPP","path":"src/evaluate.py","file_url":"https://github.com/YifanZhang-git/SKAPP/blob/HEAD/src/evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f4e3ad40031b9bb8","mcp_get_code":{"code_sha256":"f4e3ad40031b9bb8"}},{"arxiv_id":"Zeng_Visual-Oriented_Fine-Grained_Knowledge_Editing_for_MultiModal_Large_Language_Models_ICCV_2025_paper","paper":null,"title":"arXiv:Zeng_Visual-Oriented_Fine-Grained_Knowledge_Editing_for_MultiModal_Large_Language_Models_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"zeng-zhen/FGVEdit","path":"edit_IKE.py","file_url":"https://github.com/zeng-zhen/FGVEdit/blob/HEAD/edit_IKE.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a9262ed351cea977","mcp_get_code":{"code_sha256":"a9262ed351cea977"}},{"arxiv_id":"2024.acl-long.732","paper":null,"title":"arXiv:2024.acl-long.732","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"wchrepo/mulfe","path":"evaluation/summary.py","file_url":"https://github.com/wchrepo/mulfe/blob/HEAD/evaluation/summary.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0a07c4044685d84b","mcp_get_code":{"code_sha256":"0a07c4044685d84b"}}]}