{"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/model-compression/papers/3","list_of":"/task/model-compression","task":"Model Compression","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":3,"pages_in_order":14,"rows_per_page":100,"rows":[201,300],"of":1356,"counts":{"archive_papers_tagged":1356,"with_a_code_link":440,"where_syntology_ran_a_sample":119,"not_listed_spam_title":0,"listed":1356,"listed_where_code_ran":119,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":97,"every_run_a_failure_of_syntologys_instrument":22,"listed_with_a_run_with_no_instrument_failure":97,"listed_every_run_a_failure_of_syntologys_instrument":22,"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/model-compression","prev":"/task/model-compression/papers/2","next":"/task/model-compression/papers/4","papers":[{"url":"/paper/crosskd-cross-head-knowledge-distillation-for","slug":"crosskd-cross-head-knowledge-distillation-for","title":"CrossKD: Cross-Head Knowledge Distillation for Object Detection","date":"2023-06-20","arxiv_id":"2306.11369","repositories_listed":1,"syntology":null},{"url":"/paper/hinerv-video-compression-with-hierarchical","slug":"hinerv-video-compression-with-hierarchical","title":"HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation","date":"2023-06-16","arxiv_id":"2306.09818","repositories_listed":1,"syntology":null},{"url":"/paper/a-brief-review-of-hypernetworks-in-deep","slug":"a-brief-review-of-hypernetworks-in-deep","title":"A Brief Review of Hypernetworks in Deep Learning","date":"2023-06-12","arxiv_id":"2306.06955","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"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) · 3 unverified","sample_list":"/paper/a-brief-review-of-hypernetworks-in-deep#ran","syntology_url":"https://syntology.ai/paper/2306.06955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.06955"}},"official":{"repos":["jmdvinodjmd/HyperITE"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-model-compression-also-helps-models","slug":"deep-model-compression-also-helps-models","title":"Deep Model Compression Also Helps Models Capture Ambiguity","date":"2023-06-12","arxiv_id":"2306.07061","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-quantization-aware-training-with","slug":"efficient-quantization-aware-training-with","title":"Efficient and Robust Quantization-aware Training via Adaptive Coreset Selection","date":"2023-06-12","arxiv_id":"2306.07215","repositories_listed":1,"syntology":{"n":12,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"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) · 7 unverified","sample_list":"/paper/efficient-quantization-aware-training-with#ran","syntology_url":"https://syntology.ai/paper/2306.07215","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.07215"}},"official":{"repos":["huangowen/qat-acs"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/mobilenmt-enabling-translation-in-15mb-and","slug":"mobilenmt-enabling-translation-in-15mb-and","title":"MobileNMT: Enabling Translation in 15MB and 30ms","date":"2023-06-07","arxiv_id":"2306.04235","repositories_listed":1,"syntology":null},{"url":"/paper/group-channel-pruning-and-spatial-attention","slug":"group-channel-pruning-and-spatial-attention","title":"Group channel pruning and spatial attention distilling for object detection","date":"2023-06-02","arxiv_id":"2306.01526","repositories_listed":1,"syntology":null},{"url":"/paper/pruning-meets-low-rank-parameter-efficient","slug":"pruning-meets-low-rank-parameter-efficient","title":"LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning","date":"2023-05-28","arxiv_id":"2305.18403","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/pruning-meets-low-rank-parameter-efficient#ran","syntology_url":"https://syntology.ai/paper/2305.18403","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18403"}},"official":{"repos":["aim-uofa/loraprune"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/comcat-towards-efficient-compression-and","slug":"comcat-towards-efficient-compression-and","title":"COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision Models","date":"2023-05-26","arxiv_id":"2305.17235","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/comcat-towards-efficient-compression-and#ran","syntology_url":"https://syntology.ai/paper/2305.17235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17235"}},"official":{"repos":["jinqixiao/ComCAT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/2305-14706","slug":"2305-14706","title":"PruMUX: Augmenting Data Multiplexing with Model Compression","date":"2023-05-24","arxiv_id":"2305.14706","repositories_listed":1,"syntology":null},{"url":"/paper/an-efficient-multilingual-language-model","slug":"an-efficient-multilingual-language-model","title":"An Efficient Multilingual Language Model Compression through Vocabulary Trimming","date":"2023-05-24","arxiv_id":"2305.15020","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/an-efficient-multilingual-language-model#ran","syntology_url":"https://syntology.ai/paper/2305.15020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15020"}},"official":{"repos":["asahi417/lm-vocab-trimmer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/selective-pre-training-for-private-fine","slug":"selective-pre-training-for-private-fine","title":"Selective Pre-training for Private Fine-tuning","date":"2023-05-23","arxiv_id":"2305.13865","repositories_listed":1,"syntology":null},{"url":"/paper/ad-kd-attribution-driven-knowledge","slug":"ad-kd-attribution-driven-knowledge","title":"AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression","date":"2023-05-17","arxiv_id":"2305.10010","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"3 ran (of which 1 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) · 1 unverified","sample_list":"/paper/ad-kd-attribution-driven-knowledge#ran","syntology_url":"https://syntology.ai/paper/2305.10010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10010"}},"official":{"repos":["brucewsy/ad-kd"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-understanding-and-improving-knowledge","slug":"towards-understanding-and-improving-knowledge","title":"Towards Understanding and Improving Knowledge Distillation for Neural Machine Translation","date":"2023-05-14","arxiv_id":"2305.08096","repositories_listed":1,"syntology":null},{"url":"/paper/gsb-group-superposition-binarization-for","slug":"gsb-group-superposition-binarization-for","title":"GSB: Group Superposition Binarization for Vision Transformer with Limited Training Samples","date":"2023-05-13","arxiv_id":"2305.07931","repositories_listed":1,"syntology":null},{"url":"/paper/class-attention-transfer-based-knowledge","slug":"class-attention-transfer-based-knowledge","title":"Class Attention Transfer Based Knowledge Distillation","date":"2023-04-25","arxiv_id":"2304.12777","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/class-attention-transfer-based-knowledge#ran","syntology_url":"https://syntology.ai/paper/2304.12777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.12777"}},"official":{"repos":["gzyaftermath/cat-kd"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-accurate-performance-predictors-for","slug":"learning-accurate-performance-predictors-for","title":"Learning Accurate Performance Predictors for Ultrafast Automated Model Compression","date":"2023-04-13","arxiv_id":"2304.06393","repositories_listed":1,"syntology":null},{"url":"/paper/the-tiny-time-series-transformer-low-latency","slug":"the-tiny-time-series-transformer-low-latency","title":"The Tiny Time-series Transformer: Low-latency High-throughput Classification of Astronomical Transients using Deep Model Compression","date":"2023-03-15","arxiv_id":"2303.08951","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/the-tiny-time-series-transformer-low-latency#ran","syntology_url":"https://syntology.ai/paper/2303.08951","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08951"}},"official":{"repos":["tallamjr/astronet"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-contrastive-knowledge-transfer-framework","slug":"a-contrastive-knowledge-transfer-framework","title":"A Contrastive Knowledge Transfer Framework for Model Compression and Transfer Learning","date":"2023-03-14","arxiv_id":"2303.07599","repositories_listed":1,"syntology":null},{"url":"/paper/i3d-transformer-architectures-with-input","slug":"i3d-transformer-architectures-with-input","title":"I3D: Transformer architectures with input-dependent dynamic depth for speech recognition","date":"2023-03-14","arxiv_id":"2303.07624","repositories_listed":1,"syntology":null},{"url":"/paper/otov2-automatic-generic-user-friendly","slug":"otov2-automatic-generic-user-friendly","title":"OTOV2: Automatic, Generic, User-Friendly","date":"2023-03-13","arxiv_id":"2303.06862","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/otov2-automatic-generic-user-friendly#ran","syntology_url":"https://syntology.ai/paper/2303.06862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06862"}},"official":{"repos":["tianyic/only_train_once"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/provable-convergence-of-tensor-decomposition","slug":"provable-convergence-of-tensor-decomposition","title":"On Model Compression for Neural Networks: Framework, Algorithm, and Convergence Guarantee","date":"2023-03-13","arxiv_id":"2303.06815","repositories_listed":1,"syntology":null},{"url":"/paper/rotation-invariant-quantization-for-model","slug":"rotation-invariant-quantization-for-model","title":"Rotation Invariant Quantization for Model Compression","date":"2023-03-03","arxiv_id":"2303.03106","repositories_listed":1,"syntology":null},{"url":"/paper/structured-pruning-of-self-supervised-pre","slug":"structured-pruning-of-self-supervised-pre","title":"Structured Pruning of Self-Supervised Pre-trained Models for Speech Recognition and Understanding","date":"2023-02-27","arxiv_id":"2302.14132","repositories_listed":1,"syntology":null},{"url":"/paper/dual-relation-knowledge-distillation-for","slug":"dual-relation-knowledge-distillation-for","title":"Dual Relation Knowledge Distillation for Object Detection","date":"2023-02-11","arxiv_id":"2302.05637","repositories_listed":1,"syntology":null},{"url":"/paper/accelerating-and-compressing-deep-neural","slug":"accelerating-and-compressing-deep-neural","title":"Accelerating and Compressing Deep Neural Networks for Massive MIMO CSI Feedback","date":"2023-01-20","arxiv_id":"2304.01914","repositories_listed":1,"syntology":null},{"url":"/paper/compression-aware-video-super-resolution","slug":"compression-aware-video-super-resolution","title":"Compression-Aware Video Super-Resolution","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ssda-secure-source-free-domain-adaptation","slug":"ssda-secure-source-free-domain-adaptation","title":"SSDA: Secure Source-Free Domain Adaptation","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ffnerv-flow-guided-frame-wise-neural","slug":"ffnerv-flow-guided-frame-wise-neural","title":"FFNeRV: Flow-Guided Frame-Wise Neural Representations for Videos","date":"2022-12-23","arxiv_id":"2212.12294","repositories_listed":1,"syntology":null},{"url":"/paper/spike-encoding-techniques-for-iot-time","slug":"spike-encoding-techniques-for-iot-time","title":"Spike encoding techniques for IoT time-varying signals benchmarked on a neuromorphic classification task","date":"2022-12-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/repq-vit-scale-reparameterization-for-post","slug":"repq-vit-scale-reparameterization-for-post","title":"RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers","date":"2022-12-16","arxiv_id":"2212.08254","repositories_listed":1,"syntology":null},{"url":"/paper/compressing-volumetric-radiance-fields-to-1","slug":"compressing-volumetric-radiance-fields-to-1","title":"Compressing Volumetric Radiance Fields to 1 MB","date":"2022-11-29","arxiv_id":"2211.16386","repositories_listed":1,"syntology":null},{"url":"/paper/discovering-dynamic-patterns-from","slug":"discovering-dynamic-patterns-from","title":"Discovering Dynamic Patterns from Spatiotemporal Data with Time-Varying Low-Rank Autoregression","date":"2022-11-28","arxiv_id":"2211.15482","repositories_listed":1,"syntology":null},{"url":"/paper/unbiased-knowledge-distillation-for","slug":"unbiased-knowledge-distillation-for","title":"Unbiased Knowledge Distillation for Recommendation","date":"2022-11-27","arxiv_id":"2211.14729","repositories_listed":1,"syntology":null},{"url":"/paper/sparse-probabilistic-circuits-via-pruning-and","slug":"sparse-probabilistic-circuits-via-pruning-and","title":"Sparse Probabilistic Circuits via Pruning and Growing","date":"2022-11-22","arxiv_id":"2211.12551","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-and-improving-knowledge-1","slug":"understanding-and-improving-knowledge-1","title":"Understanding and Improving Knowledge Distillation for Quantization-Aware Training of Large Transformer Encoders","date":"2022-11-20","arxiv_id":"2211.11014","repositories_listed":1,"syntology":null},{"url":"/paper/compressing-transformer-based-self-supervised","slug":"compressing-transformer-based-self-supervised","title":"Is Smaller Always Faster? Tradeoffs in Compressing Self-Supervised Speech Transformers","date":"2022-11-17","arxiv_id":"2211.09949","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-the-role-of-mixup-in-knowledge","slug":"understanding-the-role-of-mixup-in-knowledge","title":"Understanding the Role of Mixup in Knowledge Distillation: An Empirical Study","date":"2022-11-08","arxiv_id":"2211.03946","repositories_listed":1,"syntology":null},{"url":"/paper/cost-eff-collaborative-optimization-of","slug":"cost-eff-collaborative-optimization-of","title":"COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models","date":"2022-10-27","arxiv_id":"2210.15523","repositories_listed":1,"syntology":null},{"url":"/paper/fast-distilbert-on-cpus","slug":"fast-distilbert-on-cpus","title":"Fast DistilBERT on CPUs","date":"2022-10-27","arxiv_id":"2211.07715","repositories_listed":1,"syntology":null},{"url":"/paper/parameter-efficient-masking-networks","slug":"parameter-efficient-masking-networks","title":"Parameter-Efficient Masking Networks","date":"2022-10-13","arxiv_id":"2210.06699","repositories_listed":1,"syntology":null},{"url":"/paper/less-is-more-task-aware-layer-wise","slug":"less-is-more-task-aware-layer-wise","title":"Less is More: Task-aware Layer-wise Distillation for Language Model Compression","date":"2022-10-04","arxiv_id":"2210.01351","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-distillation-with-reptile-meta","slug":"knowledge-distillation-with-reptile-meta","title":"Knowledge Distillation with Reptile Meta-Learning for Pretrained Language Model Compression","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/attacking-compressed-vision-transformers","slug":"attacking-compressed-vision-transformers","title":"Attacking Compressed Vision Transformers","date":"2022-09-28","arxiv_id":"2209.13785","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-on-device-session-based","slug":"efficient-on-device-session-based","title":"Efficient On-Device Session-Based Recommendation","date":"2022-09-27","arxiv_id":"2209.13422","repositories_listed":1,"syntology":null},{"url":"/paper/psaq-vit-v2-towards-accurate-and-general-data","slug":"psaq-vit-v2-towards-accurate-and-general-data","title":"PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformers","date":"2022-09-13","arxiv_id":"2209.05687","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"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) · 3 unverified","sample_list":"/paper/psaq-vit-v2-towards-accurate-and-general-data#ran","syntology_url":"https://syntology.ai/paper/2209.05687","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.05687"}},"official":{"repos":["zkkli/psaq-vit"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/metanetwork-a-task-agnostic-network","slug":"metanetwork-a-task-agnostic-network","title":"DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization","date":"2022-09-12","arxiv_id":"2209.05227","repositories_listed":1,"syntology":null},{"url":"/paper/towards-sparsification-of-graph-neural","slug":"towards-sparsification-of-graph-neural","title":"Towards Sparsification of Graph Neural Networks","date":"2022-09-11","arxiv_id":"2209.04766","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/towards-sparsification-of-graph-neural#ran","syntology_url":"https://syntology.ai/paper/2209.04766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.04766"}},"official":{"repos":["harveyp123/iccd_sptrn_slr"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/federated-sparse-training-lottery-aware-model","slug":"federated-sparse-training-lottery-aware-model","title":"Lottery Aware Sparsity Hunting: Enabling Federated Learning on Resource-Limited Edge","date":"2022-08-27","arxiv_id":"2208.13092","repositories_listed":1,"syntology":null},{"url":"/paper/optimal-brain-compression-a-framework-for","slug":"optimal-brain-compression-a-framework-for","title":"Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning","date":"2022-08-24","arxiv_id":"2208.11580","repositories_listed":1,"syntology":null},{"url":"/paper/robust-dnn-watermarking-via-fixed-embedding","slug":"robust-dnn-watermarking-via-fixed-embedding","title":"Robust and Large-Payload DNN Watermarking via Fixed, Distribution-Optimized, Weights","date":"2022-08-23","arxiv_id":"2208.10973","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-model-compression-with-random","slug":"efficient-model-compression-with-random","title":"Efficient model compression with Random Operation Access Specific Tile (ROAST) hashing","date":"2022-07-21","arxiv_id":"2207.10702","repositories_listed":1,"syntology":null},{"url":"/paper/3dg-stfm-3d-geometric-guided-student-teacher","slug":"3dg-stfm-3d-geometric-guided-student-teacher","title":"3DG-STFM: 3D Geometric Guided Student-Teacher Feature Matching","date":"2022-07-06","arxiv_id":"2207.02375","repositories_listed":1,"syntology":null},{"url":"/paper/cprune-compiler-informed-model-pruning-for","slug":"cprune-compiler-informed-model-pruning-for","title":"CPrune: Compiler-Informed Model Pruning for Efficient Target-Aware DNN Execution","date":"2022-07-04","arxiv_id":"2207.01260","repositories_listed":1,"syntology":null},{"url":"/paper/pcee-bert-accelerating-bert-inference-via-1","slug":"pcee-bert-accelerating-bert-inference-via-1","title":"PCEE-BERT: Accelerating BERT Inference via Patient and Confident Early Exiting","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/std-net-search-of-image-steganalytic-deep","slug":"std-net-search-of-image-steganalytic-deep","title":"STD-NET: Search of Image Steganalytic Deep-learning Architecture via Hierarchical Tensor Decomposition","date":"2022-06-12","arxiv_id":"2206.05651","repositories_listed":1,"syntology":null},{"url":"/paper/disparse-disentangled-sparsification-for-1","slug":"disparse-disentangled-sparsification-for-1","title":"DiSparse: Disentangled Sparsification for Multitask Model Compression","date":"2022-06-09","arxiv_id":"2206.04662","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"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) · 4 unverified","sample_list":"/paper/disparse-disentangled-sparsification-for-1#ran","syntology_url":"https://syntology.ai/paper/2206.04662","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.04662"}},"official":{"repos":["shi-labs/disparse-multitask-model-compression"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/canonical-convolutional-neural-networks","slug":"canonical-convolutional-neural-networks","title":"Canonical convolutional neural networks","date":"2022-06-03","arxiv_id":"2206.01509","repositories_listed":1,"syntology":null},{"url":"/paper/rlx2-training-a-sparse-deep-reinforcement","slug":"rlx2-training-a-sparse-deep-reinforcement","title":"RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch","date":"2022-05-30","arxiv_id":"2205.15043","repositories_listed":1,"syntology":null},{"url":"/paper/towards-efficient-3d-object-detection-with","slug":"towards-efficient-3d-object-detection-with","title":"Towards Efficient 3D Object Detection with Knowledge Distillation","date":"2022-05-30","arxiv_id":"2205.15156","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 4 unverified","sample_list":"/paper/towards-efficient-3d-object-detection-with#ran","syntology_url":"https://syntology.ai/paper/2205.15156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.15156"}},"official":{"repos":["cvmi-lab/sparsekd"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/autodisc-automatic-distillation-schedule-for","slug":"autodisc-automatic-distillation-schedule-for","title":"MiniDisc: Minimal Distillation Schedule for Language Model Compression","date":"2022-05-29","arxiv_id":"2205.14570","repositories_listed":1,"syntology":null},{"url":"/paper/pointdistiller-structured-knowledge","slug":"pointdistiller-structured-knowledge","title":"PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection","date":"2022-05-23","arxiv_id":"2205.11098","repositories_listed":1,"syntology":null},{"url":"/paper/mapping-emulation-for-knowledge-distillation","slug":"mapping-emulation-for-knowledge-distillation","title":"Aligning Logits Generatively for Principled Black-Box Knowledge Distillation","date":"2022-05-21","arxiv_id":"2205.10490","repositories_listed":1,"syntology":null},{"url":"/paper/indistill-transferring-knowledge-from-pruned","slug":"indistill-transferring-knowledge-from-pruned","title":"InDistill: Information flow-preserving knowledge distillation for model compression","date":"2022-05-20","arxiv_id":"2205.10003","repositories_listed":1,"syntology":null},{"url":"/paper/chemical-transformer-compression-for","slug":"chemical-transformer-compression-for","title":"Chemical transformer compression for accelerating both training and inference of molecular modeling","date":"2022-05-16","arxiv_id":"2205.07582","repositories_listed":1,"syntology":null},{"url":"/paper/multi-granularity-structural-knowledge","slug":"multi-granularity-structural-knowledge","title":"Multi-Granularity Structural Knowledge Distillation for Language Model Compression","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/leaner-and-faster-two-stage-model-compression","slug":"leaner-and-faster-two-stage-model-compression","title":"Leaner and Faster: Two-Stage Model Compression for Lightweight Text-Image Retrieval","date":"2022-04-29","arxiv_id":"2204.13913","repositories_listed":1,"syntology":null},{"url":"/paper/characterizing-and-understanding-the-behavior","slug":"characterizing-and-understanding-the-behavior","title":"Characterizing and Understanding the Behavior of Quantized Models for Reliable Deployment","date":"2022-04-08","arxiv_id":"2204.04220","repositories_listed":1,"syntology":null},{"url":"/paper/lilnetx-lightweight-networks-with-extreme","slug":"lilnetx-lightweight-networks-with-extreme","title":"LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification","date":"2022-04-06","arxiv_id":"2204.02965","repositories_listed":1,"syntology":null},{"url":"/paper/masking-adversarial-damage-finding","slug":"masking-adversarial-damage-finding","title":"Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse Network","date":"2022-04-06","arxiv_id":"2204.02738","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/masking-adversarial-damage-finding#ran","syntology_url":"https://syntology.ai/paper/2204.02738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02738"}},"official":{"repos":["ByungKwanLee/Masking-Adversarial-Damage"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/fedsynth-gradient-compression-via-synthetic","slug":"fedsynth-gradient-compression-via-synthetic","title":"FedSynth: Gradient Compression via Synthetic Data in Federated Learning","date":"2022-04-04","arxiv_id":"2204.01273","repositories_listed":1,"syntology":null},{"url":"/paper/chex-channel-exploration-for-cnn-model","slug":"chex-channel-exploration-for-cnn-model","title":"CHEX: CHannel EXploration for CNN Model Compression","date":"2022-03-29","arxiv_id":"2203.15794","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/chex-channel-exploration-for-cnn-model#ran","syntology_url":"https://syntology.ai/paper/2203.15794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15794"}},"official":null}},{"url":"/paper/cnn-lego-disassembling-and-assembling","slug":"cnn-lego-disassembling-and-assembling","title":"Model LEGO: Creating Models Like Disassembling and Assembling Building Blocks","date":"2022-03-25","arxiv_id":"2203.13453","repositories_listed":1,"syntology":null},{"url":"/paper/spdy-accurate-pruning-with-speedup-guarantees","slug":"spdy-accurate-pruning-with-speedup-guarantees","title":"SPDY: Accurate Pruning with Speedup Guarantees","date":"2022-01-31","arxiv_id":"2201.13096","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/spdy-accurate-pruning-with-speedup-guarantees#ran","syntology_url":"https://syntology.ai/paper/2201.13096","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.13096"}},"official":{"repos":["ist-daslab/spdy"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/training-thinner-and-deeper-neural-networks","slug":"training-thinner-and-deeper-neural-networks","title":"Training Thinner and Deeper Neural Networks: Jumpstart Regularization","date":"2022-01-30","arxiv_id":"2201.12795","repositories_listed":1,"syntology":null},{"url":"/paper/automc-automated-model-compression-based-on","slug":"automc-automated-model-compression-based-on","title":"AutoMC: Automated Model Compression based on Domain Knowledge and Progressive search strategy","date":"2022-01-24","arxiv_id":"2201.09884","repositories_listed":1,"syntology":null},{"url":"/paper/high-fidelity-3d-model-compression-based-on","slug":"high-fidelity-3d-model-compression-based-on","title":"High-fidelity 3D Model Compression based on Key Spheres","date":"2022-01-19","arxiv_id":"2201.07486","repositories_listed":1,"syntology":null},{"url":"/paper/threshnet-an-efficient-densenet-using","slug":"threshnet-an-efficient-densenet-using","title":"ThreshNet: An Efficient DenseNet Using Threshold Mechanism to Reduce Connections","date":"2022-01-09","arxiv_id":"2201.03013","repositories_listed":1,"syntology":null},{"url":"/paper/multi-dimensional-model-compression-of-vision","slug":"multi-dimensional-model-compression-of-vision","title":"Multi-Dimensional Model Compression of Vision Transformer","date":"2021-12-31","arxiv_id":"2201.00043","repositories_listed":1,"syntology":null},{"url":"/paper/finding-the-task-optimal-low-bit-sub","slug":"finding-the-task-optimal-low-bit-sub","title":"Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks","date":"2021-12-30","arxiv_id":"2112.15139","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":0,"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/finding-the-task-optimal-low-bit-sub#ran","syntology_url":"https://syntology.ai/paper/2112.15139","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.15139"}},"official":{"repos":["RunpeiDong/DGMS"],"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/spvit-enabling-faster-vision-transformers-via","slug":"spvit-enabling-faster-vision-transformers-via","title":"SPViT: Enabling Faster Vision Transformers via Soft Token Pruning","date":"2021-12-27","arxiv_id":"2112.13890","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/spvit-enabling-faster-vision-transformers-via#ran","syntology_url":"https://syntology.ai/paper/2112.13890","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.13890"}},"official":{"repos":["peiyanflying/spvit"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/pixel-distillation-a-new-knowledge","slug":"pixel-distillation-a-new-knowledge","title":"Pixel Distillation: A New Knowledge Distillation Scheme for Low-Resolution Image Recognition","date":"2021-12-17","arxiv_id":"2112.09532","repositories_listed":1,"syntology":null},{"url":"/paper/fast-test-input-generation-for-finding","slug":"fast-test-input-generation-for-finding","title":"Finding Deviated Behaviors of the Compressed DNN Models for Image Classifications","date":"2021-12-06","arxiv_id":"2112.02819","repositories_listed":1,"syntology":null},{"url":"/paper/aligned-structured-sparsity-learning-for","slug":"aligned-structured-sparsity-learning-for","title":"Aligned Structured Sparsity Learning for Efficient Image Super-Resolution","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/comprehensive-knowledge-distillation-with","slug":"comprehensive-knowledge-distillation-with","title":"Comprehensive Knowledge Distillation with Causal Intervention","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/shapeshifter-a-parameter-efficient","slug":"shapeshifter-a-parameter-efficient","title":"Shapeshifter: a Parameter-efficient Transformer using Factorized Reshaped Matrices","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-unified-pruning-framework-for-vision","slug":"a-unified-pruning-framework-for-vision","title":"A Unified Pruning Framework for Vision Transformers","date":"2021-11-30","arxiv_id":"2111.15127","repositories_listed":1,"syntology":null},{"url":"/paper/nam-normalization-based-attention-module","slug":"nam-normalization-based-attention-module","title":"NAM: Normalization-based Attention Module","date":"2021-11-24","arxiv_id":"2111.12419","repositories_listed":1,"syntology":null},{"url":"/paper/semi-online-knowledge-distillation","slug":"semi-online-knowledge-distillation","title":"Semi-Online Knowledge Distillation","date":"2021-11-23","arxiv_id":"2111.11747","repositories_listed":1,"syntology":null},{"url":"/paper/limuse-lightweight-multi-modal-speaker","slug":"limuse-lightweight-multi-modal-speaker","title":"LiMuSE: Lightweight Multi-modal Speaker Extraction","date":"2021-11-07","arxiv_id":"2111.04063","repositories_listed":1,"syntology":null},{"url":"/paper/distilling-object-detectors-with-feature","slug":"distilling-object-detectors-with-feature","title":"Distilling Object Detectors with Feature Richness","date":"2021-11-01","arxiv_id":"2111.00674","repositories_listed":1,"syntology":null},{"url":"/paper/generalized-depthwise-separable-convolutions","slug":"generalized-depthwise-separable-convolutions","title":"Generalized Depthwise-Separable Convolutions for Adversarially Robust and Efficient Neural Networks","date":"2021-10-28","arxiv_id":"2110.14871","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":4,"n_ran_checked":6,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/generalized-depthwise-separable-convolutions#ran","syntology_url":"https://syntology.ai/paper/2110.14871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.14871"}},"official":{"repos":["hsndbk4/gdws"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/exploring-gradient-flow-based-saliency-for","slug":"exploring-gradient-flow-based-saliency-for","title":"Exploring Gradient Flow Based Saliency for DNN Model Compression","date":"2021-10-24","arxiv_id":"2110.12477","repositories_listed":1,"syntology":null},{"url":"/paper/hrkd-hierarchical-relational-knowledge","slug":"hrkd-hierarchical-relational-knowledge","title":"HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model Compression","date":"2021-10-16","arxiv_id":"2110.08551","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 3 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) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/hrkd-hierarchical-relational-knowledge#ran","syntology_url":"https://syntology.ai/paper/2110.08551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.08551"}},"official":{"repos":["cheneydon/hrkd"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/joint-channel-and-weight-pruning-for-model","slug":"joint-channel-and-weight-pruning-for-model","title":"Joint Channel and Weight Pruning for Model Acceleration on Moblie Devices","date":"2021-10-15","arxiv_id":"2110.08013","repositories_listed":1,"syntology":null},{"url":"/paper/backdoor-attacks-on-federated-learning-with","slug":"backdoor-attacks-on-federated-learning-with","title":"Backdoor Attacks on Federated Learning with Lottery Ticket Hypothesis","date":"2021-09-22","arxiv_id":"2109.10512","repositories_listed":1,"syntology":null},{"url":"/paper/high-dimensional-bayesian-optimization-for","slug":"high-dimensional-bayesian-optimization-for","title":"Bayesian Optimization with Clustering and Rollback for CNN Auto Pruning","date":"2021-09-22","arxiv_id":"2109.10591","repositories_listed":1,"syntology":null},{"url":"/paper/ds-net-dynamic-weight-slicing-for-efficient","slug":"ds-net-dynamic-weight-slicing-for-efficient","title":"DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers","date":"2021-09-21","arxiv_id":"2109.10060","repositories_listed":1,"syntology":null},{"url":"/paper/distilling-linguistic-context-for-language","slug":"distilling-linguistic-context-for-language","title":"Distilling Linguistic Context for Language Model Compression","date":"2021-09-17","arxiv_id":"2109.08359","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/distilling-linguistic-context-for-language#ran","syntology_url":"https://syntology.ai/paper/2109.08359","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.08359"}},"official":{"repos":["geondopark/ckd"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/causal-explanation-of-convolutional-neural","slug":"causal-explanation-of-convolutional-neural","title":"Causal Explanation of Convolutional Neural Networks","date":"2021-09-13","arxiv_id":null,"repositories_listed":1,"syntology":null}],"record_sha256":"8ec47ecddfa8496b010fca041a661be83839b46a80be7613d4ff810d0fcb6bf7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}