{"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":"/code/unpack","entry":"unpack","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-10-05T00:36:11+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 = n_papers_ran_no_instrument_failure (papers with a run with no instrument failure) + n_papers_ran_instrument_only (papers where every run was a failure of Syntology's instrument); n_samples_ran = n_samples_ran_checked (honoured, violated, no contract) + n_samples_instrument (failures of Syntology's instrument, not of the code).","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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":18,"n_papers_ran":15,"n_papers_ran_no_instrument_failure":4,"n_papers_ran_instrument_only":11,"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":15,"n_samples_ran":12,"n_samples_constructed":0,"n_samples_ran_checked":4,"n_samples_instrument":8,"n_samples_unverified":3,"n_samples_fingerprinted":0,"n_places":18,"n_places_pointer_only":4,"n_places_pointer_only_link_open":0,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_places_pointer_only_link_open counts the places where this paper's link allows the text and the stored copy does not","by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":5,"ran_fixture":3,"ran":4,"unverified":3},"key_notes":{"n_samples_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_samples_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":{"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":"2606.26560","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2606-26560","title":"Erase-then-Delta Attention: Decoupling Erase and Write Addresses in Delta-Rule Linear Attention","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"QwenLM/FlashQLA","path":"flash_qla/utils/pack.py","file_url":"https://github.com/QwenLM/FlashQLA/blob/HEAD/flash_qla/utils/pack.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"e1e90a347a0962b9","code_sha256_prefix":"e1e90a347a0962b9","mcp_get_code":{"code_sha256":"e1e90a347a0962b9"}},{"arxiv_id":"2506.18095","arxiv_id_is_arxiv":true,"paper":"/paper/sharegpt-4o-image-aligning-multimodal-models","title":"ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation","date":"2025-06-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"freedomintelligence/sharegpt-4o-image","path":"demo/app_janus4o.py","file_url":"https://github.com/freedomintelligence/sharegpt-4o-image/blob/HEAD/demo/app_janus4o.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, freedomintelligence/sharegpt-4o-image when it was checked","code_sha256":"9635e4f79a6f30d4","code_sha256_prefix":"9635e4f79a6f30d4","mcp_get_code":{"code_sha256":"9635e4f79a6f30d4"}},{"arxiv_id":"2504.02160","arxiv_id_is_arxiv":true,"paper":"/paper/less-to-more-generalization-unlocking-more","title":"Less-to-More Generalization: Unlocking More Controllability by In-Context Generation","date":"2025-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bytedance/UNO","path":"uno/flux/pipeline.py","file_url":"https://github.com/bytedance/UNO/blob/HEAD/uno/flux/pipeline.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"330e00c9f233c90f","code_sha256_prefix":"330e00c9f233c90f","mcp_get_code":{"code_sha256":"330e00c9f233c90f"}},{"arxiv_id":"2502.17363","arxiv_id_is_arxiv":true,"paper":"/paper/kv-edit-training-free-image-editing-for","title":"KV-Edit: Training-Free Image Editing for Precise Background Preservation","date":"2025-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Xilluill/KV-Edit","path":"models/kv_edit.py","file_url":"https://github.com/Xilluill/KV-Edit/blob/HEAD/models/kv_edit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a9451ac1452e533d","code_sha256_prefix":"a9451ac1452e533d","mcp_get_code":{"code_sha256":"a9451ac1452e533d"}},{"arxiv_id":"2404.07991","arxiv_id_is_arxiv":true,"paper":"/paper/gomavatar-efficient-animatable-human-modeling","title":"GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh","date":"2024-04-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wenj/GoMAvatar","path":"train_pose.py","file_url":"https://github.com/wenj/GoMAvatar/blob/HEAD/train_pose.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a54617b4d1951dc3","code_sha256_prefix":"a54617b4d1951dc3","mcp_get_code":{"code_sha256":"a54617b4d1951dc3"}},{"arxiv_id":"2402.10193","arxiv_id_is_arxiv":true,"paper":"/paper/bitdelta-your-fine-tune-may-only-be-worth-one","title":"BitDelta: Your Fine-Tune May Only Be Worth One Bit","date":"2024-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FasterDecoding/BitDelta","path":"bitdelta/binary_gemm_kernel.py","file_url":"https://github.com/FasterDecoding/BitDelta/blob/HEAD/bitdelta/binary_gemm_kernel.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"7b1afaa65397beea","code_sha256_prefix":"7b1afaa65397beea","mcp_get_code":{"code_sha256":"7b1afaa65397beea"}},{"arxiv_id":"2110.04175","arxiv_id_is_arxiv":true,"paper":"/paper/relaysum-for-decentralized-deep-learning-on","title":"RelaySum for Decentralized Deep Learning on Heterogeneous Data","date":"2021-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"epfml/relaysgd","path":"utils/communication.py","file_url":"https://github.com/epfml/relaysgd/blob/HEAD/utils/communication.py","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"3f9b26dabda4b0a8","code_sha256_prefix":"3f9b26dabda4b0a8","mcp_get_code":{"code_sha256":"3f9b26dabda4b0a8"}},{"arxiv_id":"2104.05344","arxiv_id_is_arxiv":true,"paper":"/paper/how-sensitive-are-meta-learners-to-dataset","title":"How Sensitive are Meta-Learners to Dataset Imbalance?","date":"2021-04-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mattochal/imbalanced_fsl_public","path":"generator.py","file_url":"https://github.com/mattochal/imbalanced_fsl_public/blob/HEAD/generator.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"1bdfd97bb9483c1b","code_sha256_prefix":"1bdfd97bb9483c1b","mcp_get_code":{"code_sha256":"1bdfd97bb9483c1b"}},{"arxiv_id":"2101.02523","arxiv_id_is_arxiv":true,"paper":"/paper/few-shot-learning-with-class-imbalance","title":"Few-Shot Learning with Class Imbalance","date":"2021-01-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","code_sha256":"1bdfd97bb9483c1b","code_sha256_prefix":"1bdfd97bb9483c1b","mcp_get_code":{"code_sha256":"1bdfd97bb9483c1b"}},{"arxiv_id":"2008.11459","arxiv_id_is_arxiv":true,"paper":"/paper/semantic-graph-based-place-recognition-for-3d","title":"Semantic Graph Based Place Recognition for 3D Point Clouds","date":"2020-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kxhit/SG_PR","path":"data_process/auxiliary/SSCDataset.py","file_url":"https://github.com/kxhit/SG_PR/blob/HEAD/data_process/auxiliary/SSCDataset.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"b6ce60277ddab1d7","code_sha256_prefix":"b6ce60277ddab1d7","mcp_get_code":{"code_sha256":"b6ce60277ddab1d7"}},{"arxiv_id":"2008.01425","arxiv_id_is_arxiv":true,"paper":"/paper/powergossip-practical-low-rank-communication","title":"PowerGossip: Practical Low-Rank Communication Compression in Decentralized Deep Learning","date":"2020-08-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","code_sha256":"3f9b26dabda4b0a8","code_sha256_prefix":"3f9b26dabda4b0a8","mcp_get_code":{"code_sha256":"3f9b26dabda4b0a8"}},{"arxiv_id":"2002.12418","arxiv_id_is_arxiv":true,"paper":"/paper/mnn-a-universal-and-efficient-inference","title":"MNN: A Universal and Efficient Inference Engine","date":"2020-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alibaba/MNN","path":"transformers/llm/export/mnn_quant_ref.py","file_url":"https://github.com/alibaba/MNN/blob/HEAD/transformers/llm/export/mnn_quant_ref.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"37b7040f99813ca6","code_sha256_prefix":"37b7040f99813ca6","mcp_get_code":{"code_sha256":"37b7040f99813ca6"}},{"arxiv_id":"1912.04232","arxiv_id_is_arxiv":true,"paper":"/paper/jax-md-end-to-end-differentiable-hardware-1","title":"JAX, M.D.: A Framework for Differentiable Physics","date":"2019-12-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google/jax-md","path":"jax_md/dataclasses.py","file_url":"https://github.com/google/jax-md/blob/HEAD/jax_md/dataclasses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a9d0437b7f7e7a53","code_sha256_prefix":"a9d0437b7f7e7a53","mcp_get_code":{"code_sha256":"a9d0437b7f7e7a53"}},{"arxiv_id":"1908.09791","arxiv_id_is_arxiv":true,"paper":"/paper/once-for-all-train-one-network-and-specialize","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","date":"2019-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MaximIntegratedAI/ai8x-synthesis","path":"izer/datamem.py","file_url":"https://github.com/MaximIntegratedAI/ai8x-synthesis/blob/HEAD/izer/datamem.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"1db0589ff0da8775","code_sha256_prefix":"1db0589ff0da8775","mcp_get_code":{"code_sha256":"1db0589ff0da8775"}},{"arxiv_id":"1904.01416","arxiv_id_is_arxiv":true,"paper":"/paper/a-dataset-for-semantic-segmentation-of-point","title":"SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences","date":"2019-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PRBonn/semantic-kitti-api","path":"auxiliary/SSCDataset.py","file_url":"https://github.com/PRBonn/semantic-kitti-api/blob/HEAD/auxiliary/SSCDataset.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"b6ce60277ddab1d7","code_sha256_prefix":"b6ce60277ddab1d7","mcp_get_code":{"code_sha256":"b6ce60277ddab1d7"}},{"arxiv_id":"1812.05784","arxiv_id_is_arxiv":true,"paper":"/paper/pointpillars-fast-encoders-for-object","title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","date":"2018-12-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"isl-org/Open3D-ML","path":"ml3d/tf/models/point_pillars.py","file_url":"https://github.com/isl-org/Open3D-ML/blob/HEAD/ml3d/tf/models/point_pillars.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, isl-org/Open3D-ML (NOASSERTION)","code_sha256":"1354276502be4aa8","code_sha256_prefix":"1354276502be4aa8","mcp_get_code":{"code_sha256":"1354276502be4aa8"}},{"arxiv_id":"1811.08674","arxiv_id_is_arxiv":true,"paper":"/paper/graph-refinement-based-tree-extraction-using","title":"Graph Refinement based Airway Extraction using Mean-Field Networks and Graph Neural Networks","date":"2018-11-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"raghavian/graph_refinement","path":"starter.py","file_url":"https://github.com/raghavian/graph_refinement/blob/HEAD/starter.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"25efaf0ad97e3fbc","code_sha256_prefix":"25efaf0ad97e3fbc","mcp_get_code":{"code_sha256":"25efaf0ad97e3fbc"}},{"arxiv_id":"1802.10062","arxiv_id_is_arxiv":true,"paper":"/paper/csrnet-dilated-convolutional-neural-networks","title":"CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes","date":"2018-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Saritus/Crowd-Counter","path":"mat4conda.py","file_url":"https://github.com/Saritus/Crowd-Counter/blob/HEAD/mat4conda.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"0deef73b258cd476","code_sha256_prefix":"0deef73b258cd476","mcp_get_code":{"code_sha256":"0deef73b258cd476"}}],"record_sha256":"c30a8a802e69a14ecb533eed92878832a309ebae1f454d6ceb88bff0c5c88b43","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}