{"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/get-grads","entry":"get_grads","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":13,"n_papers_ran":12,"n_papers_ran_no_instrument_failure":9,"n_papers_ran_instrument_only":3,"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":12,"n_samples_ran":11,"n_samples_constructed":0,"n_samples_ran_checked":8,"n_samples_instrument":3,"n_samples_unverified":1,"n_samples_fingerprinted":2,"n_places":13,"n_places_pointer_only":5,"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":2,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":6,"unverified":1},"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":"2605.19607","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2605-19607","title":"Spectral Integrated Gradients for Coarse-to-Fine Feature Attribution","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"leekwoon/sig","path":"cleanig/explainer/spectral_ig.py","file_url":"https://github.com/leekwoon/sig/blob/HEAD/cleanig/explainer/spectral_ig.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"8fd0d6c205dcc0f2","code_sha256_prefix":"8fd0d6c205dcc0f2","mcp_get_code":{"code_sha256":"8fd0d6c205dcc0f2"}},{"arxiv_id":"2605.08464","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2605-08464","title":"The Geometric Structure of Models Learning Sparse Data","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"ThomasWalker1/RFAM","path":"utils/rfm.py","file_url":"https://github.com/ThomasWalker1/RFAM/blob/HEAD/utils/rfm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ThomasWalker1/RFAM when it was checked","code_sha256":"d43a7623958fe7e6","code_sha256_prefix":"d43a7623958fe7e6","mcp_get_code":{"code_sha256":"d43a7623958fe7e6"}},{"arxiv_id":"2410.22113","arxiv_id_is_arxiv":true,"paper":"/paper/where-do-large-learning-rates-lead-us","title":"Where Do Large Learning Rates Lead Us?","date":"2024-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"isadrtdinov/understanding-large-lrs","path":"synthetic_example/model.py","file_url":"https://github.com/isadrtdinov/understanding-large-lrs/blob/HEAD/synthetic_example/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"84a8ef25008d233d","code_sha256_prefix":"84a8ef25008d233d","mcp_get_code":{"code_sha256":"84a8ef25008d233d"}},{"arxiv_id":"2405.05349","arxiv_id_is_arxiv":true,"paper":"/paper/offline-model-based-optimization-via-policy","title":"Offline Model-Based Optimization via Policy-Guided Gradient Search","date":"2024-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yassineCh/PGS","path":"generate_trajectories.py","file_url":"https://github.com/yassineCh/PGS/blob/HEAD/generate_trajectories.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, yassineCh/PGS when it was checked","code_sha256":"753958f65f38b74a","code_sha256_prefix":"753958f65f38b74a","mcp_get_code":{"code_sha256":"753958f65f38b74a"}},{"arxiv_id":"2312.12232","arxiv_id_is_arxiv":true,"paper":"/paper/brush-your-text-synthesize-any-scene-text-on","title":"Brush Your Text: Synthesize Any Scene Text on Images via Diffusion Model","date":"2023-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ecnuljzhang/brush-your-text","path":"controlnet_util/Textgen/poisson_reconstruct.py","file_url":"https://github.com/ecnuljzhang/brush-your-text/blob/HEAD/controlnet_util/Textgen/poisson_reconstruct.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ecnuljzhang/brush-your-text when it was checked","code_sha256":"48688abc93b004ef","code_sha256_prefix":"48688abc93b004ef","mcp_get_code":{"code_sha256":"48688abc93b004ef"}},{"arxiv_id":"2206.07737","arxiv_id_is_arxiv":true,"paper":"/paper/disparate-impact-in-differential-privacy-from","title":"Disparate Impact in Differential Privacy from Gradient Misalignment","date":"2022-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"layer6ai-labs/fair-dp","path":"utils.py","file_url":"https://github.com/layer6ai-labs/fair-dp/blob/HEAD/utils.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":"cfc5de3ebf0a6a02","code_sha256_prefix":"cfc5de3ebf0a6a02","mcp_get_code":{"code_sha256":"cfc5de3ebf0a6a02"}},{"arxiv_id":"2104.02768","arxiv_id_is_arxiv":true,"paper":"/paper/robust-semantic-interpretability-revisiting","title":"Robust Semantic Interpretability: Revisiting Concept Activation Vectors","date":"2021-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"keiserlab/rcav","path":"rcav_utils.py","file_url":"https://github.com/keiserlab/rcav/blob/HEAD/rcav_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, keiserlab/rcav when it was checked","code_sha256":"97795a7b853c4260","code_sha256_prefix":"97795a7b853c4260","mcp_get_code":{"code_sha256":"97795a7b853c4260"}},{"arxiv_id":"2009.10588","arxiv_id_is_arxiv":true,"paper":"/paper/anomalous-diffusion-dynamics-of-learning-in","title":"Anomalous diffusion dynamics of learning in deep neural networks","date":"2020-09-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ifgovh/Anomalous-diffusion-dynamics-of-SGD","path":"get_gradient_weight/gradient_noise.py","file_url":"https://github.com/ifgovh/Anomalous-diffusion-dynamics-of-SGD/blob/HEAD/get_gradient_weight/gradient_noise.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":"81aabb5979983838","code_sha256_prefix":"81aabb5979983838","mcp_get_code":{"code_sha256":"81aabb5979983838"}},{"arxiv_id":"2006.09313","arxiv_id_is_arxiv":true,"paper":"/paper/hausdorff-dimension-stochastic-differential","title":"Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks","date":"2020-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"umutsimsekli/Hausdorff-Dimension-and-Generalization","path":"src/utils.py","file_url":"https://github.com/umutsimsekli/Hausdorff-Dimension-and-Generalization/blob/HEAD/src/utils.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":"81aabb5979983838","code_sha256_prefix":"81aabb5979983838","mcp_get_code":{"code_sha256":"81aabb5979983838"}},{"arxiv_id":"2002.08709","arxiv_id_is_arxiv":true,"paper":"/paper/do-we-need-zero-training-loss-after-achieving","title":"Do We Need Zero Training Loss After Achieving Zero Training Error?","date":"2020-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"takashiishida/flooding","path":"utils/utils_algo.py","file_url":"https://github.com/takashiishida/flooding/blob/HEAD/utils/utils_algo.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GPL-3.0, as GitHub detects it on this paper's repository, takashiishida/flooding, is not in the permissive set Syntology serves inline","code_sha256":"d251cab596a514b3","code_sha256_prefix":"d251cab596a514b3","mcp_get_code":{"code_sha256":"d251cab596a514b3"}},{"arxiv_id":"1703.09452","arxiv_id_is_arxiv":true,"paper":"/paper/segan-speech-enhancement-generative","title":"SEGAN: Speech Enhancement Generative Adversarial Network","date":"2017-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"santi-pdp/segan_pytorch","path":"segan/models/ops.py","file_url":"https://github.com/santi-pdp/segan_pytorch/blob/HEAD/segan/models/ops.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":"26c162c3caa1223a","code_sha256_prefix":"26c162c3caa1223a","mcp_get_code":{"code_sha256":"26c162c3caa1223a"}},{"arxiv_id":"1604.06646","arxiv_id_is_arxiv":true,"paper":"/paper/synthetic-data-for-text-localisation-in","title":"Synthetic Data for Text Localisation in Natural Images","date":"2016-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ankush-me/SynthText","path":"poisson_reconstruct.py","file_url":"https://github.com/ankush-me/SynthText/blob/HEAD/poisson_reconstruct.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"15c813055f58cb66","code_sha256_prefix":"15c813055f58cb66","mcp_get_code":{"code_sha256":"15c813055f58cb66"}},{"arxiv_id":"1504.06852","arxiv_id_is_arxiv":true,"paper":"/paper/flownet-learning-optical-flow-with","title":"FlowNet: Learning Optical Flow with Convolutional Networks","date":"2015-04-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ClementPinard/Pytorch-Correlation-extension","path":"check.py","file_url":"https://github.com/ClementPinard/Pytorch-Correlation-extension/blob/HEAD/check.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":"19ee68e6a7f1011b","code_sha256_prefix":"19ee68e6a7f1011b","mcp_get_code":{"code_sha256":"19ee68e6a7f1011b"}}],"record_sha256":"33db2c0b435eec51129f17f7ccc6ee19c1a9848b2d2149d63cf551f21e275e49","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}