{"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/get-num-params","entry":"get_num_params","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":15,"n_papers_ran":8,"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":8,"n_samples_ran":5,"n_samples_fingerprinted":0,"n_places":15,"n_places_pointer_only":7,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":4,"unverified":3},"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":"2601.22156","paper":"/paper/arxiv-2601-22156","title":"Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"THUNLP/hybrid-linear-attention","path":"halo/utils.py","file_url":"https://github.com/THUNLP/hybrid-linear-attention/blob/HEAD/halo/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cb746560d2b54ee7","mcp_get_code":{"code_sha256":"cb746560d2b54ee7"}},{"arxiv_id":"2510.06195","paper":"/paper/arxiv-2510-06195","title":"Latent Speech-Text Transformer","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"facebookresearch/lst","path":"lst/metrics.py","file_url":"https://github.com/facebookresearch/lst/blob/HEAD/lst/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"81d8582d1fab7bda","mcp_get_code":{"code_sha256":"81d8582d1fab7bda"}},{"arxiv_id":"2506.14761","paper":"/paper/from-bytes-to-ideas-language-modeling-with","title":"From Bytes to Ideas: Language Modeling with Autoregressive U-Nets","date":"2025-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/lingua","path":"lingua/metrics.py","file_url":"https://github.com/facebookresearch/lingua/blob/HEAD/lingua/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"81d8582d1fab7bda","mcp_get_code":{"code_sha256":"81d8582d1fab7bda"}},{"arxiv_id":"2503.18866","paper":"/paper/reasoning-to-learn-from-latent-thoughts","title":"Reasoning to Learn from Latent Thoughts","date":"2025-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ryoungj/BoLT","path":"lingua/metrics.py","file_url":"https://github.com/ryoungj/BoLT/blob/HEAD/lingua/metrics.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":"81d8582d1fab7bda","mcp_get_code":{"code_sha256":"81d8582d1fab7bda"}},{"arxiv_id":"2412.09764","paper":"/paper/memory-layers-at-scale","title":"Memory Layers at Scale","date":"2024-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/memory","path":"lingua/metrics.py","file_url":"https://github.com/facebookresearch/memory/blob/HEAD/lingua/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"81d8582d1fab7bda","mcp_get_code":{"code_sha256":"81d8582d1fab7bda"}},{"arxiv_id":"2412.00420","paper":"/paper/tarot-targeted-data-selection-via-optimal","title":"TAROT: Targeted Data Selection via Optimal Transport","date":"2024-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vita-epfl/tarot","path":"tarot/utils.py","file_url":"https://github.com/vita-epfl/tarot/blob/HEAD/tarot/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"580e08522d1c5ea9","mcp_get_code":{"code_sha256":"580e08522d1c5ea9"}},{"arxiv_id":"2403.13268","paper":"/paper/unifews-unified-entry-wise-sparsification-for","title":"Unifews: Unified Entry-Wise Sparsification for Efficient Graph Neural Network","date":"2024-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gdmnl/Unifews","path":"utils/metric.py","file_url":"https://github.com/gdmnl/Unifews/blob/HEAD/utils/metric.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"537e2f1c3fdb882e","mcp_get_code":{"code_sha256":"537e2f1c3fdb882e"}},{"arxiv_id":"2402.15978","paper":"/paper/shaving-weights-with-occam-s-razor-bayesian","title":"Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihood","date":"2024-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fortuinlab/spam-pruning","path":"experiment/src/marglikopt.py","file_url":"https://github.com/fortuinlab/spam-pruning/blob/HEAD/experiment/src/marglikopt.py","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b81882decca625ee","mcp_get_code":{"code_sha256":"b81882decca625ee"}},{"arxiv_id":"2402.12789","paper":"/paper/fair-classifiers-without-fair-training-an","title":"Fairness Without Harm: An Influence-Guided Active Sampling Approach","date":"2024-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ucsc-real/fairnesswithoutharm","path":"src/models.py","file_url":"https://github.com/ucsc-real/fairnesswithoutharm/blob/HEAD/src/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"63410cdc89b2ca7a","mcp_get_code":{"code_sha256":"63410cdc89b2ca7a"}},{"arxiv_id":"2402.10211","paper":"/paper/hierarchical-state-space-models-for","title":"Hierarchical State Space Models for Continuous Sequence-to-Sequence Modeling","date":"2024-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"raunaqbhirangi/hiss","path":"hiss/utils/train_utils.py","file_url":"https://github.com/raunaqbhirangi/hiss/blob/HEAD/hiss/utils/train_utils.py","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b81882decca625ee","mcp_get_code":{"code_sha256":"b81882decca625ee"}},{"arxiv_id":"2312.06205","paper":"/paper/the-journey-not-the-destination-how-data","title":"The Journey, Not the Destination: How Data Guides Diffusion Models","date":"2023-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"madrylab/journey-trak","path":"diffusion_trak/utils.py","file_url":"https://github.com/madrylab/journey-trak/blob/HEAD/diffusion_trak/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"01f28d033fcc4188","mcp_get_code":{"code_sha256":"01f28d033fcc4188"}},{"arxiv_id":"2308.16475","paper":"/paper/transformer-compression-via-subspace","title":"$\\rm SP^3$: Enhancing Structured Pruning via PCA Projection","date":"2023-08-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hyx1999/sp3","path":"bert/pipeline/glue/entry.py","file_url":"https://github.com/hyx1999/sp3/blob/HEAD/bert/pipeline/glue/entry.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"04c98539fd77722e","mcp_get_code":{"code_sha256":"04c98539fd77722e"}},{"arxiv_id":"2306.05651","paper":"/paper/differentially-private-sharpness-aware","title":"Differentially Private Sharpness-Aware Training","date":"2023-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TheSunWillRise/DPNAS","path":"dp_evaluate/models.py","file_url":"https://github.com/TheSunWillRise/DPNAS/blob/HEAD/dp_evaluate/models.py","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b81882decca625ee","mcp_get_code":{"code_sha256":"b81882decca625ee"}},{"arxiv_id":"2107.07075","paper":"/paper/deep-learning-on-a-data-diet-finding","title":"Deep Learning on a Data Diet: Finding Important Examples Early in Training","date":"2021-07-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mansheej/data_diet","path":"data_diet/models.py","file_url":"https://github.com/mansheej/data_diet/blob/HEAD/data_diet/models.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":"63410cdc89b2ca7a","mcp_get_code":{"code_sha256":"63410cdc89b2ca7a"}},{"arxiv_id":"2024.acl-long.803","paper":null,"title":"arXiv:2024.acl-long.803","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"MadryLab/trak","path":"trak/utils.py","file_url":"https://github.com/MadryLab/trak/blob/HEAD/trak/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"580e08522d1c5ea9","mcp_get_code":{"code_sha256":"580e08522d1c5ea9"}}]}