{"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/pad-or-trim","entry":"pad_or_trim","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":12,"n_papers_ran":1,"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":6,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":12,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":5},"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":"2604.13073","paper":"/paper/arxiv-2604-13073","title":"OmniTrace: A Unified Framework for Generation-Time Attribution in Omni-Modal LLMs","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"openai/whisper","path":"whisper/audio.py","file_url":"https://github.com/openai/whisper/blob/HEAD/whisper/audio.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9f13de1c23e4003d","mcp_get_code":{"code_sha256":"9f13de1c23e4003d"}},{"arxiv_id":"2602.12241","paper":"/paper/arxiv-2602-12241","title":"Moonshine v2: Ergodic Streaming Encoder ASR for Latency-Critical Speech Applications","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"SYSTRAN/faster-whisper","path":"faster_whisper/audio.py","file_url":"https://github.com/SYSTRAN/faster-whisper/blob/HEAD/faster_whisper/audio.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4db3da4d6c68fdfd","mcp_get_code":{"code_sha256":"4db3da4d6c68fdfd"}},{"arxiv_id":"2510.26096","paper":"/paper/arxiv-2510-26096","title":"ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio-Language Models","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"WeifeiJin/ALMGuard","path":"whisper/audio.py","file_url":"https://github.com/WeifeiJin/ALMGuard/blob/HEAD/whisper/audio.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9f13de1c23e4003d","mcp_get_code":{"code_sha256":"9f13de1c23e4003d"}},{"arxiv_id":"2506.08967","paper":"/paper/2506-08967","title":"Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model","date":"2025-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stepfun-ai/step-audio","path":"funasr_detach/models/whisper/utils/audio.py","file_url":"https://github.com/stepfun-ai/step-audio/blob/HEAD/funasr_detach/models/whisper/utils/audio.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":"9f13de1c23e4003d","mcp_get_code":{"code_sha256":"9f13de1c23e4003d"}},{"arxiv_id":"2406.10082","paper":"/paper/whisper-flamingo-integrating-visual-features","title":"Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation","date":"2024-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"roudimit/whisper-flamingo","path":"whisper/audio.py","file_url":"https://github.com/roudimit/whisper-flamingo/blob/HEAD/whisper/audio.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9f13de1c23e4003d","mcp_get_code":{"code_sha256":"9f13de1c23e4003d"}},{"arxiv_id":"2405.17537","paper":"/paper/bioscan-clip-bridging-vision-and-genomics-for","title":"CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scale","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VectorInstitute/mmlearn","path":"mmlearn/datasets/librispeech.py","file_url":"https://github.com/VectorInstitute/mmlearn/blob/HEAD/mmlearn/datasets/librispeech.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":"ecf7c6b9c5e91f70","mcp_get_code":{"code_sha256":"ecf7c6b9c5e91f70"}},{"arxiv_id":"2309.15701","paper":"/paper/hyporadise-an-open-baseline-for-generative-1","title":"HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models","date":"2023-09-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hypotheses-paradise/hypo2trans","path":"generate_data/whisper/whisper/audio.py","file_url":"https://github.com/hypotheses-paradise/hypo2trans/blob/HEAD/generate_data/whisper/whisper/audio.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5d9d25629a2e0506","mcp_get_code":{"code_sha256":"5d9d25629a2e0506"}},{"arxiv_id":"2308.06112","paper":"/paper/lip2vec-efficient-and-robust-visual-speech","title":"Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping","date":"2023-08-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YasserdahouML/Lip2Vec","path":"datasets/audio.py","file_url":"https://github.com/YasserdahouML/Lip2Vec/blob/HEAD/datasets/audio.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9f13de1c23e4003d","mcp_get_code":{"code_sha256":"9f13de1c23e4003d"}},{"arxiv_id":"2306.01428","paper":"/paper/improved-deepfake-detection-using-whisper","title":"Improved DeepFake Detection Using Whisper Features","date":"2023-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"piotrkawa/deepfake-whisper-features","path":"src/models/whisper_main.py","file_url":"https://github.com/piotrkawa/deepfake-whisper-features/blob/HEAD/src/models/whisper_main.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b7043f3ab423733b","mcp_get_code":{"code_sha256":"b7043f3ab423733b"}},{"arxiv_id":"2305.17491","paper":"/paper/fermat-an-alternative-to-accuracy-for","title":"FERMAT: An Alternative to Accuracy for Numerical Reasoning","date":"2023-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jasivan/FERMAT","path":"codes/char_level_rep.py","file_url":"https://github.com/jasivan/FERMAT/blob/HEAD/codes/char_level_rep.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bd8cd57d2905efde","mcp_get_code":{"code_sha256":"bd8cd57d2905efde"}},{"arxiv_id":"2212.04356","paper":"/paper/robust-speech-recognition-via-large-scale-1","title":"Robust Speech Recognition via Large-Scale Weak Supervision","date":"2022-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"briansidp/whisperbiasing","path":"whisper/audio.py","file_url":"https://github.com/briansidp/whisperbiasing/blob/HEAD/whisper/audio.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"9f13de1c23e4003d","mcp_get_code":{"code_sha256":"9f13de1c23e4003d"}},{"arxiv_id":"2205.06733","paper":"/paper/improving-the-numerical-reasoning-skills-of","title":"Arithmetic-Based Pretraining -- Improving Numeracy of Pretrained Language Models","date":"2022-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ukplab/emnlp2022-reasoning-aware-pretraining","path":"char_level_representation.py","file_url":"https://github.com/ukplab/emnlp2022-reasoning-aware-pretraining/blob/HEAD/char_level_representation.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":"bd8cd57d2905efde","mcp_get_code":{"code_sha256":"bd8cd57d2905efde"}}]}