{"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/sinusoids","entry":"sinusoids","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":13,"n_papers_ran":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":6,"n_samples_ran":3,"n_samples_fingerprinted":3,"n_places":14,"n_places_pointer_only":6,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"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":"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/model.py","file_url":"https://github.com/openai/whisper/blob/HEAD/whisper/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e529c9641c178fe0","mcp_get_code":{"code_sha256":"e529c9641c178fe0"}},{"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/model.py","file_url":"https://github.com/WeifeiJin/ALMGuard/blob/HEAD/whisper/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e529c9641c178fe0","mcp_get_code":{"code_sha256":"e529c9641c178fe0"}},{"arxiv_id":"2506.15220","paper":"/paper/video-salmonn-2-captioning-enhanced-audio","title":"video-SALMONN 2: Captioning-Enhanced Audio-Visual Large Language Models","date":"2025-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bytedance/video-salmonn-2","path":"video_SALMONN2_plus/qwenvl/model/modeling_whisper.py","file_url":"https://github.com/bytedance/video-salmonn-2/blob/HEAD/video_SALMONN2_plus/qwenvl/model/modeling_whisper.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":"ec2159dcc8c21e1d","mcp_get_code":{"code_sha256":"ec2159dcc8c21e1d"}},{"arxiv_id":"2412.02612","paper":"/paper/glm-4-voice-towards-intelligent-and-human","title":"GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot","date":"2024-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thudm/glm-4-voice","path":"speech_tokenizer/modeling_whisper.py","file_url":"https://github.com/thudm/glm-4-voice/blob/HEAD/speech_tokenizer/modeling_whisper.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":"04714b15c8ffaf40","mcp_get_code":{"code_sha256":"04714b15c8ffaf40"}},{"arxiv_id":"2407.04051","paper":"/paper/funaudiollm-voice-understanding-and","title":"FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs","date":"2024-07-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xingchensong/s3tokenizer","path":"s3tokenizer/model.py","file_url":"https://github.com/xingchensong/s3tokenizer/blob/HEAD/s3tokenizer/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e529c9641c178fe0","mcp_get_code":{"code_sha256":"e529c9641c178fe0"}},{"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/model.py","file_url":"https://github.com/roudimit/whisper-flamingo/blob/HEAD/whisper/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e529c9641c178fe0","mcp_get_code":{"code_sha256":"e529c9641c178fe0"}},{"arxiv_id":"2310.00704","paper":"/paper/uniaudio-an-audio-foundation-model-toward-1","title":"UniAudio: An Audio Foundation Model Toward Universal Audio Generation","date":null,"month_inferred_from_arxiv_id":"2023-10","title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"e529c9641c178fe0","mcp_get_code":{"code_sha256":"e529c9641c178fe0"}},{"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/model.py","file_url":"https://github.com/hypotheses-paradise/hypo2trans/blob/HEAD/generate_data/whisper/whisper/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e529c9641c178fe0","mcp_get_code":{"code_sha256":"e529c9641c178fe0"}},{"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":"models/prior.py","file_url":"https://github.com/YasserdahouML/Lip2Vec/blob/HEAD/models/prior.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a314b3fcba001058","mcp_get_code":{"code_sha256":"a314b3fcba001058"}},{"arxiv_id":"2307.16372","paper":"/paper/lp-musiccaps-llm-based-pseudo-music","title":"LP-MusicCaps: LLM-Based Pseudo Music Captioning","date":"2023-07-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seungheondoh/lp-music-caps","path":"lpmc/music_captioning/model/modules.py","file_url":"https://github.com/seungheondoh/lp-music-caps/blob/HEAD/lpmc/music_captioning/model/modules.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e04a7c27c2fe82f7","mcp_get_code":{"code_sha256":"e04a7c27c2fe82f7"}},{"arxiv_id":"2307.03183","paper":"/paper/whisper-at-noise-robust-automatic-speech","title":"Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers","date":null,"month_inferred_from_arxiv_id":"2023-07","title_source":"archive","repo":"YuanGongND/whisper-at","path":"package/whisper-at/whisper_at/model.py","file_url":"https://github.com/YuanGongND/whisper-at/blob/HEAD/package/whisper-at/whisper_at/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"e529c9641c178fe0","mcp_get_code":{"code_sha256":"e529c9641c178fe0"}},{"arxiv_id":"2306.05284","paper":"/paper/simple-and-controllable-music-generation","title":"Simple and Controllable Music Generation","date":"2023-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"collabora/whisperspeech","path":"whisperspeech/modules.py","file_url":"https://github.com/collabora/whisperspeech/blob/HEAD/whisperspeech/modules.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a314b3fcba001058","mcp_get_code":{"code_sha256":"a314b3fcba001058"}},{"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/model.py","file_url":"https://github.com/briansidp/whisperbiasing/blob/HEAD/whisper/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"e529c9641c178fe0","mcp_get_code":{"code_sha256":"e529c9641c178fe0"}},{"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":"kadirnar/whisper-plus","path":"whisperplus/pipelines/lightning_whisper_mlx/torch_whisper.py","file_url":"https://github.com/kadirnar/whisper-plus/blob/HEAD/whisperplus/pipelines/lightning_whisper_mlx/torch_whisper.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":"407b4297398ff29d","mcp_get_code":{"code_sha256":"407b4297398ff29d"}}]}