{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TSHGVIVB2BOUH4XILXXO2FRYAS","short_pith_number":"pith:TSHGVIVB","schema_version":"1.0","canonical_sha256":"9c8e6aa2a1d05d43f2e85deeed163804b1502da9369eebc4d1bc880a6e4f5e59","source":{"kind":"arxiv","id":"2209.03143","version":2},"attestation_state":"computed","paper":{"title":"AudioLM: a Language Modeling Approach to Audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Damien Vincent, David Grangier, Dominik Roblek, Eugene Kharitonov, Marco Tagliasacchi, Matt Sharifi, Neil Zeghidour, Olivier Pietquin, Olivier Teboul, Rapha\\\"el Marinier, Zal\\'an Borsos","submitted_at":"2022-09-07T13:40:08Z","abstract_excerpt":"We introduce AudioLM, a framework for high-quality audio generation with long-term consistency. AudioLM maps the input audio to a sequence of discrete tokens and casts audio generation as a language modeling task in this representation space. We show how existing audio tokenizers provide different trade-offs between reconstruction quality and long-term structure, and we propose a hybrid tokenization scheme to achieve both objectives. Namely, we leverage the discretized activations of a masked language model pre-trained on audio to capture long-term structure and the discrete codes produced by "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2209.03143","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-09-07T13:40:08Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"2a4b88587a08276e6103f76776364f1b50c1407588500ea32527e69c6233d7d4","abstract_canon_sha256":"7d42f8c4de2752664d22129273038c6ead65c1cd4372966d57f1e012b49f04af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:34:45.731544Z","signature_b64":"JW+uP2pmdjFaPK4OMLzqkKTHAhkyjocPiFY5XU+b0qcxrkuOZapyOwO9hFBkDWJ5rtqtqZY3KbGoeXWnRZqVAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c8e6aa2a1d05d43f2e85deeed163804b1502da9369eebc4d1bc880a6e4f5e59","last_reissued_at":"2026-07-05T06:34:45.730999Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:34:45.730999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AudioLM: a Language Modeling Approach to Audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Damien Vincent, David Grangier, Dominik Roblek, Eugene Kharitonov, Marco Tagliasacchi, Matt Sharifi, Neil Zeghidour, Olivier Pietquin, Olivier Teboul, Rapha\\\"el Marinier, Zal\\'an Borsos","submitted_at":"2022-09-07T13:40:08Z","abstract_excerpt":"We introduce AudioLM, a framework for high-quality audio generation with long-term consistency. AudioLM maps the input audio to a sequence of discrete tokens and casts audio generation as a language modeling task in this representation space. We show how existing audio tokenizers provide different trade-offs between reconstruction quality and long-term structure, and we propose a hybrid tokenization scheme to achieve both objectives. Namely, we leverage the discretized activations of a masked language model pre-trained on audio to capture long-term structure and the discrete codes produced by "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.03143","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2209.03143/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2209.03143","created_at":"2026-07-05T06:34:45.731066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.03143v2","created_at":"2026-07-05T06:34:45.731066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.03143","created_at":"2026-07-05T06:34:45.731066+00:00"},{"alias_kind":"pith_short_12","alias_value":"TSHGVIVB2BOU","created_at":"2026-07-05T06:34:45.731066+00:00"},{"alias_kind":"pith_short_16","alias_value":"TSHGVIVB2BOUH4XI","created_at":"2026-07-05T06:34:45.731066+00:00"},{"alias_kind":"pith_short_8","alias_value":"TSHGVIVB","created_at":"2026-07-05T06:34:45.731066+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06357","citing_title":"F3-Tokenizer: Taming Audio Autoencoder Latents for Understanding and Generation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02385","citing_title":"How Optimality Structures Sparse Dictionaries: A Theory for Understanding SAE Representations","ref_index":279,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28779","citing_title":"Telephony Voice Agent for Banking Services","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25967","citing_title":"Hidden in Plain Tokens: Simply Robust, Gradient-Free Watermark for Synthetic Audio","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20519","citing_title":"Codec-Robust Attacks on Audio LLMs","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2603.03190","citing_title":"Expectation and Acoustic Neural Network Representations Enhance Music Identification from Brain Activity","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20519","citing_title":"Codec-Robust Attacks on Audio LLMs","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21081","citing_title":"Musical Attention Transformer: Music Generation Using a Music-Specific Attention Model","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2509.11717","citing_title":"CodecSep: Prompt-Driven Universal Sound Separation on Neural Audio Codec Latents","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2211.15089","citing_title":"Continuous diffusion for categorical data","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2511.01101","citing_title":"TSVer: A Benchmark for Fact Verification Against Time-Series Evidence","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07571","citing_title":"A Simple Method to Enhance Pre-trained Language Models with Speech Tokens for Classification","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2512.21204","citing_title":"SpidR-Adapt: A Universal Speech Representation Model for Few-Shot Adaptation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2305.02463","citing_title":"Shap-E: Generating Conditional 3D Implicit Functions","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2306.12925","citing_title":"AudioPaLM: A Large Language Model That Can Speak and Listen","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2301.11325","citing_title":"MusicLM: Generating Music From Text","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2301.02111","citing_title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2308.06571","citing_title":"ModelScope Text-to-Video Technical Report","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10281","citing_title":"Drum Synthesis from Expressive Drum Grids via Neural Audio Codecs","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09054","citing_title":"HAFM: Hierarchical Autoregressive Foundation Model for Music Accompaniment Generation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14825","citing_title":"Nautilus: An Auto-Scheduling Tensor Compiler for Efficient Tiled GPU Kernels","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TSHGVIVB2BOUH4XILXXO2FRYAS","json":"https://pith.science/pith/TSHGVIVB2BOUH4XILXXO2FRYAS.json","graph_json":"https://pith.science/api/pith-number/TSHGVIVB2BOUH4XILXXO2FRYAS/graph.json","events_json":"https://pith.science/api/pith-number/TSHGVIVB2BOUH4XILXXO2FRYAS/events.json","paper":"https://pith.science/paper/TSHGVIVB"},"agent_actions":{"view_html":"https://pith.science/pith/TSHGVIVB2BOUH4XILXXO2FRYAS","download_json":"https://pith.science/pith/TSHGVIVB2BOUH4XILXXO2FRYAS.json","view_paper":"https://pith.science/paper/TSHGVIVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.03143&json=true","fetch_graph":"https://pith.science/api/pith-number/TSHGVIVB2BOUH4XILXXO2FRYAS/graph.json","fetch_events":"https://pith.science/api/pith-number/TSHGVIVB2BOUH4XILXXO2FRYAS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TSHGVIVB2BOUH4XILXXO2FRYAS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TSHGVIVB2BOUH4XILXXO2FRYAS/action/storage_attestation","attest_author":"https://pith.science/pith/TSHGVIVB2BOUH4XILXXO2FRYAS/action/author_attestation","sign_citation":"https://pith.science/pith/TSHGVIVB2BOUH4XILXXO2FRYAS/action/citation_signature","submit_replication":"https://pith.science/pith/TSHGVIVB2BOUH4XILXXO2FRYAS/action/replication_record"}},"created_at":"2026-07-05T06:34:45.731066+00:00","updated_at":"2026-07-05T06:34:45.731066+00:00"}