{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TSHGVIVB2BOUH4XILXXO2FRYAS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7d42f8c4de2752664d22129273038c6ead65c1cd4372966d57f1e012b49f04af","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-09-07T13:40:08Z","title_canon_sha256":"2a4b88587a08276e6103f76776364f1b50c1407588500ea32527e69c6233d7d4"},"schema_version":"1.0","source":{"id":"2209.03143","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.03143","created_at":"2026-07-05T06:34:45Z"},{"alias_kind":"arxiv_version","alias_value":"2209.03143v2","created_at":"2026-07-05T06:34:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.03143","created_at":"2026-07-05T06:34:45Z"},{"alias_kind":"pith_short_12","alias_value":"TSHGVIVB2BOU","created_at":"2026-07-05T06:34:45Z"},{"alias_kind":"pith_short_16","alias_value":"TSHGVIVB2BOUH4XI","created_at":"2026-07-05T06:34:45Z"},{"alias_kind":"pith_short_8","alias_value":"TSHGVIVB","created_at":"2026-07-05T06:34:45Z"}],"graph_snapshots":[{"event_id":"sha256:5ae72f5dfd9eefccf23650ec71e37d0922418a40395f622ffdcbc836b6e77a07","target":"graph","created_at":"2026-07-05T06:34:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2209.03143/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","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","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-09-07T13:40:08Z","title":"AudioLM: a Language Modeling Approach to Audio Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.03143","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3eb632878d61d88ba43205ce686a93953878c7a0a4f980571a5492b014bce231","target":"record","created_at":"2026-07-05T06:34:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7d42f8c4de2752664d22129273038c6ead65c1cd4372966d57f1e012b49f04af","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-09-07T13:40:08Z","title_canon_sha256":"2a4b88587a08276e6103f76776364f1b50c1407588500ea32527e69c6233d7d4"},"schema_version":"1.0","source":{"id":"2209.03143","kind":"arxiv","version":2}},"canonical_sha256":"9c8e6aa2a1d05d43f2e85deeed163804b1502da9369eebc4d1bc880a6e4f5e59","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c8e6aa2a1d05d43f2e85deeed163804b1502da9369eebc4d1bc880a6e4f5e59","first_computed_at":"2026-07-05T06:34:45.730999Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:34:45.730999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JW+uP2pmdjFaPK4OMLzqkKTHAhkyjocPiFY5XU+b0qcxrkuOZapyOwO9hFBkDWJ5rtqtqZY3KbGoeXWnRZqVAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:34:45.731544Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.03143","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3eb632878d61d88ba43205ce686a93953878c7a0a4f980571a5492b014bce231","sha256:5ae72f5dfd9eefccf23650ec71e37d0922418a40395f622ffdcbc836b6e77a07"],"state_sha256":"5b0b313fe588652d1b3cf00ba648f4650edb0f6294a797fbada478faa8e58099"}