{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6A3RYLSTAY2COGNFEAY5YW35GF","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":"70effce4d16e604c4f4edf6eabde4eed54aba8c4420658eeb41d15f86f8116ba","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-12-25T22:24:49Z","title_canon_sha256":"79057c69eb613c6d534d2b44557858fca9659bf1ffce97257c61d35985d14e57"},"schema_version":"1.0","source":{"id":"2312.15821","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.15821","created_at":"2026-07-05T07:28:01Z"},{"alias_kind":"arxiv_version","alias_value":"2312.15821v1","created_at":"2026-07-05T07:28:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15821","created_at":"2026-07-05T07:28:01Z"},{"alias_kind":"pith_short_12","alias_value":"6A3RYLSTAY2C","created_at":"2026-07-05T07:28:01Z"},{"alias_kind":"pith_short_16","alias_value":"6A3RYLSTAY2COGNF","created_at":"2026-07-05T07:28:01Z"},{"alias_kind":"pith_short_8","alias_value":"6A3RYLST","created_at":"2026-07-05T07:28:01Z"}],"graph_snapshots":[{"event_id":"sha256:2881c385ed9d771ad5a6ff464e015f9665b14ecd9609a37351609fcfb6e861cf","target":"graph","created_at":"2026-07-05T07:28:01Z","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/2312.15821/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio is an essential part of our life, but creating it often requires expertise and is time-consuming. Research communities have made great progress over the past year advancing the performance of large scale audio generative models for a single modality (speech, sound, or music) through adopting more powerful generative models and scaling data. However, these models lack controllability in several aspects: speech generation models cannot synthesize novel styles based on text description and are limited on domain coverage such as outdoor environments; sound generation models only provide coar","authors_text":"Akinniyi Akinyemi, Alice Rakotoarison, Andros Tjandra, Apoorv Vyas, Baishan Guo, Bapi Akula, Bowen Shi, Brian Ellis, Carleigh Wood, Chris Summers, Ivan Cruz, Jeff Wang, Jiemin Zhang, Joshua Lane, Liang Tan, Mary Williamson, Matthew Le, Rashel Moritz, Robert Adkins, Wei-Ning Hsu, William Ngan, Xinyue Zhang, Yael Yungster, Yi-Chiao Wu","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-12-25T22:24:49Z","title":"Audiobox: Unified Audio Generation with Natural Language Prompts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15821","kind":"arxiv","version":1},"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":"sha256:05e4f5df7945919e8060ffafa367cacdbd999f103e5c97aaf62544a1778fc4a3","target":"record","created_at":"2026-07-05T07:28:01Z","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":"70effce4d16e604c4f4edf6eabde4eed54aba8c4420658eeb41d15f86f8116ba","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-12-25T22:24:49Z","title_canon_sha256":"79057c69eb613c6d534d2b44557858fca9659bf1ffce97257c61d35985d14e57"},"schema_version":"1.0","source":{"id":"2312.15821","kind":"arxiv","version":1}},"canonical_sha256":"f0371c2e5306342719a52031dc5b7d3141f504793bcc11795247a8368398aa69","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0371c2e5306342719a52031dc5b7d3141f504793bcc11795247a8368398aa69","first_computed_at":"2026-07-05T07:28:01.880184Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:01.880184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"prPjrD8wPoAq3OZ2Gnv/zqqqsBIxEO+wPnI4NY5lto1+5QTkTrQuz3E0qdCXqb++7nQiBz/qVJMj0f7F+QJNCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:01.880691Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.15821","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05e4f5df7945919e8060ffafa367cacdbd999f103e5c97aaf62544a1778fc4a3","sha256:2881c385ed9d771ad5a6ff464e015f9665b14ecd9609a37351609fcfb6e861cf"],"state_sha256":"3bc06cb93df6099c1bfb22112a822f318ec430ace9012b898ea1faa9a94ef362"}