{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5IRUEEIEC2RIXQ3HYKLPOCSQAF","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":"01deab8752cffd6cce8beada924514f7bd5c21690ade8bba72a1623375a3469a","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T00:02:15Z","title_canon_sha256":"36b10cdaf627c27f3bd0c4eff85b4c6e9077c6629c0b0759ce73376bb56a3a96"},"schema_version":"1.0","source":{"id":"2406.15487","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15487","created_at":"2026-07-05T08:41:27Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15487v2","created_at":"2026-07-05T08:41:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15487","created_at":"2026-07-05T08:41:27Z"},{"alias_kind":"pith_short_12","alias_value":"5IRUEEIEC2RI","created_at":"2026-07-05T08:41:27Z"},{"alias_kind":"pith_short_16","alias_value":"5IRUEEIEC2RIXQ3H","created_at":"2026-07-05T08:41:27Z"},{"alias_kind":"pith_short_8","alias_value":"5IRUEEIE","created_at":"2026-07-05T08:41:27Z"}],"graph_snapshots":[{"event_id":"sha256:15d966884ac40912a61d51ce0c207c92e4d3140cf716595d5fa182af24459b0d","target":"graph","created_at":"2026-07-05T08:41:27Z","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/2406.15487/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It is an open challenge to obtain high quality training data, especially captions, for text-to-audio models. Although prior methods have leveraged \\textit{text-only language models} to augment and improve captions, such methods have limitations related to scale and coherence between audio and captions. In this work, we propose an audio captioning pipeline that uses an \\textit{audio language model} to synthesize accurate and diverse captions for audio at scale. We leverage this pipeline to produce a dataset of synthetic captions for AudioSet, named \\texttt{AF-AudioSet}, and then evaluate the be","authors_text":"Ambuj Mehrish, Bryan Catanzaro, Deepanway Ghosal, Navonil Majumder, Rafael Valle, Sang-gil Lee, Soujanya Poria, Zhifeng Kong","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T00:02:15Z","title":"Improving Text-To-Audio Models with Synthetic Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15487","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":"sha256:081c8789a5dca13e9d618ffa3c42089a1642f473a28dfb9515772e4fb4de127d","target":"record","created_at":"2026-07-05T08:41:27Z","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":"01deab8752cffd6cce8beada924514f7bd5c21690ade8bba72a1623375a3469a","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T00:02:15Z","title_canon_sha256":"36b10cdaf627c27f3bd0c4eff85b4c6e9077c6629c0b0759ce73376bb56a3a96"},"schema_version":"1.0","source":{"id":"2406.15487","kind":"arxiv","version":2}},"canonical_sha256":"ea2342110416a28bc367c296f70a5001660f5072e236bbff958fe44d7e088f1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea2342110416a28bc367c296f70a5001660f5072e236bbff958fe44d7e088f1c","first_computed_at":"2026-07-05T08:41:27.126360Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:41:27.126360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rKkp62OR8EoUepPxq5AG9glQJwjW8ecVDw8fKapAADWTpSfE06XvZBjfdZGGPIzMUtYVJwFOCwt034uCPpg2AA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:41:27.126852Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.15487","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:081c8789a5dca13e9d618ffa3c42089a1642f473a28dfb9515772e4fb4de127d","sha256:15d966884ac40912a61d51ce0c207c92e4d3140cf716595d5fa182af24459b0d"],"state_sha256":"8f703e70802c29cdf7d0c54e355466a4bd2e910fc57b9c987fb40d848a21ea7e"}