{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:POEWCBW2UWGOTSETIWZIW4DY2V","short_pith_number":"pith:POEWCBW2","canonical_record":{"source":{"id":"2505.10561","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-15T17:59:29Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"9135475023c4c802e8b3875c90f1a1c257ef7f7dd69c1b5509eb814318bbca26","abstract_canon_sha256":"8288b35c3a560faa2d94b70437d3aad717b8c0c85affb5b9dbf6b40941220fb2"},"schema_version":"1.0"},"canonical_sha256":"7b896106daa58ce9c89345b28b7078d56f1a9ddfc074cfdbafad1d9683f1b10c","source":{"kind":"arxiv","id":"2505.10561","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.10561","created_at":"2026-07-05T11:03:45Z"},{"alias_kind":"arxiv_version","alias_value":"2505.10561v1","created_at":"2026-07-05T11:03:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10561","created_at":"2026-07-05T11:03:45Z"},{"alias_kind":"pith_short_12","alias_value":"POEWCBW2UWGO","created_at":"2026-07-05T11:03:45Z"},{"alias_kind":"pith_short_16","alias_value":"POEWCBW2UWGOTSET","created_at":"2026-07-05T11:03:45Z"},{"alias_kind":"pith_short_8","alias_value":"POEWCBW2","created_at":"2026-07-05T11:03:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:POEWCBW2UWGOTSETIWZIW4DY2V","target":"record","payload":{"canonical_record":{"source":{"id":"2505.10561","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-15T17:59:29Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"9135475023c4c802e8b3875c90f1a1c257ef7f7dd69c1b5509eb814318bbca26","abstract_canon_sha256":"8288b35c3a560faa2d94b70437d3aad717b8c0c85affb5b9dbf6b40941220fb2"},"schema_version":"1.0"},"canonical_sha256":"7b896106daa58ce9c89345b28b7078d56f1a9ddfc074cfdbafad1d9683f1b10c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:45.734714Z","signature_b64":"Tg+DWXqNoGkJqBZqGlRYpDcwZ7lVruOt2IGu9QBLrJudisrtmg+vsloxUT1LWzaFkaGzPGvzsW5S5yGrjHqPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b896106daa58ce9c89345b28b7078d56f1a9ddfc074cfdbafad1d9683f1b10c","last_reissued_at":"2026-07-05T11:03:45.734092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:45.734092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.10561","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:03:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W/ENK1ryV/pTlB8GwD2sFbpr3xtYfpbDnzDmPxbpQrzfMuUa6v92pZfsK8SjGeJosbUa/5uwdNpg2AynExKkAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:53:15.963350Z"},"content_sha256":"689e918ebca060b9e00120b851dd3a7b5b54a86d6287dcb34b6b15cde13fe086","schema_version":"1.0","event_id":"sha256:689e918ebca060b9e00120b851dd3a7b5b54a86d6287dcb34b6b15cde13fe086"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:POEWCBW2UWGOTSETIWZIW4DY2V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"T2A-Feedback: Improving Basic Capabilities of Text-to-Audio Generation via Fine-grained AI Feedback","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chen Zhu, Jiawei Huang, Ke Lei, Luping Liu, Sashuai Zhou, Shengpeng Ji, Tao Jin, Xize Cheng, Zehan Wang, Zhenhui Ye, Zhou Zhao","submitted_at":"2025-05-15T17:59:29Z","abstract_excerpt":"Text-to-audio (T2A) generation has achieved remarkable progress in generating a variety of audio outputs from language prompts. However, current state-of-the-art T2A models still struggle to satisfy human preferences for prompt-following and acoustic quality when generating complex multi-event audio. To improve the performance of the model in these high-level applications, we propose to enhance the basic capabilities of the model with AI feedback learning. First, we introduce fine-grained AI audio scoring pipelines to: 1) verify whether each event in the text prompt is present in the audio (Ev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10561","kind":"arxiv","version":1},"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/2505.10561/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:03:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aAxWYO5ma/L3sOxxnsEfW22sBPag23s9VqpYBy54FKLyBpuS73Wu4H5XqqRWo3QRWNxizzJgfwQUfXbIUW+LDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:53:15.964953Z"},"content_sha256":"19a8b68dc4fd841e20c645e5987168f237fb732a44f103452b8f72a87ae62fb5","schema_version":"1.0","event_id":"sha256:19a8b68dc4fd841e20c645e5987168f237fb732a44f103452b8f72a87ae62fb5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/POEWCBW2UWGOTSETIWZIW4DY2V/bundle.json","state_url":"https://pith.science/pith/POEWCBW2UWGOTSETIWZIW4DY2V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/POEWCBW2UWGOTSETIWZIW4DY2V/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T13:53:15Z","links":{"resolver":"https://pith.science/pith/POEWCBW2UWGOTSETIWZIW4DY2V","bundle":"https://pith.science/pith/POEWCBW2UWGOTSETIWZIW4DY2V/bundle.json","state":"https://pith.science/pith/POEWCBW2UWGOTSETIWZIW4DY2V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/POEWCBW2UWGOTSETIWZIW4DY2V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:POEWCBW2UWGOTSETIWZIW4DY2V","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":"8288b35c3a560faa2d94b70437d3aad717b8c0c85affb5b9dbf6b40941220fb2","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-15T17:59:29Z","title_canon_sha256":"9135475023c4c802e8b3875c90f1a1c257ef7f7dd69c1b5509eb814318bbca26"},"schema_version":"1.0","source":{"id":"2505.10561","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.10561","created_at":"2026-07-05T11:03:45Z"},{"alias_kind":"arxiv_version","alias_value":"2505.10561v1","created_at":"2026-07-05T11:03:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10561","created_at":"2026-07-05T11:03:45Z"},{"alias_kind":"pith_short_12","alias_value":"POEWCBW2UWGO","created_at":"2026-07-05T11:03:45Z"},{"alias_kind":"pith_short_16","alias_value":"POEWCBW2UWGOTSET","created_at":"2026-07-05T11:03:45Z"},{"alias_kind":"pith_short_8","alias_value":"POEWCBW2","created_at":"2026-07-05T11:03:45Z"}],"graph_snapshots":[{"event_id":"sha256:19a8b68dc4fd841e20c645e5987168f237fb732a44f103452b8f72a87ae62fb5","target":"graph","created_at":"2026-07-05T11:03:45Z","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/2505.10561/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-audio (T2A) generation has achieved remarkable progress in generating a variety of audio outputs from language prompts. However, current state-of-the-art T2A models still struggle to satisfy human preferences for prompt-following and acoustic quality when generating complex multi-event audio. To improve the performance of the model in these high-level applications, we propose to enhance the basic capabilities of the model with AI feedback learning. First, we introduce fine-grained AI audio scoring pipelines to: 1) verify whether each event in the text prompt is present in the audio (Ev","authors_text":"Chen Zhu, Jiawei Huang, Ke Lei, Luping Liu, Sashuai Zhou, Shengpeng Ji, Tao Jin, Xize Cheng, Zehan Wang, Zhenhui Ye, Zhou Zhao","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-15T17:59:29Z","title":"T2A-Feedback: Improving Basic Capabilities of Text-to-Audio Generation via Fine-grained AI Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10561","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":"sha256:689e918ebca060b9e00120b851dd3a7b5b54a86d6287dcb34b6b15cde13fe086","target":"record","created_at":"2026-07-05T11:03:45Z","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":"8288b35c3a560faa2d94b70437d3aad717b8c0c85affb5b9dbf6b40941220fb2","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-15T17:59:29Z","title_canon_sha256":"9135475023c4c802e8b3875c90f1a1c257ef7f7dd69c1b5509eb814318bbca26"},"schema_version":"1.0","source":{"id":"2505.10561","kind":"arxiv","version":1}},"canonical_sha256":"7b896106daa58ce9c89345b28b7078d56f1a9ddfc074cfdbafad1d9683f1b10c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b896106daa58ce9c89345b28b7078d56f1a9ddfc074cfdbafad1d9683f1b10c","first_computed_at":"2026-07-05T11:03:45.734092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:45.734092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tg+DWXqNoGkJqBZqGlRYpDcwZ7lVruOt2IGu9QBLrJudisrtmg+vsloxUT1LWzaFkaGzPGvzsW5S5yGrjHqPAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:45.734714Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.10561","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:689e918ebca060b9e00120b851dd3a7b5b54a86d6287dcb34b6b15cde13fe086","sha256:19a8b68dc4fd841e20c645e5987168f237fb732a44f103452b8f72a87ae62fb5"],"state_sha256":"d67197263afc918337d722189702996fc59c026d65b7c87db6569f7513288a18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G4UURE1qf8C7jiwzb7Xf8RzX+BXjqPUOnFI4/z992vhGWvDVyPfkUZ1N4A/fpYjmnskUczUBHC9l7oAgjTKuAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T13:53:15.971435Z","bundle_sha256":"b14ec7c21a2bf23c61498b679ed76e13d3a7305ffe8489d43b2c070082eb1e7f"}}