{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CQXWZXR64OZYXHGENQEAWEQ4AK","short_pith_number":"pith:CQXWZXR6","canonical_record":{"source":{"id":"2402.00744","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-02-01T16:39:47Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"62874150d18dff5db936130f35e7aec171255c4712b2912084916f9facc1913a","abstract_canon_sha256":"8048063ef2ef31e740652acfbc7e0342cd36486a4ddeef455f546a05a3ef16e7"},"schema_version":"1.0"},"canonical_sha256":"142f6cde3ee3b38b9cc46c080b121c028156397fc7d0667979341816ecfac3f3","source":{"kind":"arxiv","id":"2402.00744","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.00744","created_at":"2026-07-05T07:40:17Z"},{"alias_kind":"arxiv_version","alias_value":"2402.00744v1","created_at":"2026-07-05T07:40:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00744","created_at":"2026-07-05T07:40:17Z"},{"alias_kind":"pith_short_12","alias_value":"CQXWZXR64OZY","created_at":"2026-07-05T07:40:17Z"},{"alias_kind":"pith_short_16","alias_value":"CQXWZXR64OZYXHGE","created_at":"2026-07-05T07:40:17Z"},{"alias_kind":"pith_short_8","alias_value":"CQXWZXR6","created_at":"2026-07-05T07:40:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CQXWZXR64OZYXHGENQEAWEQ4AK","target":"record","payload":{"canonical_record":{"source":{"id":"2402.00744","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-02-01T16:39:47Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"62874150d18dff5db936130f35e7aec171255c4712b2912084916f9facc1913a","abstract_canon_sha256":"8048063ef2ef31e740652acfbc7e0342cd36486a4ddeef455f546a05a3ef16e7"},"schema_version":"1.0"},"canonical_sha256":"142f6cde3ee3b38b9cc46c080b121c028156397fc7d0667979341816ecfac3f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:17.220390Z","signature_b64":"URCyGSMDrbMvHPxeq+TCje9KgMkzD8mOvxSqY2Tp477X0nKwj2xpf2kISU2ZVreKO5ceFOS6SgpbwQ50GvffDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"142f6cde3ee3b38b9cc46c080b121c028156397fc7d0667979341816ecfac3f3","last_reissued_at":"2026-07-05T07:40:17.219921Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:17.219921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.00744","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":"2026-07-05T07:40:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GaAObNnplwnLKWcbyBC69L6P6rO4aN7x46NN7pVUZTTXF1Fa9SqsnBFYEG1RIaJqHrSH+dPAsYHlyQk35KbaAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T21:50:10.104455Z"},"content_sha256":"89164ad204ac559fb047365ea086d32072ce2a22523947f884a4ac0816b11ad9","schema_version":"1.0","event_id":"sha256:89164ad204ac559fb047365ea086d32072ce2a22523947f884a4ac0816b11ad9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CQXWZXR64OZYXHGENQEAWEQ4AK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BATON: Aligning Text-to-Audio Model with Human Preference Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Haonan Han, Huan Liao, Jiasheng Lu, Jingquan Liu, Kai Yang, Qinmei Xu, Rui Yang, Tianjiao Du, Xiu Li, Zunnan Xu","submitted_at":"2024-02-01T16:39:47Z","abstract_excerpt":"With the development of AI-Generated Content (AIGC), text-to-audio models are gaining widespread attention. However, it is challenging for these models to generate audio aligned with human preference due to the inherent information density of natural language and limited model understanding ability. To alleviate this issue, we formulate the BATON, a framework designed to enhance the alignment between generated audio and text prompt using human preference feedback. Our BATON comprises three key stages: Firstly, we curated a dataset containing both prompts and the corresponding generated audio, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00744","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/2402.00744/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":"2026-07-05T07:40:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z++1WiBSXBGnlmXVeOJOcKWtc96DW9fQyhpYqbWWesI/sX1aPYA0TH//c/QQADOtfj7bEhveVHT9LEISgRJuAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T21:50:10.104965Z"},"content_sha256":"286fa557dba0a41700a038e07e66b55bd3e3d85c26cd21100b4ec56eecbcb12f","schema_version":"1.0","event_id":"sha256:286fa557dba0a41700a038e07e66b55bd3e3d85c26cd21100b4ec56eecbcb12f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CQXWZXR64OZYXHGENQEAWEQ4AK/bundle.json","state_url":"https://pith.science/pith/CQXWZXR64OZYXHGENQEAWEQ4AK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CQXWZXR64OZYXHGENQEAWEQ4AK/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":"2026-08-22T21:50:10Z","links":{"resolver":"https://pith.science/pith/CQXWZXR64OZYXHGENQEAWEQ4AK","bundle":"https://pith.science/pith/CQXWZXR64OZYXHGENQEAWEQ4AK/bundle.json","state":"https://pith.science/pith/CQXWZXR64OZYXHGENQEAWEQ4AK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CQXWZXR64OZYXHGENQEAWEQ4AK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CQXWZXR64OZYXHGENQEAWEQ4AK","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":"8048063ef2ef31e740652acfbc7e0342cd36486a4ddeef455f546a05a3ef16e7","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-02-01T16:39:47Z","title_canon_sha256":"62874150d18dff5db936130f35e7aec171255c4712b2912084916f9facc1913a"},"schema_version":"1.0","source":{"id":"2402.00744","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.00744","created_at":"2026-07-05T07:40:17Z"},{"alias_kind":"arxiv_version","alias_value":"2402.00744v1","created_at":"2026-07-05T07:40:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00744","created_at":"2026-07-05T07:40:17Z"},{"alias_kind":"pith_short_12","alias_value":"CQXWZXR64OZY","created_at":"2026-07-05T07:40:17Z"},{"alias_kind":"pith_short_16","alias_value":"CQXWZXR64OZYXHGE","created_at":"2026-07-05T07:40:17Z"},{"alias_kind":"pith_short_8","alias_value":"CQXWZXR6","created_at":"2026-07-05T07:40:17Z"}],"graph_snapshots":[{"event_id":"sha256:286fa557dba0a41700a038e07e66b55bd3e3d85c26cd21100b4ec56eecbcb12f","target":"graph","created_at":"2026-07-05T07:40:17Z","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/2402.00744/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the development of AI-Generated Content (AIGC), text-to-audio models are gaining widespread attention. However, it is challenging for these models to generate audio aligned with human preference due to the inherent information density of natural language and limited model understanding ability. To alleviate this issue, we formulate the BATON, a framework designed to enhance the alignment between generated audio and text prompt using human preference feedback. Our BATON comprises three key stages: Firstly, we curated a dataset containing both prompts and the corresponding generated audio, ","authors_text":"Haonan Han, Huan Liao, Jiasheng Lu, Jingquan Liu, Kai Yang, Qinmei Xu, Rui Yang, Tianjiao Du, Xiu Li, Zunnan Xu","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-02-01T16:39:47Z","title":"BATON: Aligning Text-to-Audio Model with Human Preference Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00744","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":"sha256:89164ad204ac559fb047365ea086d32072ce2a22523947f884a4ac0816b11ad9","target":"record","created_at":"2026-07-05T07:40:17Z","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":"8048063ef2ef31e740652acfbc7e0342cd36486a4ddeef455f546a05a3ef16e7","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-02-01T16:39:47Z","title_canon_sha256":"62874150d18dff5db936130f35e7aec171255c4712b2912084916f9facc1913a"},"schema_version":"1.0","source":{"id":"2402.00744","kind":"arxiv","version":1}},"canonical_sha256":"142f6cde3ee3b38b9cc46c080b121c028156397fc7d0667979341816ecfac3f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"142f6cde3ee3b38b9cc46c080b121c028156397fc7d0667979341816ecfac3f3","first_computed_at":"2026-07-05T07:40:17.219921Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:40:17.219921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"URCyGSMDrbMvHPxeq+TCje9KgMkzD8mOvxSqY2Tp477X0nKwj2xpf2kISU2ZVreKO5ceFOS6SgpbwQ50GvffDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:40:17.220390Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.00744","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89164ad204ac559fb047365ea086d32072ce2a22523947f884a4ac0816b11ad9","sha256:286fa557dba0a41700a038e07e66b55bd3e3d85c26cd21100b4ec56eecbcb12f"],"state_sha256":"a5987a4a18b1d82b49a09610923a210878c5b3e70f1fc6a65dc274e0ce1ff754"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XAERtWlkOOTAP0e+GgrRWHy4N3/rBSTnwDU2JUgURJ327sP4EWVwvA+oXofe2cXgGG2wtG8Akb2MbZm4WkjWDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T21:50:10.113835Z","bundle_sha256":"37c74474ce93af140372099ee83c66f01152f2f84b78c9a5af3735d065d064b9"}}