{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AMQTDQER4WTAWIPLE4ZMS36JEU","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":"e0e0de328f47a82ae21228a19ac8e321a7416145debec2d795b1464ded1ffc8d","cross_cats_sorted":["cs.IR","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-16T06:33:26Z","title_canon_sha256":"759f6d4196a877e25db6dcc00a54ab7ccfb1b53ac0b56a7672ed0134c8d4c83d"},"schema_version":"1.0","source":{"id":"2409.10025","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.10025","created_at":"2026-07-05T09:21:48Z"},{"alias_kind":"arxiv_version","alias_value":"2409.10025v2","created_at":"2026-07-05T09:21:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10025","created_at":"2026-07-05T09:21:48Z"},{"alias_kind":"pith_short_12","alias_value":"AMQTDQER4WTA","created_at":"2026-07-05T09:21:48Z"},{"alias_kind":"pith_short_16","alias_value":"AMQTDQER4WTAWIPL","created_at":"2026-07-05T09:21:48Z"},{"alias_kind":"pith_short_8","alias_value":"AMQTDQER","created_at":"2026-07-05T09:21:48Z"}],"graph_snapshots":[{"event_id":"sha256:7412cd776bf4afa3311df833e7a97d1dd9ae905816161f1343e8d11f1d484d0b","target":"graph","created_at":"2026-07-05T09:21:48Z","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/2409.10025/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing audio-text retrieval (ATR) methods are essentially discriminative models that aim to maximize the conditional likelihood, represented as p(candidates|query). Nevertheless, this methodology fails to consider the intrinsic data distribution p(query), leading to difficulties in discerning out-of-distribution data. In this work, we attempt to tackle this constraint through a generative perspective and model the relationship between audio and text as their joint probability p(candidates,query). To this end, we present a diffusion-based ATR framework (DiffATR), which models ATR as an iterat","authors_text":"Xusheng Yang, Xuxin Cheng, Yifei Xin, Yuexian Zou, Zhihong Zhu","cross_cats":["cs.IR","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-16T06:33:26Z","title":"DiffATR: Diffusion-based Generative Modeling for Audio-Text Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10025","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":"sha256:6f4636ad61c3a46c44fcf6a6c10c7dd9df016bc4af3aebf380126535b96d6c00","target":"record","created_at":"2026-07-05T09:21:48Z","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":"e0e0de328f47a82ae21228a19ac8e321a7416145debec2d795b1464ded1ffc8d","cross_cats_sorted":["cs.IR","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-16T06:33:26Z","title_canon_sha256":"759f6d4196a877e25db6dcc00a54ab7ccfb1b53ac0b56a7672ed0134c8d4c83d"},"schema_version":"1.0","source":{"id":"2409.10025","kind":"arxiv","version":2}},"canonical_sha256":"032131c091e5a60b21eb2732c96fc92515fd2f1652d992485868b0210160e926","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"032131c091e5a60b21eb2732c96fc92515fd2f1652d992485868b0210160e926","first_computed_at":"2026-07-05T09:21:48.654380Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:48.654380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hvvxpwyRUfz2Pc1U3EC9xDRLUGY/sQt2ueP6WBpjQWBAAq9jYMYgsX9O8dDo3hLolQl+3xclHYkmI6Vz+jFQDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:48.654860Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.10025","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f4636ad61c3a46c44fcf6a6c10c7dd9df016bc4af3aebf380126535b96d6c00","sha256:7412cd776bf4afa3311df833e7a97d1dd9ae905816161f1343e8d11f1d484d0b"],"state_sha256":"b1dbc2b9e6eb4e711fb4ab4b582849b304a9cc99c4fc1ff2e321ad4b5ef97f6d"}