{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AMQTDQER4WTAWIPLE4ZMS36JEU","short_pith_number":"pith:AMQTDQER","schema_version":"1.0","canonical_sha256":"032131c091e5a60b21eb2732c96fc92515fd2f1652d992485868b0210160e926","source":{"kind":"arxiv","id":"2409.10025","version":2},"attestation_state":"computed","paper":{"title":"DiffATR: Diffusion-based Generative Modeling for Audio-Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","eess.AS"],"primary_cat":"cs.SD","authors_text":"Xusheng Yang, Xuxin Cheng, Yifei Xin, Yuexian Zou, Zhihong Zhu","submitted_at":"2024-09-16T06:33:26Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2409.10025","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-16T06:33:26Z","cross_cats_sorted":["cs.IR","eess.AS"],"title_canon_sha256":"759f6d4196a877e25db6dcc00a54ab7ccfb1b53ac0b56a7672ed0134c8d4c83d","abstract_canon_sha256":"e0e0de328f47a82ae21228a19ac8e321a7416145debec2d795b1464ded1ffc8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:48.654860Z","signature_b64":"hvvxpwyRUfz2Pc1U3EC9xDRLUGY/sQt2ueP6WBpjQWBAAq9jYMYgsX9O8dDo3hLolQl+3xclHYkmI6Vz+jFQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"032131c091e5a60b21eb2732c96fc92515fd2f1652d992485868b0210160e926","last_reissued_at":"2026-07-05T09:21:48.654380Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:48.654380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffATR: Diffusion-based Generative Modeling for Audio-Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","eess.AS"],"primary_cat":"cs.SD","authors_text":"Xusheng Yang, Xuxin Cheng, Yifei Xin, Yuexian Zou, Zhihong Zhu","submitted_at":"2024-09-16T06:33:26Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10025","kind":"arxiv","version":2},"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/2409.10025/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.10025","created_at":"2026-07-05T09:21:48.654439+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.10025v2","created_at":"2026-07-05T09:21:48.654439+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10025","created_at":"2026-07-05T09:21:48.654439+00:00"},{"alias_kind":"pith_short_12","alias_value":"AMQTDQER4WTA","created_at":"2026-07-05T09:21:48.654439+00:00"},{"alias_kind":"pith_short_16","alias_value":"AMQTDQER4WTAWIPL","created_at":"2026-07-05T09:21:48.654439+00:00"},{"alias_kind":"pith_short_8","alias_value":"AMQTDQER","created_at":"2026-07-05T09:21:48.654439+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AMQTDQER4WTAWIPLE4ZMS36JEU","json":"https://pith.science/pith/AMQTDQER4WTAWIPLE4ZMS36JEU.json","graph_json":"https://pith.science/api/pith-number/AMQTDQER4WTAWIPLE4ZMS36JEU/graph.json","events_json":"https://pith.science/api/pith-number/AMQTDQER4WTAWIPLE4ZMS36JEU/events.json","paper":"https://pith.science/paper/AMQTDQER"},"agent_actions":{"view_html":"https://pith.science/pith/AMQTDQER4WTAWIPLE4ZMS36JEU","download_json":"https://pith.science/pith/AMQTDQER4WTAWIPLE4ZMS36JEU.json","view_paper":"https://pith.science/paper/AMQTDQER","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.10025&json=true","fetch_graph":"https://pith.science/api/pith-number/AMQTDQER4WTAWIPLE4ZMS36JEU/graph.json","fetch_events":"https://pith.science/api/pith-number/AMQTDQER4WTAWIPLE4ZMS36JEU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AMQTDQER4WTAWIPLE4ZMS36JEU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AMQTDQER4WTAWIPLE4ZMS36JEU/action/storage_attestation","attest_author":"https://pith.science/pith/AMQTDQER4WTAWIPLE4ZMS36JEU/action/author_attestation","sign_citation":"https://pith.science/pith/AMQTDQER4WTAWIPLE4ZMS36JEU/action/citation_signature","submit_replication":"https://pith.science/pith/AMQTDQER4WTAWIPLE4ZMS36JEU/action/replication_record"}},"created_at":"2026-07-05T09:21:48.654439+00:00","updated_at":"2026-07-05T09:21:48.654439+00:00"}