{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HLXZE3MZB2KXMRYAFVXUC2GM6H","short_pith_number":"pith:HLXZE3MZ","schema_version":"1.0","canonical_sha256":"3aef926d990e957647002d6f4168ccf1dee18a77455f3e9d13a3bd8c1198bce8","source":{"kind":"arxiv","id":"2408.02978","version":2},"attestation_state":"computed","paper":{"title":"ASR-enhanced Multimodal Representation Learning for Cross-Domain Product Retrieval","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.MM","authors_text":"Han Li, Jian Jia, Peng Jiang, Quan Chen, Ruixiang Zhao, Xirong Li, Xuehan Bai, Yan Li","submitted_at":"2024-08-06T06:24:10Z","abstract_excerpt":"E-commerce is increasingly multimedia-enriched, with products exhibited in a broad-domain manner as images, short videos, or live stream promotions. A unified and vectorized cross-domain production representation is essential. Due to large intra-product variance and high inter-product similarity in the broad-domain scenario, a visual-only representation is inadequate. While Automatic Speech Recognition (ASR) text derived from the short or live-stream videos is readily accessible, how to de-noise the excessively noisy text for multimodal representation learning is mostly untouched. We propose A"},"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":"2408.02978","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.MM","submitted_at":"2024-08-06T06:24:10Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"36e7970cc23649d944aff4fefe32fa77b48d7b09707c7c11b7a668aac6e31a1f","abstract_canon_sha256":"9ef49b304216cfa42ce4909a9d6fce17c6bd3b3de6f1f62d7c2170efb70ff049"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:23.625053Z","signature_b64":"dy/v8Rw42PmHfGVJud1y+4E/Da4rDcvLHTErd2ZCZLsGNnwJqZ2u2qv3+3Tkk3H8sgQntjZEjqbc8LvYcM7ZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3aef926d990e957647002d6f4168ccf1dee18a77455f3e9d13a3bd8c1198bce8","last_reissued_at":"2026-07-05T11:26:23.624558Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:23.624558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ASR-enhanced Multimodal Representation Learning for Cross-Domain Product Retrieval","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.MM","authors_text":"Han Li, Jian Jia, Peng Jiang, Quan Chen, Ruixiang Zhao, Xirong Li, Xuehan Bai, Yan Li","submitted_at":"2024-08-06T06:24:10Z","abstract_excerpt":"E-commerce is increasingly multimedia-enriched, with products exhibited in a broad-domain manner as images, short videos, or live stream promotions. A unified and vectorized cross-domain production representation is essential. Due to large intra-product variance and high inter-product similarity in the broad-domain scenario, a visual-only representation is inadequate. While Automatic Speech Recognition (ASR) text derived from the short or live-stream videos is readily accessible, how to de-noise the excessively noisy text for multimodal representation learning is mostly untouched. We propose A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02978","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/2408.02978/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":"2408.02978","created_at":"2026-07-05T11:26:23.624618+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.02978v2","created_at":"2026-07-05T11:26:23.624618+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02978","created_at":"2026-07-05T11:26:23.624618+00:00"},{"alias_kind":"pith_short_12","alias_value":"HLXZE3MZB2KX","created_at":"2026-07-05T11:26:23.624618+00:00"},{"alias_kind":"pith_short_16","alias_value":"HLXZE3MZB2KXMRYA","created_at":"2026-07-05T11:26:23.624618+00:00"},{"alias_kind":"pith_short_8","alias_value":"HLXZE3MZ","created_at":"2026-07-05T11:26:23.624618+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/HLXZE3MZB2KXMRYAFVXUC2GM6H","json":"https://pith.science/pith/HLXZE3MZB2KXMRYAFVXUC2GM6H.json","graph_json":"https://pith.science/api/pith-number/HLXZE3MZB2KXMRYAFVXUC2GM6H/graph.json","events_json":"https://pith.science/api/pith-number/HLXZE3MZB2KXMRYAFVXUC2GM6H/events.json","paper":"https://pith.science/paper/HLXZE3MZ"},"agent_actions":{"view_html":"https://pith.science/pith/HLXZE3MZB2KXMRYAFVXUC2GM6H","download_json":"https://pith.science/pith/HLXZE3MZB2KXMRYAFVXUC2GM6H.json","view_paper":"https://pith.science/paper/HLXZE3MZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.02978&json=true","fetch_graph":"https://pith.science/api/pith-number/HLXZE3MZB2KXMRYAFVXUC2GM6H/graph.json","fetch_events":"https://pith.science/api/pith-number/HLXZE3MZB2KXMRYAFVXUC2GM6H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HLXZE3MZB2KXMRYAFVXUC2GM6H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HLXZE3MZB2KXMRYAFVXUC2GM6H/action/storage_attestation","attest_author":"https://pith.science/pith/HLXZE3MZB2KXMRYAFVXUC2GM6H/action/author_attestation","sign_citation":"https://pith.science/pith/HLXZE3MZB2KXMRYAFVXUC2GM6H/action/citation_signature","submit_replication":"https://pith.science/pith/HLXZE3MZB2KXMRYAFVXUC2GM6H/action/replication_record"}},"created_at":"2026-07-05T11:26:23.624618+00:00","updated_at":"2026-07-05T11:26:23.624618+00:00"}