{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HLXZE3MZB2KXMRYAFVXUC2GM6H","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":"9ef49b304216cfa42ce4909a9d6fce17c6bd3b3de6f1f62d7c2170efb70ff049","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.MM","submitted_at":"2024-08-06T06:24:10Z","title_canon_sha256":"36e7970cc23649d944aff4fefe32fa77b48d7b09707c7c11b7a668aac6e31a1f"},"schema_version":"1.0","source":{"id":"2408.02978","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.02978","created_at":"2026-07-05T11:26:23Z"},{"alias_kind":"arxiv_version","alias_value":"2408.02978v2","created_at":"2026-07-05T11:26:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02978","created_at":"2026-07-05T11:26:23Z"},{"alias_kind":"pith_short_12","alias_value":"HLXZE3MZB2KX","created_at":"2026-07-05T11:26:23Z"},{"alias_kind":"pith_short_16","alias_value":"HLXZE3MZB2KXMRYA","created_at":"2026-07-05T11:26:23Z"},{"alias_kind":"pith_short_8","alias_value":"HLXZE3MZ","created_at":"2026-07-05T11:26:23Z"}],"graph_snapshots":[{"event_id":"sha256:0fa9e050b48e49377d79596f0b3ebd3a230a3cce99e11241c24bbc1e6d8aad7e","target":"graph","created_at":"2026-07-05T11:26:23Z","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/2408.02978/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Han Li, Jian Jia, Peng Jiang, Quan Chen, Ruixiang Zhao, Xirong Li, Xuehan Bai, Yan Li","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.MM","submitted_at":"2024-08-06T06:24:10Z","title":"ASR-enhanced Multimodal Representation Learning for Cross-Domain Product Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02978","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":"sha256:01c8ce023cc1b22ca6f3667a952606c41f8529f1ef4456ef92ee8981ce661cea","target":"record","created_at":"2026-07-05T11:26:23Z","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":"9ef49b304216cfa42ce4909a9d6fce17c6bd3b3de6f1f62d7c2170efb70ff049","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.MM","submitted_at":"2024-08-06T06:24:10Z","title_canon_sha256":"36e7970cc23649d944aff4fefe32fa77b48d7b09707c7c11b7a668aac6e31a1f"},"schema_version":"1.0","source":{"id":"2408.02978","kind":"arxiv","version":2}},"canonical_sha256":"3aef926d990e957647002d6f4168ccf1dee18a77455f3e9d13a3bd8c1198bce8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3aef926d990e957647002d6f4168ccf1dee18a77455f3e9d13a3bd8c1198bce8","first_computed_at":"2026-07-05T11:26:23.624558Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:23.624558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dy/v8Rw42PmHfGVJud1y+4E/Da4rDcvLHTErd2ZCZLsGNnwJqZ2u2qv3+3Tkk3H8sgQntjZEjqbc8LvYcM7ZAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:23.625053Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.02978","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01c8ce023cc1b22ca6f3667a952606c41f8529f1ef4456ef92ee8981ce661cea","sha256:0fa9e050b48e49377d79596f0b3ebd3a230a3cce99e11241c24bbc1e6d8aad7e"],"state_sha256":"ea436aae127f04a53d33ad6fc466b4ab5b30052ae6888c696e7ba0cf3b305aac"}