{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AZK4ATHZEJ5KJHSVTCPMJZPTPS","short_pith_number":"pith:AZK4ATHZ","schema_version":"1.0","canonical_sha256":"0655c04cf9227aa49e55989ec4e5f37c8f0aa7d013d13c25b0d22400e387a05a","source":{"kind":"arxiv","id":"2508.11801","version":1},"attestation_state":"computed","paper":{"title":"VideoAVE: A Multi-Attribute Video-to-Text Attribute Value Extraction Dataset and Benchmark Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hoda Eldardiry, Jiaying Gong, Jiazhen Hu, Ming Cheng, Tong Wu","submitted_at":"2025-08-15T20:58:47Z","abstract_excerpt":"Attribute Value Extraction (AVE) is important for structuring product information in e-commerce. However, existing AVE datasets are primarily limited to text-to-text or image-to-text settings, lacking support for product videos, diverse attribute coverage, and public availability. To address these gaps, we introduce VideoAVE, the first publicly available video-to-text e-commerce AVE dataset across 14 different domains and covering 172 unique attributes. To ensure data quality, we propose a post-hoc CLIP-based Mixture of Experts filtering system (CLIP-MoE) to remove the mismatched video-product"},"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":"2508.11801","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-15T20:58:47Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e1ccb33d267939f5520f9461eef523f7a7b2904fd1cd66240a8898303b1ae0da","abstract_canon_sha256":"e4514b645aa3241ac3679a6225070b286c3d604de9d725840f7f17345bb2ddf8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:54.707571Z","signature_b64":"nS2nfKrY5Cx0Xqk6KKdQYLqo6vqEYBP563FT32hiWKbF2D1nvp91DxFWZDxMMQ/N0kfpxC1H/7WcR9fpF735AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0655c04cf9227aa49e55989ec4e5f37c8f0aa7d013d13c25b0d22400e387a05a","last_reissued_at":"2026-07-05T11:54:54.707021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:54.707021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoAVE: A Multi-Attribute Video-to-Text Attribute Value Extraction Dataset and Benchmark Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hoda Eldardiry, Jiaying Gong, Jiazhen Hu, Ming Cheng, Tong Wu","submitted_at":"2025-08-15T20:58:47Z","abstract_excerpt":"Attribute Value Extraction (AVE) is important for structuring product information in e-commerce. However, existing AVE datasets are primarily limited to text-to-text or image-to-text settings, lacking support for product videos, diverse attribute coverage, and public availability. To address these gaps, we introduce VideoAVE, the first publicly available video-to-text e-commerce AVE dataset across 14 different domains and covering 172 unique attributes. To ensure data quality, we propose a post-hoc CLIP-based Mixture of Experts filtering system (CLIP-MoE) to remove the mismatched video-product"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11801","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/2508.11801/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":"2508.11801","created_at":"2026-07-05T11:54:54.707083+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.11801v1","created_at":"2026-07-05T11:54:54.707083+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11801","created_at":"2026-07-05T11:54:54.707083+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZK4ATHZEJ5K","created_at":"2026-07-05T11:54:54.707083+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZK4ATHZEJ5KJHSV","created_at":"2026-07-05T11:54:54.707083+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZK4ATHZ","created_at":"2026-07-05T11:54:54.707083+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/AZK4ATHZEJ5KJHSVTCPMJZPTPS","json":"https://pith.science/pith/AZK4ATHZEJ5KJHSVTCPMJZPTPS.json","graph_json":"https://pith.science/api/pith-number/AZK4ATHZEJ5KJHSVTCPMJZPTPS/graph.json","events_json":"https://pith.science/api/pith-number/AZK4ATHZEJ5KJHSVTCPMJZPTPS/events.json","paper":"https://pith.science/paper/AZK4ATHZ"},"agent_actions":{"view_html":"https://pith.science/pith/AZK4ATHZEJ5KJHSVTCPMJZPTPS","download_json":"https://pith.science/pith/AZK4ATHZEJ5KJHSVTCPMJZPTPS.json","view_paper":"https://pith.science/paper/AZK4ATHZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.11801&json=true","fetch_graph":"https://pith.science/api/pith-number/AZK4ATHZEJ5KJHSVTCPMJZPTPS/graph.json","fetch_events":"https://pith.science/api/pith-number/AZK4ATHZEJ5KJHSVTCPMJZPTPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZK4ATHZEJ5KJHSVTCPMJZPTPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZK4ATHZEJ5KJHSVTCPMJZPTPS/action/storage_attestation","attest_author":"https://pith.science/pith/AZK4ATHZEJ5KJHSVTCPMJZPTPS/action/author_attestation","sign_citation":"https://pith.science/pith/AZK4ATHZEJ5KJHSVTCPMJZPTPS/action/citation_signature","submit_replication":"https://pith.science/pith/AZK4ATHZEJ5KJHSVTCPMJZPTPS/action/replication_record"}},"created_at":"2026-07-05T11:54:54.707083+00:00","updated_at":"2026-07-05T11:54:54.707083+00:00"}