{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DBPSTTJFZ26COC23ZSU4SUVIIF","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":"27da1a247e8a4405c44a587f4e86e0981c2b6e81d6d6a091b69308817b47c840","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-22T15:39:44Z","title_canon_sha256":"013dad5aede58658f3533d4bb1af0ba991f2fd226e68dc6b2bbc7d581547363f"},"schema_version":"1.0","source":{"id":"2311.02084","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.02084","created_at":"2026-07-05T07:49:15Z"},{"alias_kind":"arxiv_version","alias_value":"2311.02084v2","created_at":"2026-07-05T07:49:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02084","created_at":"2026-07-05T07:49:15Z"},{"alias_kind":"pith_short_12","alias_value":"DBPSTTJFZ26C","created_at":"2026-07-05T07:49:15Z"},{"alias_kind":"pith_short_16","alias_value":"DBPSTTJFZ26COC23","created_at":"2026-07-05T07:49:15Z"},{"alias_kind":"pith_short_8","alias_value":"DBPSTTJF","created_at":"2026-07-05T07:49:15Z"}],"graph_snapshots":[{"event_id":"sha256:31690cc82b675b8a54c526909de922c9a9a883a9ae1e7e707f356fe965670880","target":"graph","created_at":"2026-07-05T07:49:15Z","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/2311.02084/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Product embedding serves as a cornerstone for a wide range of applications in eCommerce. The product embedding learned from multiple modalities shows significant improvement over that from a single modality, since different modalities provide complementary information. However, some modalities are more informatively dominant than others. How to teach a model to learn embedding from different modalities without neglecting information from the less dominant modality is challenging. We present an image-text embedding model (ITEm), an unsupervised learning method that is designed to better attend ","authors_text":"Baohao Liao, Jiangbo Yuan, Michael Kozielski, Sanjika Hewavitharana, Shahram Khadivi, Tomer Lancewicki","cross_cats":["cs.CL","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-22T15:39:44Z","title":"ITEm: Unsupervised Image-Text Embedding Learning for eCommerce"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02084","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":"sha256:0f133d5d23b81356c509c82752f987abdc244d0c53eeae08d5c311f20b2c361c","target":"record","created_at":"2026-07-05T07:49:15Z","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":"27da1a247e8a4405c44a587f4e86e0981c2b6e81d6d6a091b69308817b47c840","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-22T15:39:44Z","title_canon_sha256":"013dad5aede58658f3533d4bb1af0ba991f2fd226e68dc6b2bbc7d581547363f"},"schema_version":"1.0","source":{"id":"2311.02084","kind":"arxiv","version":2}},"canonical_sha256":"185f29cd25cebc270b5bcca9c952a841450797d6932f9e1067c1eb2e63f24aa8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"185f29cd25cebc270b5bcca9c952a841450797d6932f9e1067c1eb2e63f24aa8","first_computed_at":"2026-07-05T07:49:15.746868Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:49:15.746868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3COrsoMZBvwwAsjH6onIX6ImoXuD6EnZJvOwUL7uzUek4gsRmuIDSxStTJaM4Xfxwy0Sa4OUZhEzM3r4FbmpAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:49:15.747283Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.02084","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f133d5d23b81356c509c82752f987abdc244d0c53eeae08d5c311f20b2c361c","sha256:31690cc82b675b8a54c526909de922c9a9a883a9ae1e7e707f356fe965670880"],"state_sha256":"48f99c3cc72f519f3cc6fe2e002594c9f99f333b10a3ca37ce37f72ecb8a651b"}