{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FV4MJEX24NRBIGCJJROXTZUHCG","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":"e5d3ce53f4ea63afcbbe0b5574feba38710c609692978e4d3383042fe64406d1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-12T17:56:01Z","title_canon_sha256":"83fdc52a574fb3fbc79accba51880af7f0da8465453946a3fef39210766a6462"},"schema_version":"1.0","source":{"id":"2306.07272","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07272","created_at":"2026-07-05T07:52:40Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07272v2","created_at":"2026-07-05T07:52:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07272","created_at":"2026-07-05T07:52:40Z"},{"alias_kind":"pith_short_12","alias_value":"FV4MJEX24NRB","created_at":"2026-07-05T07:52:40Z"},{"alias_kind":"pith_short_16","alias_value":"FV4MJEX24NRBIGCJ","created_at":"2026-07-05T07:52:40Z"},{"alias_kind":"pith_short_8","alias_value":"FV4MJEX2","created_at":"2026-07-05T07:52:40Z"}],"graph_snapshots":[{"event_id":"sha256:a5b1e793bdc2a06c4368dfb2d7023dacd62ab04e6e1837bc4a4ac347e71c0911","target":"graph","created_at":"2026-07-05T07:52:40Z","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/2306.07272/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we consider the problem of composed image retrieval (CIR), it aims to train a model that can fuse multi-modal information, e.g., text and images, to accurately retrieve images that match the query, extending the user's expression ability. We make the following contributions: (i) we initiate a scalable pipeline to automatically construct datasets for training CIR model, by simply exploiting a large-scale dataset of image-text pairs, e.g., a subset of LAION-5B; (ii) we introduce a transformer-based adaptive aggregation model, TransAgg, which employs a simple yet efficient fusion m","authors_text":"Jiangchao Yao, Weidi Xie, Yanfeng Wang, Ya Zhang, Yikun Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-12T17:56:01Z","title":"Zero-shot Composed Text-Image Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07272","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":"sha256:4e7ce87beda97cb3baf2ec74ba18a5141642d63a883fd49c8315056c01670fe8","target":"record","created_at":"2026-07-05T07:52:40Z","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":"e5d3ce53f4ea63afcbbe0b5574feba38710c609692978e4d3383042fe64406d1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-12T17:56:01Z","title_canon_sha256":"83fdc52a574fb3fbc79accba51880af7f0da8465453946a3fef39210766a6462"},"schema_version":"1.0","source":{"id":"2306.07272","kind":"arxiv","version":2}},"canonical_sha256":"2d78c492fae3621418494c5d79e68711b818c2162843598acaacb5a3abd179a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d78c492fae3621418494c5d79e68711b818c2162843598acaacb5a3abd179a0","first_computed_at":"2026-07-05T07:52:40.668891Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:52:40.668891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pqtRFpwPFK6K7BhxKjp9tRy3jkXAlspzhh8neNUNovv8WEutEZAHBnsUb1G1REDatRb9EFO+VKdezw58NxjfBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:52:40.669408Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.07272","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e7ce87beda97cb3baf2ec74ba18a5141642d63a883fd49c8315056c01670fe8","sha256:a5b1e793bdc2a06c4368dfb2d7023dacd62ab04e6e1837bc4a4ac347e71c0911"],"state_sha256":"0ecd4a9be7f53e8556ae35049ee9323e07d7a82e8b6eef873dea29e60094a818"}