{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SCDOSR5S7DQKAM7KIT2GUCIEVW","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":"d126d9187d9078cf21ff8886db3a5b6c7f5ebc5ae9d5287de13671ea9e3baf79","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-03T07:58:03Z","title_canon_sha256":"632a0cba51bcf8f52609f36548af0b5d112ebf06fa5374dbe5cbdb0dd92012df"},"schema_version":"1.0","source":{"id":"2403.01431","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01431","created_at":"2026-07-05T07:51:47Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01431v1","created_at":"2026-07-05T07:51:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01431","created_at":"2026-07-05T07:51:47Z"},{"alias_kind":"pith_short_12","alias_value":"SCDOSR5S7DQK","created_at":"2026-07-05T07:51:47Z"},{"alias_kind":"pith_short_16","alias_value":"SCDOSR5S7DQKAM7K","created_at":"2026-07-05T07:51:47Z"},{"alias_kind":"pith_short_8","alias_value":"SCDOSR5S","created_at":"2026-07-05T07:51:47Z"}],"graph_snapshots":[{"event_id":"sha256:5926c21d22d7e242568f5e1d4fdc2cfaed7d8dcd61b37efdcb430188fa32e208","target":"graph","created_at":"2026-07-05T07:51:47Z","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/2403.01431/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The task of composed image retrieval (CIR) aims to retrieve images based on the query image and the text describing the users' intent. Existing methods have made great progress with the advanced large vision-language (VL) model in CIR task, however, they generally suffer from two main issues: lack of labeled triplets for model training and difficulty of deployment on resource-restricted environments when deploying the large vision-language model. To tackle the above problems, we propose Image2Sentence based Asymmetric zero-shot composed image retrieval (ISA), which takes advantage of the VL mo","authors_text":"Houqiang Li, Min Wang, Shuping Hui, Wengang Zhou, Yongchao Du","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-03T07:58:03Z","title":"Image2Sentence based Asymmetrical Zero-shot Composed Image Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01431","kind":"arxiv","version":1},"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":"sha256:1ecb2a1c983ac2d6b623e1c821070c38338b407957b34f9b016ddfde86d7987f","target":"record","created_at":"2026-07-05T07:51:47Z","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":"d126d9187d9078cf21ff8886db3a5b6c7f5ebc5ae9d5287de13671ea9e3baf79","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-03T07:58:03Z","title_canon_sha256":"632a0cba51bcf8f52609f36548af0b5d112ebf06fa5374dbe5cbdb0dd92012df"},"schema_version":"1.0","source":{"id":"2403.01431","kind":"arxiv","version":1}},"canonical_sha256":"9086e947b2f8e0a033ea44f46a0904ad9b268422353bb6077a2b2484af9630ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9086e947b2f8e0a033ea44f46a0904ad9b268422353bb6077a2b2484af9630ce","first_computed_at":"2026-07-05T07:51:47.181087Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:47.181087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yj5+9iPArSPo+8q8pBzL62KS4JbwP+Y2t2TfcFcmgyd3q7rlKX4L/bOPDIeAmRFhO5QN0shOnk3cGCLhDlxVCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:47.181599Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.01431","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ecb2a1c983ac2d6b623e1c821070c38338b407957b34f9b016ddfde86d7987f","sha256:5926c21d22d7e242568f5e1d4fdc2cfaed7d8dcd61b37efdcb430188fa32e208"],"state_sha256":"2760448ef91aa729e9e787ee43a7324037a0455619ecf175e448a7560af98ae2"}