{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5XBBVZVMUA4LS6GHKML4D47REV","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":"aa619c9884863b9e9d8a7c84c2f9d05107095a68932747930728be66a35740fc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-22T15:03:16Z","title_canon_sha256":"febe4fba7d5faf22c0c796436c919ce0178397728dbaac4761187547b72c23ae"},"schema_version":"1.0","source":{"id":"2308.11485","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.11485","created_at":"2026-07-05T06:43:35Z"},{"alias_kind":"arxiv_version","alias_value":"2308.11485v1","created_at":"2026-07-05T06:43:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.11485","created_at":"2026-07-05T06:43:35Z"},{"alias_kind":"pith_short_12","alias_value":"5XBBVZVMUA4L","created_at":"2026-07-05T06:43:35Z"},{"alias_kind":"pith_short_16","alias_value":"5XBBVZVMUA4LS6GH","created_at":"2026-07-05T06:43:35Z"},{"alias_kind":"pith_short_8","alias_value":"5XBBVZVM","created_at":"2026-07-05T06:43:35Z"}],"graph_snapshots":[{"event_id":"sha256:cc5119b87832f3c906e754102d0299bae54ceec5fa9991b922ca7c709a35fce2","target":"graph","created_at":"2026-07-05T06:43:35Z","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/2308.11485/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Given a query composed of a reference image and a relative caption, the Composed Image Retrieval goal is to retrieve images visually similar to the reference one that integrates the modifications expressed by the caption. Given that recent research has demonstrated the efficacy of large-scale vision and language pre-trained (VLP) models in various tasks, we rely on features from the OpenAI CLIP model to tackle the considered task. We initially perform a task-oriented fine-tuning of both CLIP encoders using the element-wise sum of visual and textual features. Then, in the second stage, we train","authors_text":"Alberto Baldrati, Alberto Del Bimbo, Marco Bertini, Tiberio Uricchio","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-22T15:03:16Z","title":"Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.11485","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:ae488c128a5d6c4055b26daa6281b1f14d571707fd535f72f5f1082a939df490","target":"record","created_at":"2026-07-05T06:43:35Z","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":"aa619c9884863b9e9d8a7c84c2f9d05107095a68932747930728be66a35740fc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-22T15:03:16Z","title_canon_sha256":"febe4fba7d5faf22c0c796436c919ce0178397728dbaac4761187547b72c23ae"},"schema_version":"1.0","source":{"id":"2308.11485","kind":"arxiv","version":1}},"canonical_sha256":"edc21ae6aca038b978c75317c1f3f1255b7360fda2757fee741e2aec652c4490","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edc21ae6aca038b978c75317c1f3f1255b7360fda2757fee741e2aec652c4490","first_computed_at":"2026-07-05T06:43:35.611289Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:43:35.611289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tk/8bloT37OzDDkeE5QD2NVVlV9upYIN9zPJEvv+45D5SrUodOhhYTdrzhh/KxrghJtZDtW16y1SkBuw5f3GAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:43:35.611766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.11485","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae488c128a5d6c4055b26daa6281b1f14d571707fd535f72f5f1082a939df490","sha256:cc5119b87832f3c906e754102d0299bae54ceec5fa9991b922ca7c709a35fce2"],"state_sha256":"4b4f66dc9c2c48e45a7ebcd15929aa8a6f3b6a9f738da1c56ad78735c67f12d9"}