{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SVEDVBQ72VIAP22NAOGYV7XO5R","short_pith_number":"pith:SVEDVBQ7","schema_version":"1.0","canonical_sha256":"95483a861fd55007eb4d038d8afeeeec64cdac02cdc46d6c9008dc7fd285a987","source":{"kind":"arxiv","id":"2606.07032","version":1},"attestation_state":"computed","paper":{"title":"Never Seen Before: Benchmarking Genuine Zero-Shot Composed Image Retrieval with Consistent Video-Sourced Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Shengsheng Qian, Zemin Du, Zhenyu Yang","submitted_at":"2026-06-05T08:23:25Z","abstract_excerpt":"Zero-Shot Composed Image Retrieval (ZS-CIR) aims to retrieve a target image based on a query composed of a reference image and a relative caption without training samples. Existing ZS-CIR datasets often suffer from complete irrelevance between reference and target images due to noisy image sources, and do not achieve a true zero-shot scenario as they use public image datasets that models like CLIP have been trained on. To tackle these challenges, we introduce ZeroSight, a novel benchmark for ZS-CIR. It includes a dataset with consistent reference-target pairs sourced from videos, a data constr"},"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":"2606.07032","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T08:23:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5146f76eabe9876bdd6b07b25e8d1476bc34965cfadce4ef951132714376fc52","abstract_canon_sha256":"67b412830d315059029c693cd3b20845ce293f852357c0144ca33f0049521d47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:42.327031Z","signature_b64":"8yLXiB5yvortTT4uCYgyRdB/am5tKn7NGFwAvmim/7ENPQ7vftFnYls2FFeN5f3XtOh86O0doRTQs0kftH0rBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95483a861fd55007eb4d038d8afeeeec64cdac02cdc46d6c9008dc7fd285a987","last_reissued_at":"2026-06-08T01:04:42.326209Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:42.326209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Never Seen Before: Benchmarking Genuine Zero-Shot Composed Image Retrieval with Consistent Video-Sourced Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Shengsheng Qian, Zemin Du, Zhenyu Yang","submitted_at":"2026-06-05T08:23:25Z","abstract_excerpt":"Zero-Shot Composed Image Retrieval (ZS-CIR) aims to retrieve a target image based on a query composed of a reference image and a relative caption without training samples. Existing ZS-CIR datasets often suffer from complete irrelevance between reference and target images due to noisy image sources, and do not achieve a true zero-shot scenario as they use public image datasets that models like CLIP have been trained on. To tackle these challenges, we introduce ZeroSight, a novel benchmark for ZS-CIR. It includes a dataset with consistent reference-target pairs sourced from videos, a data constr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07032","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/2606.07032/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":"2606.07032","created_at":"2026-06-08T01:04:42.326336+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07032v1","created_at":"2026-06-08T01:04:42.326336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07032","created_at":"2026-06-08T01:04:42.326336+00:00"},{"alias_kind":"pith_short_12","alias_value":"SVEDVBQ72VIA","created_at":"2026-06-08T01:04:42.326336+00:00"},{"alias_kind":"pith_short_16","alias_value":"SVEDVBQ72VIAP22N","created_at":"2026-06-08T01:04:42.326336+00:00"},{"alias_kind":"pith_short_8","alias_value":"SVEDVBQ7","created_at":"2026-06-08T01:04:42.326336+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/SVEDVBQ72VIAP22NAOGYV7XO5R","json":"https://pith.science/pith/SVEDVBQ72VIAP22NAOGYV7XO5R.json","graph_json":"https://pith.science/api/pith-number/SVEDVBQ72VIAP22NAOGYV7XO5R/graph.json","events_json":"https://pith.science/api/pith-number/SVEDVBQ72VIAP22NAOGYV7XO5R/events.json","paper":"https://pith.science/paper/SVEDVBQ7"},"agent_actions":{"view_html":"https://pith.science/pith/SVEDVBQ72VIAP22NAOGYV7XO5R","download_json":"https://pith.science/pith/SVEDVBQ72VIAP22NAOGYV7XO5R.json","view_paper":"https://pith.science/paper/SVEDVBQ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07032&json=true","fetch_graph":"https://pith.science/api/pith-number/SVEDVBQ72VIAP22NAOGYV7XO5R/graph.json","fetch_events":"https://pith.science/api/pith-number/SVEDVBQ72VIAP22NAOGYV7XO5R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SVEDVBQ72VIAP22NAOGYV7XO5R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SVEDVBQ72VIAP22NAOGYV7XO5R/action/storage_attestation","attest_author":"https://pith.science/pith/SVEDVBQ72VIAP22NAOGYV7XO5R/action/author_attestation","sign_citation":"https://pith.science/pith/SVEDVBQ72VIAP22NAOGYV7XO5R/action/citation_signature","submit_replication":"https://pith.science/pith/SVEDVBQ72VIAP22NAOGYV7XO5R/action/replication_record"}},"created_at":"2026-06-08T01:04:42.326336+00:00","updated_at":"2026-06-08T01:04:42.326336+00:00"}