{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7OHTRCFRVU247MX4H3MMWZHTUU","short_pith_number":"pith:7OHTRCFR","schema_version":"1.0","canonical_sha256":"fb8f3888b1ad35cfb2fc3ed8cb64f3a505ca1a220a660228b94f4ff53b0e81e2","source":{"kind":"arxiv","id":"2412.18806","version":1},"attestation_state":"computed","paper":{"title":"FOR: Finetuning for Object Level Open Vocabulary Image Retrieval","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dan Levi, Guy Heller, Hila Levi","submitted_at":"2024-12-25T07:08:51Z","abstract_excerpt":"As working with large datasets becomes standard, the task of accurately retrieving images containing objects of interest by an open set textual query gains practical importance. The current leading approach utilizes a pre-trained CLIP model without any adaptation to the target domain, balancing accuracy and efficiency through additional post-processing. In this work, we propose FOR: Finetuning for Object-centric Open-vocabulary Image Retrieval, which allows finetuning on a target dataset using closed-set labels while keeping the visual-language association crucial for open vocabulary retrieval"},"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":"2412.18806","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-25T07:08:51Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"5d64743411e6d3792ad85876a6c2ea064c97418fedad8c3e67b38948855d5804","abstract_canon_sha256":"075ef72983e6e3d5d16f003490b237bea67e00b19384bdef99dc9da9ba3865f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:11.170427Z","signature_b64":"uoY8V/aYlk8KSoiKsyd8+DTI+rwOuI9nvMYkj4vE5fALa3Mo1FVDmMc+CcPfVOYcoNaimmPCaMjKG3fns2YCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb8f3888b1ad35cfb2fc3ed8cb64f3a505ca1a220a660228b94f4ff53b0e81e2","last_reissued_at":"2026-07-05T09:54:11.169961Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:11.169961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FOR: Finetuning for Object Level Open Vocabulary Image Retrieval","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dan Levi, Guy Heller, Hila Levi","submitted_at":"2024-12-25T07:08:51Z","abstract_excerpt":"As working with large datasets becomes standard, the task of accurately retrieving images containing objects of interest by an open set textual query gains practical importance. The current leading approach utilizes a pre-trained CLIP model without any adaptation to the target domain, balancing accuracy and efficiency through additional post-processing. In this work, we propose FOR: Finetuning for Object-centric Open-vocabulary Image Retrieval, which allows finetuning on a target dataset using closed-set labels while keeping the visual-language association crucial for open vocabulary retrieval"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18806","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/2412.18806/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":"2412.18806","created_at":"2026-07-05T09:54:11.170017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18806v1","created_at":"2026-07-05T09:54:11.170017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18806","created_at":"2026-07-05T09:54:11.170017+00:00"},{"alias_kind":"pith_short_12","alias_value":"7OHTRCFRVU24","created_at":"2026-07-05T09:54:11.170017+00:00"},{"alias_kind":"pith_short_16","alias_value":"7OHTRCFRVU247MX4","created_at":"2026-07-05T09:54:11.170017+00:00"},{"alias_kind":"pith_short_8","alias_value":"7OHTRCFR","created_at":"2026-07-05T09:54:11.170017+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/7OHTRCFRVU247MX4H3MMWZHTUU","json":"https://pith.science/pith/7OHTRCFRVU247MX4H3MMWZHTUU.json","graph_json":"https://pith.science/api/pith-number/7OHTRCFRVU247MX4H3MMWZHTUU/graph.json","events_json":"https://pith.science/api/pith-number/7OHTRCFRVU247MX4H3MMWZHTUU/events.json","paper":"https://pith.science/paper/7OHTRCFR"},"agent_actions":{"view_html":"https://pith.science/pith/7OHTRCFRVU247MX4H3MMWZHTUU","download_json":"https://pith.science/pith/7OHTRCFRVU247MX4H3MMWZHTUU.json","view_paper":"https://pith.science/paper/7OHTRCFR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18806&json=true","fetch_graph":"https://pith.science/api/pith-number/7OHTRCFRVU247MX4H3MMWZHTUU/graph.json","fetch_events":"https://pith.science/api/pith-number/7OHTRCFRVU247MX4H3MMWZHTUU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7OHTRCFRVU247MX4H3MMWZHTUU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7OHTRCFRVU247MX4H3MMWZHTUU/action/storage_attestation","attest_author":"https://pith.science/pith/7OHTRCFRVU247MX4H3MMWZHTUU/action/author_attestation","sign_citation":"https://pith.science/pith/7OHTRCFRVU247MX4H3MMWZHTUU/action/citation_signature","submit_replication":"https://pith.science/pith/7OHTRCFRVU247MX4H3MMWZHTUU/action/replication_record"}},"created_at":"2026-07-05T09:54:11.170017+00:00","updated_at":"2026-07-05T09:54:11.170017+00:00"}