{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FLVDWNLH7UPGKDIIQV4YEEF6A4","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":"33f030be2fb9e9b43c2fff06c4c7917b72fad869aa055b2681e0729460912f99","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-25T09:41:57Z","title_canon_sha256":"674d6f54bbc312e98270c0685379726434ed1dba43c39fe6d6261b82236d7445"},"schema_version":"1.0","source":{"id":"2211.13977","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.13977","created_at":"2026-07-05T05:29:40Z"},{"alias_kind":"arxiv_version","alias_value":"2211.13977v4","created_at":"2026-07-05T05:29:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.13977","created_at":"2026-07-05T05:29:40Z"},{"alias_kind":"pith_short_12","alias_value":"FLVDWNLH7UPG","created_at":"2026-07-05T05:29:40Z"},{"alias_kind":"pith_short_16","alias_value":"FLVDWNLH7UPGKDII","created_at":"2026-07-05T05:29:40Z"},{"alias_kind":"pith_short_8","alias_value":"FLVDWNLH","created_at":"2026-07-05T05:29:40Z"}],"graph_snapshots":[{"event_id":"sha256:ab70df5a8c4a3082cc87db8ade1299d489ed86b51680f819c298d69f41532fd0","target":"graph","created_at":"2026-07-05T05:29:40Z","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/2211.13977/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained vision-language models like CLIP have recently shown superior performances on various downstream tasks, including image classification and segmentation. However, in fine-grained image re-identification (ReID), the labels are indexes, lacking concrete text descriptions. Therefore, it remains to be determined how such models could be applied to these tasks. This paper first finds out that simply fine-tuning the visual model initialized by the image encoder in CLIP, has already obtained competitive performances in various ReID tasks. Then we propose a two-stage strategy to facilitate ","authors_text":"Li Sun, Qingli Li, Siyuan Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-25T09:41:57Z","title":"CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.13977","kind":"arxiv","version":4},"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":"sha256:446750b2792851d4b17eaf2e7da3a9ce046d48c6598f28f6108a1fded2e92163","target":"record","created_at":"2026-07-05T05:29:40Z","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":"33f030be2fb9e9b43c2fff06c4c7917b72fad869aa055b2681e0729460912f99","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-25T09:41:57Z","title_canon_sha256":"674d6f54bbc312e98270c0685379726434ed1dba43c39fe6d6261b82236d7445"},"schema_version":"1.0","source":{"id":"2211.13977","kind":"arxiv","version":4}},"canonical_sha256":"2aea3b3567fd1e650d0885798210be07185777ea829d3ae67edd5813e7cf2d57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2aea3b3567fd1e650d0885798210be07185777ea829d3ae67edd5813e7cf2d57","first_computed_at":"2026-07-05T05:29:40.360347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:29:40.360347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1kX0K8WSK843LwYhl1VoHOVmWagxOrKVo3SvyBCIBLqwYtELHyYMcUZfn63Fj5MGuuho3C/zV0ahHuezTkojCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:29:40.360736Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.13977","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:446750b2792851d4b17eaf2e7da3a9ce046d48c6598f28f6108a1fded2e92163","sha256:ab70df5a8c4a3082cc87db8ade1299d489ed86b51680f819c298d69f41532fd0"],"state_sha256":"a7241f76a95c3427cc0f51d2cc18e7fd0342b3d9b0337d40a00ddb314b36c2af"}