{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GPMIGZXN4MEUNML3H5SH3DD5FK","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":"f0bb1233b23a965f31cbafbb08ee33d871d95748d68e76b7ddc6de1a56a250ed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T07:42:00Z","title_canon_sha256":"427e67f736dfc96a2b7be333fe570de029148d1c2f509ba2018e7252f45845c3"},"schema_version":"1.0","source":{"id":"2312.14494","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.14494","created_at":"2026-07-05T09:19:53Z"},{"alias_kind":"arxiv_version","alias_value":"2312.14494v4","created_at":"2026-07-05T09:19:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14494","created_at":"2026-07-05T09:19:53Z"},{"alias_kind":"pith_short_12","alias_value":"GPMIGZXN4MEU","created_at":"2026-07-05T09:19:53Z"},{"alias_kind":"pith_short_16","alias_value":"GPMIGZXN4MEUNML3","created_at":"2026-07-05T09:19:53Z"},{"alias_kind":"pith_short_8","alias_value":"GPMIGZXN","created_at":"2026-07-05T09:19:53Z"}],"graph_snapshots":[{"event_id":"sha256:4758e67a513c425f55e366b398abf785606058dde4a15fc4a20e2b35d798ed89","target":"graph","created_at":"2026-07-05T09:19:53Z","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/2312.14494/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The era of vision-language models (VLMs) trained on web-scale datasets challenges conventional formulations of \"open-world\" perception. In this work, we revisit the task of few-shot object detection (FSOD) in the context of recent foundational VLMs. First, we point out that zero-shot predictions from VLMs such as GroundingDINO significantly outperform state-of-the-art few-shot detectors (48 vs. 33 AP) on COCO. Despite their strong zero-shot performance, such foundation models may still be sub-optimal. For example, trucks on the web may be defined differently from trucks for a target applicatio","authors_text":"Anish Madan, Deva Ramanan, Neehar Peri, Shu Kong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T07:42:00Z","title":"Revisiting Few-Shot Object Detection with Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14494","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:d5b2af6a7055d32021550c7156c4febaf67e42bf2080599a4599186f61336e2b","target":"record","created_at":"2026-07-05T09:19:53Z","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":"f0bb1233b23a965f31cbafbb08ee33d871d95748d68e76b7ddc6de1a56a250ed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T07:42:00Z","title_canon_sha256":"427e67f736dfc96a2b7be333fe570de029148d1c2f509ba2018e7252f45845c3"},"schema_version":"1.0","source":{"id":"2312.14494","kind":"arxiv","version":4}},"canonical_sha256":"33d88366ede30946b17b3f647d8c7d2a99a36076bede433707ef6d2bc0e85821","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33d88366ede30946b17b3f647d8c7d2a99a36076bede433707ef6d2bc0e85821","first_computed_at":"2026-07-05T09:19:53.443122Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:53.443122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dfkXeAPz39YvDeWCsdH1gI50TMc80ymcrvWMwZUDxOEEf+OtU+OoE1IJdUkACfdAeg3uJI3gKy+4AVVPUyYXBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:53.443525Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.14494","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5b2af6a7055d32021550c7156c4febaf67e42bf2080599a4599186f61336e2b","sha256:4758e67a513c425f55e366b398abf785606058dde4a15fc4a20e2b35d798ed89"],"state_sha256":"e2938e20c9636072d42be77d863aa497a59c3b3f7fd20afd9f2be921660fb2a7"}