{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KONG6QI247JH3KYPNFAI2O7KXB","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":"c28fdc8687ac7ac8c8caf9934ee06438e0262e11eb429e3e59e193b662888121","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-30T17:59:52Z","title_canon_sha256":"fd0a2400c54fdb8019868f4caaebd331d55e6024951ffcfcc6c2cf61cc897f4e"},"schema_version":"1.0","source":{"id":"2209.15639","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.15639","created_at":"2026-07-05T05:45:05Z"},{"alias_kind":"arxiv_version","alias_value":"2209.15639v2","created_at":"2026-07-05T05:45:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15639","created_at":"2026-07-05T05:45:05Z"},{"alias_kind":"pith_short_12","alias_value":"KONG6QI247JH","created_at":"2026-07-05T05:45:05Z"},{"alias_kind":"pith_short_16","alias_value":"KONG6QI247JH3KYP","created_at":"2026-07-05T05:45:05Z"},{"alias_kind":"pith_short_8","alias_value":"KONG6QI2","created_at":"2026-07-05T05:45:05Z"}],"graph_snapshots":[{"event_id":"sha256:42075a039420ca98e8e4b956d533dcc97e38991bfe0ad940e7fa14642e239791","target":"graph","created_at":"2026-07-05T05:45:05Z","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/2209.15639/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present F-VLM, a simple open-vocabulary object detection method built upon Frozen Vision and Language Models. F-VLM simplifies the current multi-stage training pipeline by eliminating the need for knowledge distillation or detection-tailored pretraining. Surprisingly, we observe that a frozen VLM: 1) retains the locality-sensitive features necessary for detection, and 2) is a strong region classifier. We finetune only the detector head and combine the detector and VLM outputs for each region at inference time. F-VLM shows compelling scaling behavior and achieves +6.5 mask AP improvement ove","authors_text":"AJ Piergiovanni, Anelia Angelova, Weicheng Kuo, Xiuye Gu, Yin Cui","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-30T17:59:52Z","title":"F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15639","kind":"arxiv","version":2},"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:f04953e8966a95804442eae2830c48c392666fae01d85770f3f1368910f304a7","target":"record","created_at":"2026-07-05T05:45:05Z","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":"c28fdc8687ac7ac8c8caf9934ee06438e0262e11eb429e3e59e193b662888121","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-30T17:59:52Z","title_canon_sha256":"fd0a2400c54fdb8019868f4caaebd331d55e6024951ffcfcc6c2cf61cc897f4e"},"schema_version":"1.0","source":{"id":"2209.15639","kind":"arxiv","version":2}},"canonical_sha256":"539a6f411ae7d27dab0f69408d3beab8513d63eb236fa1184c3b33609970404f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"539a6f411ae7d27dab0f69408d3beab8513d63eb236fa1184c3b33609970404f","first_computed_at":"2026-07-05T05:45:05.186818Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:45:05.186818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y0Ss6T+SoTdnFgmslRz5i8AlQ6jTcomN81Wggcyn9J9TVvQohjcrInXRauP7boaPtESbGwxK36kTfg8YwBD3CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:45:05.187261Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.15639","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f04953e8966a95804442eae2830c48c392666fae01d85770f3f1368910f304a7","sha256:42075a039420ca98e8e4b956d533dcc97e38991bfe0ad940e7fa14642e239791"],"state_sha256":"86d27277de58c3e497fd9a288eeee04708d514429fdff3fa58bd099fbd76248d"}