{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:47CVQGI2RSFFRGPLUZPIK2CBYG","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":"887493d2028218765de8cd4f4d48cfe6d79af870aaf48af23305ef6ac3332213","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-23T18:57:43Z","title_canon_sha256":"581cc463ca22da6cb036434c689a4d2e7bb494c7d0e555a36b5647970c5855e5"},"schema_version":"1.0","source":{"id":"2412.17800","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.17800","created_at":"2026-07-05T09:53:27Z"},{"alias_kind":"arxiv_version","alias_value":"2412.17800v1","created_at":"2026-07-05T09:53:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17800","created_at":"2026-07-05T09:53:27Z"},{"alias_kind":"pith_short_12","alias_value":"47CVQGI2RSFF","created_at":"2026-07-05T09:53:27Z"},{"alias_kind":"pith_short_16","alias_value":"47CVQGI2RSFFRGPL","created_at":"2026-07-05T09:53:27Z"},{"alias_kind":"pith_short_8","alias_value":"47CVQGI2","created_at":"2026-07-05T09:53:27Z"}],"graph_snapshots":[{"event_id":"sha256:4a6a1926e9b5505a5fe562f8eef4ea6e53f6213b9650a79c4bd5407ee90d4f21","target":"graph","created_at":"2026-07-05T09:53:27Z","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/2412.17800/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Enabling models to recognize vast open-world categories has been a longstanding pursuit in object detection. By leveraging the generalization capabilities of vision-language models, current open-world detectors can recognize a broader range of vocabularies, despite being trained on limited categories. However, when the scale of the category vocabularies during training expands to a real-world level, previous classifiers aligned with coarse class names significantly reduce the recognition performance of these detectors. In this paper, we introduce Prova, a multi-modal prototype classifier for v","authors_text":"Lingchen Meng, Sihong Wu, Wenhao Yao, Yitong Chen, Yu-Gang Jiang, Zuxuan Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-23T18:57:43Z","title":"Comprehensive Multi-Modal Prototypes are Simple and Effective Classifiers for Vast-Vocabulary Object Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17800","kind":"arxiv","version":1},"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":"sha256:07180c12a3b55cc5e87ef84b879011d30654c5f544a3ae8a93d9bbee6b6e205a","target":"record","created_at":"2026-07-05T09:53:27Z","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":"887493d2028218765de8cd4f4d48cfe6d79af870aaf48af23305ef6ac3332213","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-23T18:57:43Z","title_canon_sha256":"581cc463ca22da6cb036434c689a4d2e7bb494c7d0e555a36b5647970c5855e5"},"schema_version":"1.0","source":{"id":"2412.17800","kind":"arxiv","version":1}},"canonical_sha256":"e7c558191a8c8a5899eba65e856841c1955a220a8600b6387c442173ae10a3d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7c558191a8c8a5899eba65e856841c1955a220a8600b6387c442173ae10a3d3","first_computed_at":"2026-07-05T09:53:27.545806Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:27.545806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1fj6ZfOHUh6rnXRqW9jj450kffkBr8dMhIqFyKQXuETtYSMIbKDKfnkmS+MjS7Pxj1T06+XF1kf1DA0If1uxAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:27.546416Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.17800","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07180c12a3b55cc5e87ef84b879011d30654c5f544a3ae8a93d9bbee6b6e205a","sha256:4a6a1926e9b5505a5fe562f8eef4ea6e53f6213b9650a79c4bd5407ee90d4f21"],"state_sha256":"c9def0c5e4f5ee4dfdca99dc9a31bfd43c425f33d12cece64a74bd76af1fa82e"}