{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:47CVQGI2RSFFRGPLUZPIK2CBYG","short_pith_number":"pith:47CVQGI2","schema_version":"1.0","canonical_sha256":"e7c558191a8c8a5899eba65e856841c1955a220a8600b6387c442173ae10a3d3","source":{"kind":"arxiv","id":"2412.17800","version":1},"attestation_state":"computed","paper":{"title":"Comprehensive Multi-Modal Prototypes are Simple and Effective Classifiers for Vast-Vocabulary Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lingchen Meng, Sihong Wu, Wenhao Yao, Yitong Chen, Yu-Gang Jiang, Zuxuan Wu","submitted_at":"2024-12-23T18:57:43Z","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"},"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":"2412.17800","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-23T18:57:43Z","cross_cats_sorted":[],"title_canon_sha256":"581cc463ca22da6cb036434c689a4d2e7bb494c7d0e555a36b5647970c5855e5","abstract_canon_sha256":"887493d2028218765de8cd4f4d48cfe6d79af870aaf48af23305ef6ac3332213"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:27.546416Z","signature_b64":"1fj6ZfOHUh6rnXRqW9jj450kffkBr8dMhIqFyKQXuETtYSMIbKDKfnkmS+MjS7Pxj1T06+XF1kf1DA0If1uxAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7c558191a8c8a5899eba65e856841c1955a220a8600b6387c442173ae10a3d3","last_reissued_at":"2026-07-05T09:53:27.545806Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:27.545806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comprehensive Multi-Modal Prototypes are Simple and Effective Classifiers for Vast-Vocabulary Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lingchen Meng, Sihong Wu, Wenhao Yao, Yitong Chen, Yu-Gang Jiang, Zuxuan Wu","submitted_at":"2024-12-23T18:57:43Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17800","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/2412.17800/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":"2412.17800","created_at":"2026-07-05T09:53:27.545877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17800v1","created_at":"2026-07-05T09:53:27.545877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17800","created_at":"2026-07-05T09:53:27.545877+00:00"},{"alias_kind":"pith_short_12","alias_value":"47CVQGI2RSFF","created_at":"2026-07-05T09:53:27.545877+00:00"},{"alias_kind":"pith_short_16","alias_value":"47CVQGI2RSFFRGPL","created_at":"2026-07-05T09:53:27.545877+00:00"},{"alias_kind":"pith_short_8","alias_value":"47CVQGI2","created_at":"2026-07-05T09:53:27.545877+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/47CVQGI2RSFFRGPLUZPIK2CBYG","json":"https://pith.science/pith/47CVQGI2RSFFRGPLUZPIK2CBYG.json","graph_json":"https://pith.science/api/pith-number/47CVQGI2RSFFRGPLUZPIK2CBYG/graph.json","events_json":"https://pith.science/api/pith-number/47CVQGI2RSFFRGPLUZPIK2CBYG/events.json","paper":"https://pith.science/paper/47CVQGI2"},"agent_actions":{"view_html":"https://pith.science/pith/47CVQGI2RSFFRGPLUZPIK2CBYG","download_json":"https://pith.science/pith/47CVQGI2RSFFRGPLUZPIK2CBYG.json","view_paper":"https://pith.science/paper/47CVQGI2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17800&json=true","fetch_graph":"https://pith.science/api/pith-number/47CVQGI2RSFFRGPLUZPIK2CBYG/graph.json","fetch_events":"https://pith.science/api/pith-number/47CVQGI2RSFFRGPLUZPIK2CBYG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/47CVQGI2RSFFRGPLUZPIK2CBYG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/47CVQGI2RSFFRGPLUZPIK2CBYG/action/storage_attestation","attest_author":"https://pith.science/pith/47CVQGI2RSFFRGPLUZPIK2CBYG/action/author_attestation","sign_citation":"https://pith.science/pith/47CVQGI2RSFFRGPLUZPIK2CBYG/action/citation_signature","submit_replication":"https://pith.science/pith/47CVQGI2RSFFRGPLUZPIK2CBYG/action/replication_record"}},"created_at":"2026-07-05T09:53:27.545877+00:00","updated_at":"2026-07-05T09:53:27.545877+00:00"}