{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2LBBF4VZVIC25NWABG4RAT7EAM","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":"bff5a5c201a673c23373e11307982371f8c3008a949dfb43f9dc53d07c02db6d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T14:31:02Z","title_canon_sha256":"fc3eed064fc942f3d7f5a69dde26e6810b50b59815605d8bab8f1d59a1089eaf"},"schema_version":"1.0","source":{"id":"2310.16667","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16667","created_at":"2026-07-05T07:05:01Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16667v1","created_at":"2026-07-05T07:05:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16667","created_at":"2026-07-05T07:05:01Z"},{"alias_kind":"pith_short_12","alias_value":"2LBBF4VZVIC2","created_at":"2026-07-05T07:05:01Z"},{"alias_kind":"pith_short_16","alias_value":"2LBBF4VZVIC25NWA","created_at":"2026-07-05T07:05:01Z"},{"alias_kind":"pith_short_8","alias_value":"2LBBF4VZ","created_at":"2026-07-05T07:05:01Z"}],"graph_snapshots":[{"event_id":"sha256:08cdb95f5cc0a4071da572b609d782ae6e7a16d289eed75ae5c7505ad7618917","target":"graph","created_at":"2026-07-05T07:05:01Z","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/2310.16667/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deriving reliable region-word alignment from image-text pairs is critical to learn object-level vision-language representations for open-vocabulary object detection. Existing methods typically rely on pre-trained or self-trained vision-language models for alignment, which are prone to limitations in localization accuracy or generalization capabilities. In this paper, we propose CoDet, a novel approach that overcomes the reliance on pre-aligned vision-language space by reformulating region-word alignment as a co-occurring object discovery problem. Intuitively, by grouping images that mention a ","authors_text":"Chuofan Ma, Xiaojuan Qi, Xin Wen, Yi Jiang, Zehuan Yuan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T14:31:02Z","title":"CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16667","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":"sha256:67aa674e6c90973f80fa72c26a30f293ae1ac654609e3e010ccd1ef3330e9c39","target":"record","created_at":"2026-07-05T07:05:01Z","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":"bff5a5c201a673c23373e11307982371f8c3008a949dfb43f9dc53d07c02db6d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T14:31:02Z","title_canon_sha256":"fc3eed064fc942f3d7f5a69dde26e6810b50b59815605d8bab8f1d59a1089eaf"},"schema_version":"1.0","source":{"id":"2310.16667","kind":"arxiv","version":1}},"canonical_sha256":"d2c212f2b9aa05aeb6c009b9104fe40315dc54fe8bf55dbea56a68cb7af8a53c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2c212f2b9aa05aeb6c009b9104fe40315dc54fe8bf55dbea56a68cb7af8a53c","first_computed_at":"2026-07-05T07:05:01.037012Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:01.037012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E2Ie4pXSSgEdZRJvH3DdORBirUnMQYzebgwBJmcFhs8ZsnM3OWd1MmxXcHuQWcmpcD//l+OgnW5f1lahZZQVAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:01.037501Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.16667","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67aa674e6c90973f80fa72c26a30f293ae1ac654609e3e010ccd1ef3330e9c39","sha256:08cdb95f5cc0a4071da572b609d782ae6e7a16d289eed75ae5c7505ad7618917"],"state_sha256":"f41e64534c18210551635a7eca0644016bdc0887ba171225333399d0822b5cf6"}