{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:2LBBF4VZVIC25NWABG4RAT7EAM","short_pith_number":"pith:2LBBF4VZ","canonical_record":{"source":{"id":"2310.16667","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T14:31:02Z","cross_cats_sorted":[],"title_canon_sha256":"fc3eed064fc942f3d7f5a69dde26e6810b50b59815605d8bab8f1d59a1089eaf","abstract_canon_sha256":"bff5a5c201a673c23373e11307982371f8c3008a949dfb43f9dc53d07c02db6d"},"schema_version":"1.0"},"canonical_sha256":"d2c212f2b9aa05aeb6c009b9104fe40315dc54fe8bf55dbea56a68cb7af8a53c","source":{"kind":"arxiv","id":"2310.16667","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:2LBBF4VZVIC25NWABG4RAT7EAM","target":"record","payload":{"canonical_record":{"source":{"id":"2310.16667","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T14:31:02Z","cross_cats_sorted":[],"title_canon_sha256":"fc3eed064fc942f3d7f5a69dde26e6810b50b59815605d8bab8f1d59a1089eaf","abstract_canon_sha256":"bff5a5c201a673c23373e11307982371f8c3008a949dfb43f9dc53d07c02db6d"},"schema_version":"1.0"},"canonical_sha256":"d2c212f2b9aa05aeb6c009b9104fe40315dc54fe8bf55dbea56a68cb7af8a53c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:01.037501Z","signature_b64":"E2Ie4pXSSgEdZRJvH3DdORBirUnMQYzebgwBJmcFhs8ZsnM3OWd1MmxXcHuQWcmpcD//l+OgnW5f1lahZZQVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2c212f2b9aa05aeb6c009b9104fe40315dc54fe8bf55dbea56a68cb7af8a53c","last_reissued_at":"2026-07-05T07:05:01.037012Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:01.037012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.16667","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:05:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bY8fOIW2P3x9wZALlo9dgZYc3o+FxQB0YSNNL1MefDZZkN2knq2NAXotsIlGG/cuKitFjHnWBCoMOZRNcl5QAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:05:23.189773Z"},"content_sha256":"67aa674e6c90973f80fa72c26a30f293ae1ac654609e3e010ccd1ef3330e9c39","schema_version":"1.0","event_id":"sha256:67aa674e6c90973f80fa72c26a30f293ae1ac654609e3e010ccd1ef3330e9c39"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:2LBBF4VZVIC25NWABG4RAT7EAM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuofan Ma, Xiaojuan Qi, Xin Wen, Yi Jiang, Zehuan Yuan","submitted_at":"2023-10-25T14:31:02Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16667","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/2310.16667/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:05:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wsZFQE7UMCenxT8gGam6u+EAE59bB62eBt/DzyTXGbTn6rjW9hX+ZxVdyNuQxGXsj7MBCE1ba00bQaOHftibBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:05:23.190274Z"},"content_sha256":"08cdb95f5cc0a4071da572b609d782ae6e7a16d289eed75ae5c7505ad7618917","schema_version":"1.0","event_id":"sha256:08cdb95f5cc0a4071da572b609d782ae6e7a16d289eed75ae5c7505ad7618917"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2LBBF4VZVIC25NWABG4RAT7EAM/bundle.json","state_url":"https://pith.science/pith/2LBBF4VZVIC25NWABG4RAT7EAM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2LBBF4VZVIC25NWABG4RAT7EAM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T06:05:23Z","links":{"resolver":"https://pith.science/pith/2LBBF4VZVIC25NWABG4RAT7EAM","bundle":"https://pith.science/pith/2LBBF4VZVIC25NWABG4RAT7EAM/bundle.json","state":"https://pith.science/pith/2LBBF4VZVIC25NWABG4RAT7EAM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2LBBF4VZVIC25NWABG4RAT7EAM/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yhv+Pjc47j68LpHeBRMIM0dHfRYVc2vPEzVOpkF0afxVG9SFTVn0T9lBh/AZbKU4CTIxalMbScLQzMdy2jJAAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T06:05:23.195823Z","bundle_sha256":"c2ae6dace638e9fbb40169dd2f584bbc3dbc12d7a955255f375396d0ea8c7a2f"}}