{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DHLMPU4MK6VHW2V4CJOYE6RGNG","short_pith_number":"pith:DHLMPU4M","canonical_record":{"source":{"id":"2308.15846","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-30T08:33:13Z","cross_cats_sorted":[],"title_canon_sha256":"a3169dfcf970cc00e9bbeb74a0e00734f6960a72f66abc25ff73d2bf07e5cd02","abstract_canon_sha256":"bb1a21e27e70f03aaa594dade8b2d5c5384b5e2696c37f4872f95a7af0f1fbf9"},"schema_version":"1.0"},"canonical_sha256":"19d6c7d38c57aa7b6abc125d827a2669bd683fcbc68b57b33c452d5be0e95cb0","source":{"kind":"arxiv","id":"2308.15846","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.15846","created_at":"2026-07-05T06:46:14Z"},{"alias_kind":"arxiv_version","alias_value":"2308.15846v1","created_at":"2026-07-05T06:46:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15846","created_at":"2026-07-05T06:46:14Z"},{"alias_kind":"pith_short_12","alias_value":"DHLMPU4MK6VH","created_at":"2026-07-05T06:46:14Z"},{"alias_kind":"pith_short_16","alias_value":"DHLMPU4MK6VHW2V4","created_at":"2026-07-05T06:46:14Z"},{"alias_kind":"pith_short_8","alias_value":"DHLMPU4M","created_at":"2026-07-05T06:46:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DHLMPU4MK6VHW2V4CJOYE6RGNG","target":"record","payload":{"canonical_record":{"source":{"id":"2308.15846","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-30T08:33:13Z","cross_cats_sorted":[],"title_canon_sha256":"a3169dfcf970cc00e9bbeb74a0e00734f6960a72f66abc25ff73d2bf07e5cd02","abstract_canon_sha256":"bb1a21e27e70f03aaa594dade8b2d5c5384b5e2696c37f4872f95a7af0f1fbf9"},"schema_version":"1.0"},"canonical_sha256":"19d6c7d38c57aa7b6abc125d827a2669bd683fcbc68b57b33c452d5be0e95cb0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:14.134485Z","signature_b64":"7TeekQozzBQ8rANoglnFccjW2A/qJo8Ucl8FB1/z06TW3gBoh5PKs3MUWYNOl2fciEr9i8wAU06+P35d6FlUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19d6c7d38c57aa7b6abc125d827a2669bd683fcbc68b57b33c452d5be0e95cb0","last_reissued_at":"2026-07-05T06:46:14.133986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:14.133986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.15846","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":"2026-07-05T06:46:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PusD+rFNhYzHMeZu/YZs1k25xtQb20KA2W5JYkbpPsu/htpqKLwcms02ib4mANEUu3oiaOjlwQh3MXwkuoENDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:47:46.010423Z"},"content_sha256":"20715d0a7c72e18def03c7289d035ff5c8a4d447819f83308b3433d7f1ca254c","schema_version":"1.0","event_id":"sha256:20715d0a7c72e18def03c7289d035ff5c8a4d447819f83308b3433d7f1ca254c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DHLMPU4MK6VHW2V4CJOYE6RGNG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring Multi-Modal Contextual Knowledge for Open-Vocabulary Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Mengdan Zhang, Xiaoshan Yang, Yifan Xu","submitted_at":"2023-08-30T08:33:13Z","abstract_excerpt":"In this paper, we for the first time explore helpful multi-modal contextual knowledge to understand novel categories for open-vocabulary object detection (OVD). The multi-modal contextual knowledge stands for the joint relationship across regions and words. However, it is challenging to incorporate such multi-modal contextual knowledge into OVD. The reason is that previous detection frameworks fail to jointly model multi-modal contextual knowledge, as object detectors only support vision inputs and no caption description is provided at test time. To this end, we propose a multi-modal contextua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15846","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/2308.15846/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":"2026-07-05T06:46:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F0wrBOtJ+uB5v0CMi4NAhnFFPoHV82CpX0kcr8O+E1snMf93aogsTgYFXgul6cPZxdBtjM5GZ91ktt7leXHaCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:47:46.011373Z"},"content_sha256":"8d3f83586f42a57778af43097e1aacdc164d5ddb3faa6bddb15c74011bb1c80d","schema_version":"1.0","event_id":"sha256:8d3f83586f42a57778af43097e1aacdc164d5ddb3faa6bddb15c74011bb1c80d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DHLMPU4MK6VHW2V4CJOYE6RGNG/bundle.json","state_url":"https://pith.science/pith/DHLMPU4MK6VHW2V4CJOYE6RGNG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DHLMPU4MK6VHW2V4CJOYE6RGNG/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":"2026-08-17T23:47:46Z","links":{"resolver":"https://pith.science/pith/DHLMPU4MK6VHW2V4CJOYE6RGNG","bundle":"https://pith.science/pith/DHLMPU4MK6VHW2V4CJOYE6RGNG/bundle.json","state":"https://pith.science/pith/DHLMPU4MK6VHW2V4CJOYE6RGNG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DHLMPU4MK6VHW2V4CJOYE6RGNG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DHLMPU4MK6VHW2V4CJOYE6RGNG","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":"bb1a21e27e70f03aaa594dade8b2d5c5384b5e2696c37f4872f95a7af0f1fbf9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-30T08:33:13Z","title_canon_sha256":"a3169dfcf970cc00e9bbeb74a0e00734f6960a72f66abc25ff73d2bf07e5cd02"},"schema_version":"1.0","source":{"id":"2308.15846","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.15846","created_at":"2026-07-05T06:46:14Z"},{"alias_kind":"arxiv_version","alias_value":"2308.15846v1","created_at":"2026-07-05T06:46:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15846","created_at":"2026-07-05T06:46:14Z"},{"alias_kind":"pith_short_12","alias_value":"DHLMPU4MK6VH","created_at":"2026-07-05T06:46:14Z"},{"alias_kind":"pith_short_16","alias_value":"DHLMPU4MK6VHW2V4","created_at":"2026-07-05T06:46:14Z"},{"alias_kind":"pith_short_8","alias_value":"DHLMPU4M","created_at":"2026-07-05T06:46:14Z"}],"graph_snapshots":[{"event_id":"sha256:8d3f83586f42a57778af43097e1aacdc164d5ddb3faa6bddb15c74011bb1c80d","target":"graph","created_at":"2026-07-05T06:46:14Z","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/2308.15846/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we for the first time explore helpful multi-modal contextual knowledge to understand novel categories for open-vocabulary object detection (OVD). The multi-modal contextual knowledge stands for the joint relationship across regions and words. However, it is challenging to incorporate such multi-modal contextual knowledge into OVD. The reason is that previous detection frameworks fail to jointly model multi-modal contextual knowledge, as object detectors only support vision inputs and no caption description is provided at test time. To this end, we propose a multi-modal contextua","authors_text":"Changsheng Xu, Mengdan Zhang, Xiaoshan Yang, Yifan Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-30T08:33:13Z","title":"Exploring Multi-Modal Contextual Knowledge for Open-Vocabulary Object Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15846","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":"sha256:20715d0a7c72e18def03c7289d035ff5c8a4d447819f83308b3433d7f1ca254c","target":"record","created_at":"2026-07-05T06:46:14Z","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":"bb1a21e27e70f03aaa594dade8b2d5c5384b5e2696c37f4872f95a7af0f1fbf9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-30T08:33:13Z","title_canon_sha256":"a3169dfcf970cc00e9bbeb74a0e00734f6960a72f66abc25ff73d2bf07e5cd02"},"schema_version":"1.0","source":{"id":"2308.15846","kind":"arxiv","version":1}},"canonical_sha256":"19d6c7d38c57aa7b6abc125d827a2669bd683fcbc68b57b33c452d5be0e95cb0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19d6c7d38c57aa7b6abc125d827a2669bd683fcbc68b57b33c452d5be0e95cb0","first_computed_at":"2026-07-05T06:46:14.133986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:46:14.133986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7TeekQozzBQ8rANoglnFccjW2A/qJo8Ucl8FB1/z06TW3gBoh5PKs3MUWYNOl2fciEr9i8wAU06+P35d6FlUCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:46:14.134485Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.15846","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20715d0a7c72e18def03c7289d035ff5c8a4d447819f83308b3433d7f1ca254c","sha256:8d3f83586f42a57778af43097e1aacdc164d5ddb3faa6bddb15c74011bb1c80d"],"state_sha256":"771779c02cddb990ad95017afa5027b033c1f9408ab699894380ff308a534105"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V3Hfq7E+uKXH9Ew+eAoRWm/iuW04tdWAj2KKHNor0JcncybxY5pKmffpqEFS0yHVRlo+bUlZ+cQP0EFCk5ZzDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T23:47:46.124828Z","bundle_sha256":"18af6634db5dd51da51c369f05d792c37a480678b001c81cc7b03e9325bd30d4"}}