{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4BL32UJSF3DWJ7CYMLTIDOLTXX","short_pith_number":"pith:4BL32UJS","canonical_record":{"source":{"id":"2305.18279","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-29T17:50:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"155dcd4d05fea465ff063e17a67e5f25ccc29142587e537d57aa1c97fffb612c","abstract_canon_sha256":"21f31878236e942677f6df97e23203e6a8bc801639bea9da9bbfcf362b77da40"},"schema_version":"1.0"},"canonical_sha256":"e057bd51322ec764fc5862e681b973bdfb12cedbafdc49a8e79a1fceaf9ba504","source":{"kind":"arxiv","id":"2305.18279","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18279","created_at":"2026-07-05T08:54:02Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18279v2","created_at":"2026-07-05T08:54:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18279","created_at":"2026-07-05T08:54:02Z"},{"alias_kind":"pith_short_12","alias_value":"4BL32UJSF3DW","created_at":"2026-07-05T08:54:02Z"},{"alias_kind":"pith_short_16","alias_value":"4BL32UJSF3DWJ7CY","created_at":"2026-07-05T08:54:02Z"},{"alias_kind":"pith_short_8","alias_value":"4BL32UJS","created_at":"2026-07-05T08:54:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4BL32UJSF3DWJ7CYMLTIDOLTXX","target":"record","payload":{"canonical_record":{"source":{"id":"2305.18279","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-29T17:50:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"155dcd4d05fea465ff063e17a67e5f25ccc29142587e537d57aa1c97fffb612c","abstract_canon_sha256":"21f31878236e942677f6df97e23203e6a8bc801639bea9da9bbfcf362b77da40"},"schema_version":"1.0"},"canonical_sha256":"e057bd51322ec764fc5862e681b973bdfb12cedbafdc49a8e79a1fceaf9ba504","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:02.269389Z","signature_b64":"faTFFb2Wb0ix+I2F4MtZRofidosR88kNrL1OIKN08/O0kAyw0DGqy2YwoHzSarL4bHAm6EbMPeyPeqD/j+70Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e057bd51322ec764fc5862e681b973bdfb12cedbafdc49a8e79a1fceaf9ba504","last_reissued_at":"2026-07-05T08:54:02.268931Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:02.268931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.18279","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:54:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KsP6o4o5nEXNjhLbvxfbs1omzRx1TrzdindBzacz31v73Ch5hy0LNtcYei21E/3dqeTnIGUpPiL0QSo3gwZ8Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:53:13.632660Z"},"content_sha256":"9ee5734e657429b0c0832fbbd0924f1f2371f58b2435387337b94211c0663056","schema_version":"1.0","event_id":"sha256:9ee5734e657429b0c0832fbbd0924f1f2371f58b2435387337b94211c0663056"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4BL32UJSF3DWJ7CYMLTIDOLTXX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contextual Object Detection with Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Jun Han, Kaiyang Zhou, Wei Li, Yuhang Zang","submitted_at":"2023-05-29T17:50:33Z","abstract_excerpt":"Recent Multimodal Large Language Models (MLLMs) are remarkable in vision-language tasks, such as image captioning and question answering, but lack the essential perception ability, i.e., object detection. In this work, we address this limitation by introducing a novel research problem of contextual object detection -- understanding visible objects within different human-AI interactive contexts. Three representative scenarios are investigated, including the language cloze test, visual captioning, and question answering. Moreover, we present ContextDET, a unified multimodal model that is capable"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18279","kind":"arxiv","version":2},"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/2305.18279/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":"2026-07-05T08:54:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rc+uBnMj+Y5ge5mqEvteB3Sdz2r79y/OLYPQKf79hOb3RRNm38gLF/CMWuXEpuSNVs064+IorPLYg1UynxJGDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:53:13.633612Z"},"content_sha256":"d3bdf21ad913477d4e1e9b90e904dec35b717ab9715ec9b536c4f1337d544154","schema_version":"1.0","event_id":"sha256:d3bdf21ad913477d4e1e9b90e904dec35b717ab9715ec9b536c4f1337d544154"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4BL32UJSF3DWJ7CYMLTIDOLTXX/bundle.json","state_url":"https://pith.science/pith/4BL32UJSF3DWJ7CYMLTIDOLTXX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4BL32UJSF3DWJ7CYMLTIDOLTXX/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":"2026-08-07T10:53:13Z","links":{"resolver":"https://pith.science/pith/4BL32UJSF3DWJ7CYMLTIDOLTXX","bundle":"https://pith.science/pith/4BL32UJSF3DWJ7CYMLTIDOLTXX/bundle.json","state":"https://pith.science/pith/4BL32UJSF3DWJ7CYMLTIDOLTXX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4BL32UJSF3DWJ7CYMLTIDOLTXX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4BL32UJSF3DWJ7CYMLTIDOLTXX","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":"21f31878236e942677f6df97e23203e6a8bc801639bea9da9bbfcf362b77da40","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-29T17:50:33Z","title_canon_sha256":"155dcd4d05fea465ff063e17a67e5f25ccc29142587e537d57aa1c97fffb612c"},"schema_version":"1.0","source":{"id":"2305.18279","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18279","created_at":"2026-07-05T08:54:02Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18279v2","created_at":"2026-07-05T08:54:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18279","created_at":"2026-07-05T08:54:02Z"},{"alias_kind":"pith_short_12","alias_value":"4BL32UJSF3DW","created_at":"2026-07-05T08:54:02Z"},{"alias_kind":"pith_short_16","alias_value":"4BL32UJSF3DWJ7CY","created_at":"2026-07-05T08:54:02Z"},{"alias_kind":"pith_short_8","alias_value":"4BL32UJS","created_at":"2026-07-05T08:54:02Z"}],"graph_snapshots":[{"event_id":"sha256:d3bdf21ad913477d4e1e9b90e904dec35b717ab9715ec9b536c4f1337d544154","target":"graph","created_at":"2026-07-05T08:54:02Z","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/2305.18279/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent Multimodal Large Language Models (MLLMs) are remarkable in vision-language tasks, such as image captioning and question answering, but lack the essential perception ability, i.e., object detection. In this work, we address this limitation by introducing a novel research problem of contextual object detection -- understanding visible objects within different human-AI interactive contexts. Three representative scenarios are investigated, including the language cloze test, visual captioning, and question answering. Moreover, we present ContextDET, a unified multimodal model that is capable","authors_text":"Chen Change Loy, Jun Han, Kaiyang Zhou, Wei Li, Yuhang Zang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-29T17:50:33Z","title":"Contextual Object Detection with Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18279","kind":"arxiv","version":2},"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":"sha256:9ee5734e657429b0c0832fbbd0924f1f2371f58b2435387337b94211c0663056","target":"record","created_at":"2026-07-05T08:54:02Z","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":"21f31878236e942677f6df97e23203e6a8bc801639bea9da9bbfcf362b77da40","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-29T17:50:33Z","title_canon_sha256":"155dcd4d05fea465ff063e17a67e5f25ccc29142587e537d57aa1c97fffb612c"},"schema_version":"1.0","source":{"id":"2305.18279","kind":"arxiv","version":2}},"canonical_sha256":"e057bd51322ec764fc5862e681b973bdfb12cedbafdc49a8e79a1fceaf9ba504","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e057bd51322ec764fc5862e681b973bdfb12cedbafdc49a8e79a1fceaf9ba504","first_computed_at":"2026-07-05T08:54:02.268931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:54:02.268931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"faTFFb2Wb0ix+I2F4MtZRofidosR88kNrL1OIKN08/O0kAyw0DGqy2YwoHzSarL4bHAm6EbMPeyPeqD/j+70Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:54:02.269389Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.18279","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ee5734e657429b0c0832fbbd0924f1f2371f58b2435387337b94211c0663056","sha256:d3bdf21ad913477d4e1e9b90e904dec35b717ab9715ec9b536c4f1337d544154"],"state_sha256":"f8a55657e2b00708e0de8fb141c6a383fe89a91d278e2500d97641aa9c686033"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6iwk/cst/QdYk/RVB5awYH7S9vuFarleXTm7b9lNPDQ7FEdeqqUcyAvqT03Fsl304hHNP7Tu7Z8Blg0Kcld7Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T10:53:13.640619Z","bundle_sha256":"c0c7eb6643aa88734b189d710373fc2ec42f2faff82e8371f1c94c869c418622"}}