{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:GWYD6GFQAQ2RJO5EFG5GKHLS2R","short_pith_number":"pith:GWYD6GFQ","canonical_record":{"source":{"id":"2205.04072","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-09T07:03:30Z","cross_cats_sorted":[],"title_canon_sha256":"b95d84d8c4e9d7d54c72fcc2f72212a735e48f492f07497f5a5ceacbdffb9a10","abstract_canon_sha256":"a1792e647fa9242e4fb88ccad9ab764c19ba1edfd1b692b1ffb00ccdc19112a6"},"schema_version":"1.0"},"canonical_sha256":"35b03f18b0043514bba429ba651d72d4779ac3f5907c45201103dc5ecab842cf","source":{"kind":"arxiv","id":"2205.04072","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.04072","created_at":"2026-07-05T04:21:20Z"},{"alias_kind":"arxiv_version","alias_value":"2205.04072v1","created_at":"2026-07-05T04:21:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.04072","created_at":"2026-07-05T04:21:20Z"},{"alias_kind":"pith_short_12","alias_value":"GWYD6GFQAQ2R","created_at":"2026-07-05T04:21:20Z"},{"alias_kind":"pith_short_16","alias_value":"GWYD6GFQAQ2RJO5E","created_at":"2026-07-05T04:21:20Z"},{"alias_kind":"pith_short_8","alias_value":"GWYD6GFQ","created_at":"2026-07-05T04:21:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:GWYD6GFQAQ2RJO5EFG5GKHLS2R","target":"record","payload":{"canonical_record":{"source":{"id":"2205.04072","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-09T07:03:30Z","cross_cats_sorted":[],"title_canon_sha256":"b95d84d8c4e9d7d54c72fcc2f72212a735e48f492f07497f5a5ceacbdffb9a10","abstract_canon_sha256":"a1792e647fa9242e4fb88ccad9ab764c19ba1edfd1b692b1ffb00ccdc19112a6"},"schema_version":"1.0"},"canonical_sha256":"35b03f18b0043514bba429ba651d72d4779ac3f5907c45201103dc5ecab842cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:21:20.953504Z","signature_b64":"glNFEGzdB9xdbAAkSOcF/BIaJpz2YI8xpFSxC0d7ERzXxs3GYqZ+4apgz2NyIPZokF+vQZmeXoasDpRBjRFUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35b03f18b0043514bba429ba651d72d4779ac3f5907c45201103dc5ecab842cf","last_reissued_at":"2026-07-05T04:21:20.953076Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:21:20.953076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.04072","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":"2026-07-05T04:21:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wmSryqOBZdRt7isu/28vN+KA0UJapX2RMy0tuvc2orm2Ag9ebrTjvNwASTUQCTdVI+f98dcxCDXnyhVnTo7fDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:44:23.731199Z"},"content_sha256":"991bd4f891b982c6eca765086b5984d14bd4d34416c547cc0cd205557ccb3f0b","schema_version":"1.0","event_id":"sha256:991bd4f891b982c6eca765086b5984d14bd4d34416c547cc0cd205557ccb3f0b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:GWYD6GFQAQ2RJO5EFG5GKHLS2R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Bounding Box: Multimodal Knowledge Learning for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenchen Zhang, Weixin Feng, Xingyuan Bu, Xubin Li","submitted_at":"2022-05-09T07:03:30Z","abstract_excerpt":"Multimodal supervision has achieved promising results in many visual language understanding tasks, where the language plays an essential role as a hint or context for recognizing and locating instances. However, due to the defects of the human-annotated language corpus, multimodal supervision remains unexplored in fully supervised object detection scenarios. In this paper, we take advantage of language prompt to introduce effective and unbiased linguistic supervision into object detection, and propose a new mechanism called multimodal knowledge learning (\\textbf{MKL}), which is required to lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.04072","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/2205.04072/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":"2026-07-05T04:21:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FOEAMAK4AhFll51IM32y/5VxYACK6Pv4nrtgWjUdlp7EpL16YAWT5qOFIWVEdzls4rOuHga/+zMgM5SKdTGtAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:44:23.731685Z"},"content_sha256":"a3e41281caf7d9af10c95a880d9771e2dd9c54bbbb3eff3a930d992592083890","schema_version":"1.0","event_id":"sha256:a3e41281caf7d9af10c95a880d9771e2dd9c54bbbb3eff3a930d992592083890"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GWYD6GFQAQ2RJO5EFG5GKHLS2R/bundle.json","state_url":"https://pith.science/pith/GWYD6GFQAQ2RJO5EFG5GKHLS2R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GWYD6GFQAQ2RJO5EFG5GKHLS2R/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":"2026-08-19T04:44:23Z","links":{"resolver":"https://pith.science/pith/GWYD6GFQAQ2RJO5EFG5GKHLS2R","bundle":"https://pith.science/pith/GWYD6GFQAQ2RJO5EFG5GKHLS2R/bundle.json","state":"https://pith.science/pith/GWYD6GFQAQ2RJO5EFG5GKHLS2R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GWYD6GFQAQ2RJO5EFG5GKHLS2R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GWYD6GFQAQ2RJO5EFG5GKHLS2R","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":"a1792e647fa9242e4fb88ccad9ab764c19ba1edfd1b692b1ffb00ccdc19112a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-09T07:03:30Z","title_canon_sha256":"b95d84d8c4e9d7d54c72fcc2f72212a735e48f492f07497f5a5ceacbdffb9a10"},"schema_version":"1.0","source":{"id":"2205.04072","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.04072","created_at":"2026-07-05T04:21:20Z"},{"alias_kind":"arxiv_version","alias_value":"2205.04072v1","created_at":"2026-07-05T04:21:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.04072","created_at":"2026-07-05T04:21:20Z"},{"alias_kind":"pith_short_12","alias_value":"GWYD6GFQAQ2R","created_at":"2026-07-05T04:21:20Z"},{"alias_kind":"pith_short_16","alias_value":"GWYD6GFQAQ2RJO5E","created_at":"2026-07-05T04:21:20Z"},{"alias_kind":"pith_short_8","alias_value":"GWYD6GFQ","created_at":"2026-07-05T04:21:20Z"}],"graph_snapshots":[{"event_id":"sha256:a3e41281caf7d9af10c95a880d9771e2dd9c54bbbb3eff3a930d992592083890","target":"graph","created_at":"2026-07-05T04:21:20Z","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/2205.04072/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal supervision has achieved promising results in many visual language understanding tasks, where the language plays an essential role as a hint or context for recognizing and locating instances. However, due to the defects of the human-annotated language corpus, multimodal supervision remains unexplored in fully supervised object detection scenarios. In this paper, we take advantage of language prompt to introduce effective and unbiased linguistic supervision into object detection, and propose a new mechanism called multimodal knowledge learning (\\textbf{MKL}), which is required to lea","authors_text":"Chenchen Zhang, Weixin Feng, Xingyuan Bu, Xubin Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-09T07:03:30Z","title":"Beyond Bounding Box: Multimodal Knowledge Learning for Object Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.04072","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":"sha256:991bd4f891b982c6eca765086b5984d14bd4d34416c547cc0cd205557ccb3f0b","target":"record","created_at":"2026-07-05T04:21:20Z","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":"a1792e647fa9242e4fb88ccad9ab764c19ba1edfd1b692b1ffb00ccdc19112a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-09T07:03:30Z","title_canon_sha256":"b95d84d8c4e9d7d54c72fcc2f72212a735e48f492f07497f5a5ceacbdffb9a10"},"schema_version":"1.0","source":{"id":"2205.04072","kind":"arxiv","version":1}},"canonical_sha256":"35b03f18b0043514bba429ba651d72d4779ac3f5907c45201103dc5ecab842cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35b03f18b0043514bba429ba651d72d4779ac3f5907c45201103dc5ecab842cf","first_computed_at":"2026-07-05T04:21:20.953076Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:21:20.953076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"glNFEGzdB9xdbAAkSOcF/BIaJpz2YI8xpFSxC0d7ERzXxs3GYqZ+4apgz2NyIPZokF+vQZmeXoasDpRBjRFUCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:21:20.953504Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.04072","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:991bd4f891b982c6eca765086b5984d14bd4d34416c547cc0cd205557ccb3f0b","sha256:a3e41281caf7d9af10c95a880d9771e2dd9c54bbbb3eff3a930d992592083890"],"state_sha256":"ec78b74b3db12b74fbebd50b92ba95ef4ef6952ee02ed3e9fa182d3dbd798bd8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LI/OGjGHkCijsbQ4UE+BuSh3U1+4uyGDWxahtl6zaxvCbBjvbY5oVpMPAx3BlOJzITvKKGNiS5DTUCEAdMbmCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T04:44:23.735425Z","bundle_sha256":"5756a491cfbb6eb32c8e544bb9ea264320c1ba45f255b866a9d46df442eeb7ed"}}