{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WAM3TO2SAGGGEMNS4I4I6RCXL2","short_pith_number":"pith:WAM3TO2S","canonical_record":{"source":{"id":"2402.02503","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-04T14:28:23Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"25f01981203056fb0c66ecd5ff4a4f1880fb3af72c817966dca0237a28833672","abstract_canon_sha256":"dc94619bdfb373991e9d5f561ad9021dee61b88a3238c69de8349b6d69673c87"},"schema_version":"1.0"},"canonical_sha256":"b019b9bb52018c6231b2e2388f44575ea4cc796f7454bf8e9e62c72c41e34cee","source":{"kind":"arxiv","id":"2402.02503","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.02503","created_at":"2026-07-05T07:41:48Z"},{"alias_kind":"arxiv_version","alias_value":"2402.02503v1","created_at":"2026-07-05T07:41:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02503","created_at":"2026-07-05T07:41:48Z"},{"alias_kind":"pith_short_12","alias_value":"WAM3TO2SAGGG","created_at":"2026-07-05T07:41:48Z"},{"alias_kind":"pith_short_16","alias_value":"WAM3TO2SAGGGEMNS","created_at":"2026-07-05T07:41:48Z"},{"alias_kind":"pith_short_8","alias_value":"WAM3TO2S","created_at":"2026-07-05T07:41:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WAM3TO2SAGGGEMNS4I4I6RCXL2","target":"record","payload":{"canonical_record":{"source":{"id":"2402.02503","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-04T14:28:23Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"25f01981203056fb0c66ecd5ff4a4f1880fb3af72c817966dca0237a28833672","abstract_canon_sha256":"dc94619bdfb373991e9d5f561ad9021dee61b88a3238c69de8349b6d69673c87"},"schema_version":"1.0"},"canonical_sha256":"b019b9bb52018c6231b2e2388f44575ea4cc796f7454bf8e9e62c72c41e34cee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:48.907434Z","signature_b64":"hBiH3mK2+cNNbCOJjKTNZch+L8NfAmNqIyZ1/Ulqv7eUrTJfKEhPA8mcYhtc+/mqlyRgaNS9diUxVtw22IfFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b019b9bb52018c6231b2e2388f44575ea4cc796f7454bf8e9e62c72c41e34cee","last_reissued_at":"2026-07-05T07:41:48.906940Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:48.906940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.02503","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":"2026-07-05T07:41:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zVJaYtEp/uTYuGa6TNu0BZu5RrsZ5MZxEBWywFxB15fLFzJ/LaS1VTwF83kU5tsWRX8Mb6F0NhIY/QXgqHONDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T03:50:50.723045Z"},"content_sha256":"86a69cea5f5f4aeef1c266d767355c099a4516e2f5ad76c60bb52bae4a337c79","schema_version":"1.0","event_id":"sha256:86a69cea5f5f4aeef1c266d767355c099a4516e2f5ad76c60bb52bae4a337c79"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WAM3TO2SAGGGEMNS4I4I6RCXL2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bin Sun, Fuyan Ma, Jianfei Cai, Shutao Li, Ziyu Ma, Zuxiang Long","submitted_at":"2024-02-04T14:28:23Z","abstract_excerpt":"Knowledge-based visual question answering (VQA) requires world knowledge beyond the image for accurate answer. Recently, instead of extra knowledge bases, a large language model (LLM) like GPT-3 is activated as an implicit knowledge engine to jointly acquire and reason the necessary knowledge for answering by converting images into textual information (e.g., captions and answer candidates). However, such conversion may introduce irrelevant information, which causes the LLM to misinterpret images and ignore visual details crucial for accurate knowledge. We argue that multimodal large language m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02503","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/2402.02503/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":"2026-07-05T07:41:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"86R5DC43/lCW+K2yNBvYGTlFacMh1urJq2Xk96PUl1SlwnbQLs+muVYIySsB5UAsBZQZNRZoeqnFKwwOlFz7DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T03:50:50.723456Z"},"content_sha256":"2b56ad02195bae28445548c3e8497e6c2a5fbf43e616882d6b44943041cbb094","schema_version":"1.0","event_id":"sha256:2b56ad02195bae28445548c3e8497e6c2a5fbf43e616882d6b44943041cbb094"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WAM3TO2SAGGGEMNS4I4I6RCXL2/bundle.json","state_url":"https://pith.science/pith/WAM3TO2SAGGGEMNS4I4I6RCXL2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WAM3TO2SAGGGEMNS4I4I6RCXL2/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":"2026-07-06T03:50:50Z","links":{"resolver":"https://pith.science/pith/WAM3TO2SAGGGEMNS4I4I6RCXL2","bundle":"https://pith.science/pith/WAM3TO2SAGGGEMNS4I4I6RCXL2/bundle.json","state":"https://pith.science/pith/WAM3TO2SAGGGEMNS4I4I6RCXL2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WAM3TO2SAGGGEMNS4I4I6RCXL2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WAM3TO2SAGGGEMNS4I4I6RCXL2","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":"dc94619bdfb373991e9d5f561ad9021dee61b88a3238c69de8349b6d69673c87","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-04T14:28:23Z","title_canon_sha256":"25f01981203056fb0c66ecd5ff4a4f1880fb3af72c817966dca0237a28833672"},"schema_version":"1.0","source":{"id":"2402.02503","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.02503","created_at":"2026-07-05T07:41:48Z"},{"alias_kind":"arxiv_version","alias_value":"2402.02503v1","created_at":"2026-07-05T07:41:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02503","created_at":"2026-07-05T07:41:48Z"},{"alias_kind":"pith_short_12","alias_value":"WAM3TO2SAGGG","created_at":"2026-07-05T07:41:48Z"},{"alias_kind":"pith_short_16","alias_value":"WAM3TO2SAGGGEMNS","created_at":"2026-07-05T07:41:48Z"},{"alias_kind":"pith_short_8","alias_value":"WAM3TO2S","created_at":"2026-07-05T07:41:48Z"}],"graph_snapshots":[{"event_id":"sha256:2b56ad02195bae28445548c3e8497e6c2a5fbf43e616882d6b44943041cbb094","target":"graph","created_at":"2026-07-05T07:41:48Z","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/2402.02503/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Knowledge-based visual question answering (VQA) requires world knowledge beyond the image for accurate answer. Recently, instead of extra knowledge bases, a large language model (LLM) like GPT-3 is activated as an implicit knowledge engine to jointly acquire and reason the necessary knowledge for answering by converting images into textual information (e.g., captions and answer candidates). However, such conversion may introduce irrelevant information, which causes the LLM to misinterpret images and ignore visual details crucial for accurate knowledge. We argue that multimodal large language m","authors_text":"Bin Sun, Fuyan Ma, Jianfei Cai, Shutao Li, Ziyu Ma, Zuxiang Long","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-04T14:28:23Z","title":"GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02503","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":"sha256:86a69cea5f5f4aeef1c266d767355c099a4516e2f5ad76c60bb52bae4a337c79","target":"record","created_at":"2026-07-05T07:41:48Z","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":"dc94619bdfb373991e9d5f561ad9021dee61b88a3238c69de8349b6d69673c87","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-04T14:28:23Z","title_canon_sha256":"25f01981203056fb0c66ecd5ff4a4f1880fb3af72c817966dca0237a28833672"},"schema_version":"1.0","source":{"id":"2402.02503","kind":"arxiv","version":1}},"canonical_sha256":"b019b9bb52018c6231b2e2388f44575ea4cc796f7454bf8e9e62c72c41e34cee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b019b9bb52018c6231b2e2388f44575ea4cc796f7454bf8e9e62c72c41e34cee","first_computed_at":"2026-07-05T07:41:48.906940Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:41:48.906940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hBiH3mK2+cNNbCOJjKTNZch+L8NfAmNqIyZ1/Ulqv7eUrTJfKEhPA8mcYhtc+/mqlyRgaNS9diUxVtw22IfFBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:41:48.907434Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.02503","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86a69cea5f5f4aeef1c266d767355c099a4516e2f5ad76c60bb52bae4a337c79","sha256:2b56ad02195bae28445548c3e8497e6c2a5fbf43e616882d6b44943041cbb094"],"state_sha256":"aea4d98d737cfa488e293430a2cc9b1b9309a0b8faeef4e8864da6e3b499908e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SY7evp+j+55XD66gdRuD3CwKebFj2ji6dUKa0p+9XiRVN20Bgy0uPUwSm6rMEU+6PXHnIgfXjApKo9XZYqt9DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T03:50:50.725714Z","bundle_sha256":"e57e919435b7e7277dd2979bc9737d868c1fb4ed14ff6c847e2d44ff67f92b3e"}}