{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RE3HGEQULCQ4MIT6WLHKQDOQOW","short_pith_number":"pith:RE3HGEQU","canonical_record":{"source":{"id":"2402.12728","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-20T05:32:24Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR","cs.LG"],"title_canon_sha256":"2b90c41a30c14f1a4997fdc8e52e93f0125cc34228d63b0492329e353626c6d2","abstract_canon_sha256":"9e9849ae07a0f6cba63d9f4e7cf830df143fb697c26d884c57393ad90c8aeab0"},"schema_version":"1.0"},"canonical_sha256":"893673121458a1c6227eb2cea80dd0758fbba53f04f1740b18c499653d77797d","source":{"kind":"arxiv","id":"2402.12728","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12728","created_at":"2026-07-05T07:51:39Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12728v2","created_at":"2026-07-05T07:51:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12728","created_at":"2026-07-05T07:51:39Z"},{"alias_kind":"pith_short_12","alias_value":"RE3HGEQULCQ4","created_at":"2026-07-05T07:51:39Z"},{"alias_kind":"pith_short_16","alias_value":"RE3HGEQULCQ4MIT6","created_at":"2026-07-05T07:51:39Z"},{"alias_kind":"pith_short_8","alias_value":"RE3HGEQU","created_at":"2026-07-05T07:51:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RE3HGEQULCQ4MIT6WLHKQDOQOW","target":"record","payload":{"canonical_record":{"source":{"id":"2402.12728","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-20T05:32:24Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR","cs.LG"],"title_canon_sha256":"2b90c41a30c14f1a4997fdc8e52e93f0125cc34228d63b0492329e353626c6d2","abstract_canon_sha256":"9e9849ae07a0f6cba63d9f4e7cf830df143fb697c26d884c57393ad90c8aeab0"},"schema_version":"1.0"},"canonical_sha256":"893673121458a1c6227eb2cea80dd0758fbba53f04f1740b18c499653d77797d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:39.424019Z","signature_b64":"rzsIYQahM8wDsV+w5R48Ya2lxUu6/RpQ5+rNrNUnvZzsF0AU4BGZ2ny18UieIAvLnVLa3m68HWAHuD/4b9XxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"893673121458a1c6227eb2cea80dd0758fbba53f04f1740b18c499653d77797d","last_reissued_at":"2026-07-05T07:51:39.423486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:39.423486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.12728","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":"2026-07-05T07:51:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bOV1l69+Q5Gp9frL0MDP5Y4YdY1kAH1dGYqLFoNfzikmuUYHD2+YpD+N5V3LOJaGQJPvzXK6xqpWmX7FScS8Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:58:00.414378Z"},"content_sha256":"7408257dfc6d302bea0b7ba3d4f4fc8e64457e33b5a4f3f1ab770e3414b211b0","schema_version":"1.0","event_id":"sha256:7408257dfc6d302bea0b7ba3d4f4fc8e64457e33b5a4f3f1ab770e3414b211b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RE3HGEQULCQ4MIT6WLHKQDOQOW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Modality-Aware Integration with Large Language Models for Knowledge-based Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Daochen Zha, Huachi Zhou, Junnan Dong, Pai Zheng, Qinggang Zhang, Xiao Huang","submitted_at":"2024-02-20T05:32:24Z","abstract_excerpt":"Knowledge-based visual question answering (KVQA) has been extensively studied to answer visual questions with external knowledge, e.g., knowledge graphs (KGs). While several attempts have been proposed to leverage large language models (LLMs) as an implicit knowledge source, it remains challenging since LLMs may generate hallucinations. Moreover, multiple knowledge sources, e.g., images, KGs and LLMs, cannot be readily aligned for complex scenarios. To tackle these, we present a novel modality-aware integration with LLMs for KVQA (MAIL). It carefully leverages multimodal knowledge for both ima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12728","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/2402.12728/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":"2026-07-05T07:51:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B1gjQLpDdZc/FID33I3hGjKQ4EBcvDcfGKjDuJDQMSfTjL8CIZvAy9RQydeBLG8Etl2tLAvbi8ReORd50N7YDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:58:00.414885Z"},"content_sha256":"02708324a12930bc27d60713fee20e99d17e4437431d02468511e341ad456ea5","schema_version":"1.0","event_id":"sha256:02708324a12930bc27d60713fee20e99d17e4437431d02468511e341ad456ea5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RE3HGEQULCQ4MIT6WLHKQDOQOW/bundle.json","state_url":"https://pith.science/pith/RE3HGEQULCQ4MIT6WLHKQDOQOW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RE3HGEQULCQ4MIT6WLHKQDOQOW/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":"2026-08-08T20:58:00Z","links":{"resolver":"https://pith.science/pith/RE3HGEQULCQ4MIT6WLHKQDOQOW","bundle":"https://pith.science/pith/RE3HGEQULCQ4MIT6WLHKQDOQOW/bundle.json","state":"https://pith.science/pith/RE3HGEQULCQ4MIT6WLHKQDOQOW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RE3HGEQULCQ4MIT6WLHKQDOQOW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RE3HGEQULCQ4MIT6WLHKQDOQOW","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":"9e9849ae07a0f6cba63d9f4e7cf830df143fb697c26d884c57393ad90c8aeab0","cross_cats_sorted":["cs.AI","cs.CL","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-20T05:32:24Z","title_canon_sha256":"2b90c41a30c14f1a4997fdc8e52e93f0125cc34228d63b0492329e353626c6d2"},"schema_version":"1.0","source":{"id":"2402.12728","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12728","created_at":"2026-07-05T07:51:39Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12728v2","created_at":"2026-07-05T07:51:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12728","created_at":"2026-07-05T07:51:39Z"},{"alias_kind":"pith_short_12","alias_value":"RE3HGEQULCQ4","created_at":"2026-07-05T07:51:39Z"},{"alias_kind":"pith_short_16","alias_value":"RE3HGEQULCQ4MIT6","created_at":"2026-07-05T07:51:39Z"},{"alias_kind":"pith_short_8","alias_value":"RE3HGEQU","created_at":"2026-07-05T07:51:39Z"}],"graph_snapshots":[{"event_id":"sha256:02708324a12930bc27d60713fee20e99d17e4437431d02468511e341ad456ea5","target":"graph","created_at":"2026-07-05T07:51:39Z","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/2402.12728/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Knowledge-based visual question answering (KVQA) has been extensively studied to answer visual questions with external knowledge, e.g., knowledge graphs (KGs). While several attempts have been proposed to leverage large language models (LLMs) as an implicit knowledge source, it remains challenging since LLMs may generate hallucinations. Moreover, multiple knowledge sources, e.g., images, KGs and LLMs, cannot be readily aligned for complex scenarios. To tackle these, we present a novel modality-aware integration with LLMs for KVQA (MAIL). It carefully leverages multimodal knowledge for both ima","authors_text":"Daochen Zha, Huachi Zhou, Junnan Dong, Pai Zheng, Qinggang Zhang, Xiao Huang","cross_cats":["cs.AI","cs.CL","cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-20T05:32:24Z","title":"Modality-Aware Integration with Large Language Models for Knowledge-based Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12728","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":"sha256:7408257dfc6d302bea0b7ba3d4f4fc8e64457e33b5a4f3f1ab770e3414b211b0","target":"record","created_at":"2026-07-05T07:51:39Z","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":"9e9849ae07a0f6cba63d9f4e7cf830df143fb697c26d884c57393ad90c8aeab0","cross_cats_sorted":["cs.AI","cs.CL","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-20T05:32:24Z","title_canon_sha256":"2b90c41a30c14f1a4997fdc8e52e93f0125cc34228d63b0492329e353626c6d2"},"schema_version":"1.0","source":{"id":"2402.12728","kind":"arxiv","version":2}},"canonical_sha256":"893673121458a1c6227eb2cea80dd0758fbba53f04f1740b18c499653d77797d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"893673121458a1c6227eb2cea80dd0758fbba53f04f1740b18c499653d77797d","first_computed_at":"2026-07-05T07:51:39.423486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:39.423486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rzsIYQahM8wDsV+w5R48Ya2lxUu6/RpQ5+rNrNUnvZzsF0AU4BGZ2ny18UieIAvLnVLa3m68HWAHuD/4b9XxDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:39.424019Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.12728","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7408257dfc6d302bea0b7ba3d4f4fc8e64457e33b5a4f3f1ab770e3414b211b0","sha256:02708324a12930bc27d60713fee20e99d17e4437431d02468511e341ad456ea5"],"state_sha256":"368c6f44a3f7e2f55b51fbfad4bbbe80118c726e3b4d2582cb9d55742221dc78"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"793zt85ZFCp0cWO0cjs8f7NMAltnWVa31oJZ0trNZMB4QFGmEtoW+DhlZmO+dSPc5UM4OnQKhsZZqbKeO8q9AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:58:00.419136Z","bundle_sha256":"5a7442c4b0e6248a61569925a9ad72914261724a198696f903d99ea9f0951581"}}