{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6BEXOVSC6ZTTAEFQBUMQB52F64","short_pith_number":"pith:6BEXOVSC","canonical_record":{"source":{"id":"2407.12277","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T02:58:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8c60e4fb1f7749cdc98180f03331f6190e202129b325cea542d7a85955a34b90","abstract_canon_sha256":"0839c85869fda719d3f7ad5804a2242ce38d967b2be14397343339f953a5a5ae"},"schema_version":"1.0"},"canonical_sha256":"f049775642f6673010b00d1900f745f701c988203818b3a7c1fb4fde3a3877d0","source":{"kind":"arxiv","id":"2407.12277","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12277","created_at":"2026-07-05T08:45:02Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12277v1","created_at":"2026-07-05T08:45:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12277","created_at":"2026-07-05T08:45:02Z"},{"alias_kind":"pith_short_12","alias_value":"6BEXOVSC6ZTT","created_at":"2026-07-05T08:45:02Z"},{"alias_kind":"pith_short_16","alias_value":"6BEXOVSC6ZTTAEFQ","created_at":"2026-07-05T08:45:02Z"},{"alias_kind":"pith_short_8","alias_value":"6BEXOVSC","created_at":"2026-07-05T08:45:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6BEXOVSC6ZTTAEFQBUMQB52F64","target":"record","payload":{"canonical_record":{"source":{"id":"2407.12277","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T02:58:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8c60e4fb1f7749cdc98180f03331f6190e202129b325cea542d7a85955a34b90","abstract_canon_sha256":"0839c85869fda719d3f7ad5804a2242ce38d967b2be14397343339f953a5a5ae"},"schema_version":"1.0"},"canonical_sha256":"f049775642f6673010b00d1900f745f701c988203818b3a7c1fb4fde3a3877d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:02.414201Z","signature_b64":"Ox2P56PpBbLTWHvoPJR2kUYuQmWXX+DifAAUgsZ0DOwwvg7NBOnS/ySsa4Mf4gJ5HDYPKGSMHWNTdSmTx0ztCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f049775642f6673010b00d1900f745f701c988203818b3a7c1fb4fde3a3877d0","last_reissued_at":"2026-07-05T08:45:02.413789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:02.413789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.12277","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":"2026-07-05T08:45:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SjpC7IWfTrKjNayRT3kAi4yKcbuIgXy6oafasGZU1w7mR+JRnTWvQe1Umc+3IBfJIMyS2+J1RzjKTnniN2baCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:44:52.365890Z"},"content_sha256":"509b75bbb6f25e9baf75418cbdad94690f2e768576e5ed354a5c6a4e60c0f6e3","schema_version":"1.0","event_id":"sha256:509b75bbb6f25e9baf75418cbdad94690f2e768576e5ed354a5c6a4e60c0f6e3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6BEXOVSC6ZTTAEFQBUMQB52F64","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Reranking for Knowledge-Intensive Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexander Hauptmann, Hamed Zamani, Haoyang Wen, Honglei Zhuang, Michael Bendersky","submitted_at":"2024-07-17T02:58:52Z","abstract_excerpt":"Knowledge-intensive visual question answering requires models to effectively use external knowledge to help answer visual questions. A typical pipeline includes a knowledge retriever and an answer generator. However, a retriever that utilizes local information, such as an image patch, may not provide reliable question-candidate relevance scores. Besides, the two-tower architecture also limits the relevance score modeling of a retriever to select top candidates for answer generator reasoning. In this paper, we introduce an additional module, a multi-modal reranker, to improve the ranking qualit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12277","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/2407.12277/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":"2026-07-05T08:45:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ty+lQeNCGJKNx90i7W01GgBw+dssEpErF+FEwmkVTVUZCKGm7jiKMUFLvHyf5wylvoPS4uOLUQ/zyIYFTmdUAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:44:52.366399Z"},"content_sha256":"c246de529bcf46368396dda1214d750b9210922e5484c06113abc777c2d065d4","schema_version":"1.0","event_id":"sha256:c246de529bcf46368396dda1214d750b9210922e5484c06113abc777c2d065d4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6BEXOVSC6ZTTAEFQBUMQB52F64/bundle.json","state_url":"https://pith.science/pith/6BEXOVSC6ZTTAEFQBUMQB52F64/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6BEXOVSC6ZTTAEFQBUMQB52F64/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":"2026-08-04T10:44:52Z","links":{"resolver":"https://pith.science/pith/6BEXOVSC6ZTTAEFQBUMQB52F64","bundle":"https://pith.science/pith/6BEXOVSC6ZTTAEFQBUMQB52F64/bundle.json","state":"https://pith.science/pith/6BEXOVSC6ZTTAEFQBUMQB52F64/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6BEXOVSC6ZTTAEFQBUMQB52F64/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6BEXOVSC6ZTTAEFQBUMQB52F64","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":"0839c85869fda719d3f7ad5804a2242ce38d967b2be14397343339f953a5a5ae","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T02:58:52Z","title_canon_sha256":"8c60e4fb1f7749cdc98180f03331f6190e202129b325cea542d7a85955a34b90"},"schema_version":"1.0","source":{"id":"2407.12277","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12277","created_at":"2026-07-05T08:45:02Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12277v1","created_at":"2026-07-05T08:45:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12277","created_at":"2026-07-05T08:45:02Z"},{"alias_kind":"pith_short_12","alias_value":"6BEXOVSC6ZTT","created_at":"2026-07-05T08:45:02Z"},{"alias_kind":"pith_short_16","alias_value":"6BEXOVSC6ZTTAEFQ","created_at":"2026-07-05T08:45:02Z"},{"alias_kind":"pith_short_8","alias_value":"6BEXOVSC","created_at":"2026-07-05T08:45:02Z"}],"graph_snapshots":[{"event_id":"sha256:c246de529bcf46368396dda1214d750b9210922e5484c06113abc777c2d065d4","target":"graph","created_at":"2026-07-05T08:45:02Z","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/2407.12277/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Knowledge-intensive visual question answering requires models to effectively use external knowledge to help answer visual questions. A typical pipeline includes a knowledge retriever and an answer generator. However, a retriever that utilizes local information, such as an image patch, may not provide reliable question-candidate relevance scores. Besides, the two-tower architecture also limits the relevance score modeling of a retriever to select top candidates for answer generator reasoning. In this paper, we introduce an additional module, a multi-modal reranker, to improve the ranking qualit","authors_text":"Alexander Hauptmann, Hamed Zamani, Haoyang Wen, Honglei Zhuang, Michael Bendersky","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T02:58:52Z","title":"Multimodal Reranking for Knowledge-Intensive Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12277","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":"sha256:509b75bbb6f25e9baf75418cbdad94690f2e768576e5ed354a5c6a4e60c0f6e3","target":"record","created_at":"2026-07-05T08:45:02Z","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":"0839c85869fda719d3f7ad5804a2242ce38d967b2be14397343339f953a5a5ae","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T02:58:52Z","title_canon_sha256":"8c60e4fb1f7749cdc98180f03331f6190e202129b325cea542d7a85955a34b90"},"schema_version":"1.0","source":{"id":"2407.12277","kind":"arxiv","version":1}},"canonical_sha256":"f049775642f6673010b00d1900f745f701c988203818b3a7c1fb4fde3a3877d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f049775642f6673010b00d1900f745f701c988203818b3a7c1fb4fde3a3877d0","first_computed_at":"2026-07-05T08:45:02.413789Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:02.413789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ox2P56PpBbLTWHvoPJR2kUYuQmWXX+DifAAUgsZ0DOwwvg7NBOnS/ySsa4Mf4gJ5HDYPKGSMHWNTdSmTx0ztCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:02.414201Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12277","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:509b75bbb6f25e9baf75418cbdad94690f2e768576e5ed354a5c6a4e60c0f6e3","sha256:c246de529bcf46368396dda1214d750b9210922e5484c06113abc777c2d065d4"],"state_sha256":"61271b94547f4505e55552b39fa88490c3318ca21edef2363434bf9f5fdf440b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OgmLRXpb2KjwJFK4es5nXewVwSsTqNXcdMcJezW6mEbJcW5C9e0pHePqSeNMhXxw3fLKo2AaIyKL3U5TYQmoAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T10:44:52.370128Z","bundle_sha256":"44cc087da4aba6fa299b7d949af25142382732fb257a1c4ebdc58e62e513165c"}}