{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4RBTI3ULYR54OXKZYPANVJ3VPT","short_pith_number":"pith:4RBTI3UL","canonical_record":{"source":{"id":"2402.03896","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-06T11:07:05Z","cross_cats_sorted":[],"title_canon_sha256":"5392bac8841d48191202a269e9c99c3c7aee952783fc70d66e91ef01aae1042d","abstract_canon_sha256":"0a5b5b948f7d05378157866bbd9b6b5bad40cfb5b2aa8ddc379dbaebf75ec212"},"schema_version":"1.0"},"canonical_sha256":"e443346e8bc47bc75d59c3c0daa7757cff539bacc90b2bd03f38902caeb39bc5","source":{"kind":"arxiv","id":"2402.03896","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.03896","created_at":"2026-07-05T11:18:57Z"},{"alias_kind":"arxiv_version","alias_value":"2402.03896v3","created_at":"2026-07-05T11:18:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03896","created_at":"2026-07-05T11:18:57Z"},{"alias_kind":"pith_short_12","alias_value":"4RBTI3ULYR54","created_at":"2026-07-05T11:18:57Z"},{"alias_kind":"pith_short_16","alias_value":"4RBTI3ULYR54OXKZ","created_at":"2026-07-05T11:18:57Z"},{"alias_kind":"pith_short_8","alias_value":"4RBTI3UL","created_at":"2026-07-05T11:18:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4RBTI3ULYR54OXKZYPANVJ3VPT","target":"record","payload":{"canonical_record":{"source":{"id":"2402.03896","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-06T11:07:05Z","cross_cats_sorted":[],"title_canon_sha256":"5392bac8841d48191202a269e9c99c3c7aee952783fc70d66e91ef01aae1042d","abstract_canon_sha256":"0a5b5b948f7d05378157866bbd9b6b5bad40cfb5b2aa8ddc379dbaebf75ec212"},"schema_version":"1.0"},"canonical_sha256":"e443346e8bc47bc75d59c3c0daa7757cff539bacc90b2bd03f38902caeb39bc5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:57.721871Z","signature_b64":"kQlq6LOqkeyu/5TRzzHkeyUyY8QNuM39Dfts0gjYlEdM8Lxd5DPCJmGTYYg4TDaGBn/sV0Gt056IZWNBYljzCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e443346e8bc47bc75d59c3c0daa7757cff539bacc90b2bd03f38902caeb39bc5","last_reissued_at":"2026-07-05T11:18:57.721436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:57.721436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.03896","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:18:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8tSGVoEyHOPn75OTQ28y+M0+RDJ8/3K58s+SpXwFmv+2QNEvodBi4NFk4Cr9vna632tXvYyCG2xzPFCTk02pAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:43:47.892515Z"},"content_sha256":"917241a8066f02b5af96a9279b91a482846d9b2a5c7564ddd38a6c91ee88c5c1","schema_version":"1.0","event_id":"sha256:917241a8066f02b5af96a9279b91a482846d9b2a5c7564ddd38a6c91ee88c5c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4RBTI3ULYR54OXKZYPANVJ3VPT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Rationales for Explainable Visual Question Answering","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"George Vosselman, Kun Li, Michael Ying Yang","submitted_at":"2024-02-06T11:07:05Z","abstract_excerpt":"Visual Question Answering (VQA) is a challenging task of predicting the answer to a question about the content of an image. Prior works directly evaluate the answering models by simply calculating the accuracy of predicted answers. However, the inner reasoning behind the predictions is disregarded in such a \"black box\" system, and we cannot ascertain the trustworthiness of the predictions. Even more concerning, in some cases, these models predict correct answers despite focusing on irrelevant visual regions or textual tokens. To develop an explainable and trustworthy answering system, we propo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03896","kind":"arxiv","version":3},"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/2402.03896/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":"2026-07-05T11:18:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0RJybBXd92Y4OOZWupnKpyskwxuBuxJ3Lk/7vv3D/14i6/4PraJ6Hm5T4SXDGTT4iPngpWNsVbeW73HsJI0nDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:43:47.893456Z"},"content_sha256":"9c507dfdc6c55ff63b64323011e696d0327666c467127aa734f349c3a972ff3a","schema_version":"1.0","event_id":"sha256:9c507dfdc6c55ff63b64323011e696d0327666c467127aa734f349c3a972ff3a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4RBTI3ULYR54OXKZYPANVJ3VPT/bundle.json","state_url":"https://pith.science/pith/4RBTI3ULYR54OXKZYPANVJ3VPT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4RBTI3ULYR54OXKZYPANVJ3VPT/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":"2026-08-09T00:43:47Z","links":{"resolver":"https://pith.science/pith/4RBTI3ULYR54OXKZYPANVJ3VPT","bundle":"https://pith.science/pith/4RBTI3ULYR54OXKZYPANVJ3VPT/bundle.json","state":"https://pith.science/pith/4RBTI3ULYR54OXKZYPANVJ3VPT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4RBTI3ULYR54OXKZYPANVJ3VPT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4RBTI3ULYR54OXKZYPANVJ3VPT","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":"0a5b5b948f7d05378157866bbd9b6b5bad40cfb5b2aa8ddc379dbaebf75ec212","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-06T11:07:05Z","title_canon_sha256":"5392bac8841d48191202a269e9c99c3c7aee952783fc70d66e91ef01aae1042d"},"schema_version":"1.0","source":{"id":"2402.03896","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.03896","created_at":"2026-07-05T11:18:57Z"},{"alias_kind":"arxiv_version","alias_value":"2402.03896v3","created_at":"2026-07-05T11:18:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03896","created_at":"2026-07-05T11:18:57Z"},{"alias_kind":"pith_short_12","alias_value":"4RBTI3ULYR54","created_at":"2026-07-05T11:18:57Z"},{"alias_kind":"pith_short_16","alias_value":"4RBTI3ULYR54OXKZ","created_at":"2026-07-05T11:18:57Z"},{"alias_kind":"pith_short_8","alias_value":"4RBTI3UL","created_at":"2026-07-05T11:18:57Z"}],"graph_snapshots":[{"event_id":"sha256:9c507dfdc6c55ff63b64323011e696d0327666c467127aa734f349c3a972ff3a","target":"graph","created_at":"2026-07-05T11:18:57Z","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/2402.03896/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Question Answering (VQA) is a challenging task of predicting the answer to a question about the content of an image. Prior works directly evaluate the answering models by simply calculating the accuracy of predicted answers. However, the inner reasoning behind the predictions is disregarded in such a \"black box\" system, and we cannot ascertain the trustworthiness of the predictions. Even more concerning, in some cases, these models predict correct answers despite focusing on irrelevant visual regions or textual tokens. To develop an explainable and trustworthy answering system, we propo","authors_text":"George Vosselman, Kun Li, Michael Ying Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-06T11:07:05Z","title":"Multimodal Rationales for Explainable Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03896","kind":"arxiv","version":3},"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":"sha256:917241a8066f02b5af96a9279b91a482846d9b2a5c7564ddd38a6c91ee88c5c1","target":"record","created_at":"2026-07-05T11:18:57Z","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":"0a5b5b948f7d05378157866bbd9b6b5bad40cfb5b2aa8ddc379dbaebf75ec212","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-06T11:07:05Z","title_canon_sha256":"5392bac8841d48191202a269e9c99c3c7aee952783fc70d66e91ef01aae1042d"},"schema_version":"1.0","source":{"id":"2402.03896","kind":"arxiv","version":3}},"canonical_sha256":"e443346e8bc47bc75d59c3c0daa7757cff539bacc90b2bd03f38902caeb39bc5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e443346e8bc47bc75d59c3c0daa7757cff539bacc90b2bd03f38902caeb39bc5","first_computed_at":"2026-07-05T11:18:57.721436Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:57.721436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kQlq6LOqkeyu/5TRzzHkeyUyY8QNuM39Dfts0gjYlEdM8Lxd5DPCJmGTYYg4TDaGBn/sV0Gt056IZWNBYljzCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:57.721871Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.03896","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:917241a8066f02b5af96a9279b91a482846d9b2a5c7564ddd38a6c91ee88c5c1","sha256:9c507dfdc6c55ff63b64323011e696d0327666c467127aa734f349c3a972ff3a"],"state_sha256":"f77530353dcad71b0518fa5d35203779db286c5396e403e1fad3133ddf5840c4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X1iGNKNtYz8AwhaEQcbi3LUtf2x5jzhPIRofK3V4UR1hMCA21Alvjt1Q7MFKh0cdyKghJK+cpyzIZ7b9sPuCAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:43:47.898612Z","bundle_sha256":"35c8a47ca4d18e36600cc342825fb0f73cdc80181fc7fd8b496d83e5b0fc71de"}}