{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:DT7UPVJQBNLIWELFHEPNABU3AC","short_pith_number":"pith:DT7UPVJQ","canonical_record":{"source":{"id":"2211.05190","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-09T20:47:45Z","cross_cats_sorted":[],"title_canon_sha256":"bfcf164f7b12362b3eecb69cc26a103442cb2af3c49b4d2aac7d926a970f9539","abstract_canon_sha256":"da0d97a9fc0521168fec478e8f668c67bbd3d0e73fbde8dfbac9b2b847cce032"},"schema_version":"1.0"},"canonical_sha256":"1cff47d5300b568b1165391ed0069b009bce274b56edbfaaaea9029ad1fb5191","source":{"kind":"arxiv","id":"2211.05190","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.05190","created_at":"2026-07-05T05:14:47Z"},{"alias_kind":"arxiv_version","alias_value":"2211.05190v1","created_at":"2026-07-05T05:14:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.05190","created_at":"2026-07-05T05:14:47Z"},{"alias_kind":"pith_short_12","alias_value":"DT7UPVJQBNLI","created_at":"2026-07-05T05:14:47Z"},{"alias_kind":"pith_short_16","alias_value":"DT7UPVJQBNLIWELF","created_at":"2026-07-05T05:14:47Z"},{"alias_kind":"pith_short_8","alias_value":"DT7UPVJQ","created_at":"2026-07-05T05:14:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:DT7UPVJQBNLIWELFHEPNABU3AC","target":"record","payload":{"canonical_record":{"source":{"id":"2211.05190","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-09T20:47:45Z","cross_cats_sorted":[],"title_canon_sha256":"bfcf164f7b12362b3eecb69cc26a103442cb2af3c49b4d2aac7d926a970f9539","abstract_canon_sha256":"da0d97a9fc0521168fec478e8f668c67bbd3d0e73fbde8dfbac9b2b847cce032"},"schema_version":"1.0"},"canonical_sha256":"1cff47d5300b568b1165391ed0069b009bce274b56edbfaaaea9029ad1fb5191","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:14:47.582111Z","signature_b64":"1DhBsvjufGxAQeb89NghvMvlqlIvq5MiY/1nQR/sl3ex2nInU41ICKbY0FLwtjedT/LdeKOeFbgV48ETfi4JCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cff47d5300b568b1165391ed0069b009bce274b56edbfaaaea9029ad1fb5191","last_reissued_at":"2026-07-05T05:14:47.581666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:14:47.581666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.05190","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":"2026-07-05T05:14:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4NKMei1SUdagSdP5ZPdwrvnmL0zRL4bgRIqvO5aq4B+ewwFYWi3XjACsSTDJore/Lcnvv7w/F516g8xo9I7gAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:59:24.259711Z"},"content_sha256":"076682db2920fc565c32ec7eec50b7e0de9f3710b649eb372eda2af7e7d308b5","schema_version":"1.0","event_id":"sha256:076682db2920fc565c32ec7eec50b7e0de9f3710b649eb372eda2af7e7d308b5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:DT7UPVJQBNLIWELFHEPNABU3AC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Reasoning-Aware Explainable VQA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhinav Mathur, Feng Gao, Govind Thattai, Rakesh Vaideeswaran","submitted_at":"2022-11-09T20:47:45Z","abstract_excerpt":"The domain of joint vision-language understanding, especially in the context of reasoning in Visual Question Answering (VQA) models, has garnered significant attention in the recent past. While most of the existing VQA models focus on improving the accuracy of VQA, the way models arrive at an answer is oftentimes a black box. As a step towards making the VQA task more explainable and interpretable, our method is built upon the SOTA VQA framework by augmenting it with an end-to-end explanation generation module. In this paper, we investigate two network architectures, including Long Short-Term "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.05190","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/2211.05190/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":"2026-07-05T05:14:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BQ4pIILZ4gjn0Ym4C5XbkXzdNhTYRXl+6pGFBvyZqt+r1Z7MmCHLMtXfVtacVvcexKACIHbE8SA5WGv7UWA9CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:59:24.260068Z"},"content_sha256":"264edb653dab66794386b6a53a6319fe6586f024e2d1c5e8bf56c048cab049b1","schema_version":"1.0","event_id":"sha256:264edb653dab66794386b6a53a6319fe6586f024e2d1c5e8bf56c048cab049b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DT7UPVJQBNLIWELFHEPNABU3AC/bundle.json","state_url":"https://pith.science/pith/DT7UPVJQBNLIWELFHEPNABU3AC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DT7UPVJQBNLIWELFHEPNABU3AC/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":"2026-07-07T08:59:24Z","links":{"resolver":"https://pith.science/pith/DT7UPVJQBNLIWELFHEPNABU3AC","bundle":"https://pith.science/pith/DT7UPVJQBNLIWELFHEPNABU3AC/bundle.json","state":"https://pith.science/pith/DT7UPVJQBNLIWELFHEPNABU3AC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DT7UPVJQBNLIWELFHEPNABU3AC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DT7UPVJQBNLIWELFHEPNABU3AC","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":"da0d97a9fc0521168fec478e8f668c67bbd3d0e73fbde8dfbac9b2b847cce032","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-09T20:47:45Z","title_canon_sha256":"bfcf164f7b12362b3eecb69cc26a103442cb2af3c49b4d2aac7d926a970f9539"},"schema_version":"1.0","source":{"id":"2211.05190","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.05190","created_at":"2026-07-05T05:14:47Z"},{"alias_kind":"arxiv_version","alias_value":"2211.05190v1","created_at":"2026-07-05T05:14:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.05190","created_at":"2026-07-05T05:14:47Z"},{"alias_kind":"pith_short_12","alias_value":"DT7UPVJQBNLI","created_at":"2026-07-05T05:14:47Z"},{"alias_kind":"pith_short_16","alias_value":"DT7UPVJQBNLIWELF","created_at":"2026-07-05T05:14:47Z"},{"alias_kind":"pith_short_8","alias_value":"DT7UPVJQ","created_at":"2026-07-05T05:14:47Z"}],"graph_snapshots":[{"event_id":"sha256:264edb653dab66794386b6a53a6319fe6586f024e2d1c5e8bf56c048cab049b1","target":"graph","created_at":"2026-07-05T05:14:47Z","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/2211.05190/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The domain of joint vision-language understanding, especially in the context of reasoning in Visual Question Answering (VQA) models, has garnered significant attention in the recent past. While most of the existing VQA models focus on improving the accuracy of VQA, the way models arrive at an answer is oftentimes a black box. As a step towards making the VQA task more explainable and interpretable, our method is built upon the SOTA VQA framework by augmenting it with an end-to-end explanation generation module. In this paper, we investigate two network architectures, including Long Short-Term ","authors_text":"Abhinav Mathur, Feng Gao, Govind Thattai, Rakesh Vaideeswaran","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-09T20:47:45Z","title":"Towards Reasoning-Aware Explainable VQA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.05190","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":"sha256:076682db2920fc565c32ec7eec50b7e0de9f3710b649eb372eda2af7e7d308b5","target":"record","created_at":"2026-07-05T05:14:47Z","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":"da0d97a9fc0521168fec478e8f668c67bbd3d0e73fbde8dfbac9b2b847cce032","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-09T20:47:45Z","title_canon_sha256":"bfcf164f7b12362b3eecb69cc26a103442cb2af3c49b4d2aac7d926a970f9539"},"schema_version":"1.0","source":{"id":"2211.05190","kind":"arxiv","version":1}},"canonical_sha256":"1cff47d5300b568b1165391ed0069b009bce274b56edbfaaaea9029ad1fb5191","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1cff47d5300b568b1165391ed0069b009bce274b56edbfaaaea9029ad1fb5191","first_computed_at":"2026-07-05T05:14:47.581666Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:14:47.581666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1DhBsvjufGxAQeb89NghvMvlqlIvq5MiY/1nQR/sl3ex2nInU41ICKbY0FLwtjedT/LdeKOeFbgV48ETfi4JCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:14:47.582111Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.05190","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:076682db2920fc565c32ec7eec50b7e0de9f3710b649eb372eda2af7e7d308b5","sha256:264edb653dab66794386b6a53a6319fe6586f024e2d1c5e8bf56c048cab049b1"],"state_sha256":"8cd5254ff8496228eed3a071338691e64f6f8d41f09e9421ddc6b98d418463d1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GHwMsSsEaVVBO3BwQ3tiFDyGw8Aafl/6TboSwkGBR/w7Ll8X90+2xPxMYuyYibDLkFfoq7oa67xBAGFu7rWvAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:59:24.261931Z","bundle_sha256":"745d2ede66e005d915d2fb7d5258da67437207cc6d00c70207a1cdde0429926e"}}