{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3T44ORLSGJXYK6QY3BKGJYQ4OM","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":"eb7e08578e247c6074778f31b62cc6fb650c185fc4ee9c6d3e1b51e60e6b2a20","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-29T00:36:17Z","title_canon_sha256":"1b3f32d8192c1c8e8e3a099b95e6ccd01a82e36265cd0ddc85f902074eaf227f"},"schema_version":"1.0","source":{"id":"2105.02626","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.02626","created_at":"2026-07-05T02:38:03Z"},{"alias_kind":"arxiv_version","alias_value":"2105.02626v1","created_at":"2026-07-05T02:38:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.02626","created_at":"2026-07-05T02:38:03Z"},{"alias_kind":"pith_short_12","alias_value":"3T44ORLSGJXY","created_at":"2026-07-05T02:38:03Z"},{"alias_kind":"pith_short_16","alias_value":"3T44ORLSGJXYK6QY","created_at":"2026-07-05T02:38:03Z"},{"alias_kind":"pith_short_8","alias_value":"3T44ORLS","created_at":"2026-07-05T02:38:03Z"}],"graph_snapshots":[{"event_id":"sha256:38ff54a945b9c521ceaef632459f4a5b0acf30f24cf3b0bff0c673ea41e7a79f","target":"graph","created_at":"2026-07-05T02:38:03Z","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/2105.02626/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Explainable deep learning models are advantageous in many situations. Prior work mostly provide unimodal explanations through post-hoc approaches not part of the original system design. Explanation mechanisms also ignore useful textual information present in images. In this paper, we propose MTXNet, an end-to-end trainable multimodal architecture to generate multimodal explanations, which focuses on the text in the image. We curate a novel dataset TextVQA-X, containing ground truth visual and multi-reference textual explanations that can be leveraged during both training and evaluation. We the","authors_text":"Karen Hovsepian, Mingwei Shen, Varun Nagaraj Rao, Xingjian Zhen","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-29T00:36:17Z","title":"A First Look: Towards Explainable TextVQA Models via Visual and Textual Explanations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.02626","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:eac84963e209bc9192c46eeb827a703c0a18865b1238537d50e5eb6f09580305","target":"record","created_at":"2026-07-05T02:38:03Z","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":"eb7e08578e247c6074778f31b62cc6fb650c185fc4ee9c6d3e1b51e60e6b2a20","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-29T00:36:17Z","title_canon_sha256":"1b3f32d8192c1c8e8e3a099b95e6ccd01a82e36265cd0ddc85f902074eaf227f"},"schema_version":"1.0","source":{"id":"2105.02626","kind":"arxiv","version":1}},"canonical_sha256":"dcf9c74572326f857a18d85464e21c73368c7f5ae98224bad157367ecbbe0c3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcf9c74572326f857a18d85464e21c73368c7f5ae98224bad157367ecbbe0c3c","first_computed_at":"2026-07-05T02:38:03.174767Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:38:03.174767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"55/sF3QxK07myXUEInNeVBn8UnUkhrNC1GDwtPqFqLsR2woeTiSevUF4ZBF2Or+Y6yzCpJCy+Sqr2IElk1CzAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:38:03.175161Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.02626","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eac84963e209bc9192c46eeb827a703c0a18865b1238537d50e5eb6f09580305","sha256:38ff54a945b9c521ceaef632459f4a5b0acf30f24cf3b0bff0c673ea41e7a79f"],"state_sha256":"8ec6dc5e12cd08aa7bcca11a1af9194280dd3fe6117ee8aa9c34606d4b5600dd"}