{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LSB7VMBPBX4XZW4X33BG6LIIRN","short_pith_number":"pith:LSB7VMBP","schema_version":"1.0","canonical_sha256":"5c83fab02f0df97cdb97dec26f2d088b720e2db4db771d1499f86fa1cc356bc8","source":{"kind":"arxiv","id":"2007.12146","version":2},"attestation_state":"computed","paper":{"title":"Spatially Aware Multimodal Transformers for TextVQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Schwing, Devi Parikh, Dhruv Batra, Harsh Agrawal, Jiasen Lu, Peter Anderson, Yash Kant","submitted_at":"2020-07-23T17:20:55Z","abstract_excerpt":"Textual cues are essential for everyday tasks like buying groceries and using public transport. To develop this assistive technology, we study the TextVQA task, i.e., reasoning about text in images to answer a question. Existing approaches are limited in their use of spatial relations and rely on fully-connected transformer-like architectures to implicitly learn the spatial structure of a scene. In contrast, we propose a novel spatially aware self-attention layer such that each visual entity only looks at neighboring entities defined by a spatial graph. Further, each head in our multi-head sel"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2007.12146","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-23T17:20:55Z","cross_cats_sorted":[],"title_canon_sha256":"2610976198ad866cac221c5f2bb98b588abb1dbb9b5ad8120b8f859567cf5280","abstract_canon_sha256":"97b9c9725ba3d9ea29c21126ca577d813baac756a5c627ef69cfa42f36aad797"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:01:30.951554Z","signature_b64":"ZAaXX6g6jzN8xRmB3Yjycit4hRmw+PZpQjS6QcpkpkCZJKZ4zl09VO6oW+xVroaKX4gCf8ZSHhnkdlFpa8gVCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c83fab02f0df97cdb97dec26f2d088b720e2db4db771d1499f86fa1cc356bc8","last_reissued_at":"2026-07-05T02:01:30.951003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:01:30.951003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatially Aware Multimodal Transformers for TextVQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Schwing, Devi Parikh, Dhruv Batra, Harsh Agrawal, Jiasen Lu, Peter Anderson, Yash Kant","submitted_at":"2020-07-23T17:20:55Z","abstract_excerpt":"Textual cues are essential for everyday tasks like buying groceries and using public transport. To develop this assistive technology, we study the TextVQA task, i.e., reasoning about text in images to answer a question. Existing approaches are limited in their use of spatial relations and rely on fully-connected transformer-like architectures to implicitly learn the spatial structure of a scene. In contrast, we propose a novel spatially aware self-attention layer such that each visual entity only looks at neighboring entities defined by a spatial graph. Further, each head in our multi-head sel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.12146","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/2007.12146/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2007.12146","created_at":"2026-07-05T02:01:30.951063+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.12146v2","created_at":"2026-07-05T02:01:30.951063+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.12146","created_at":"2026-07-05T02:01:30.951063+00:00"},{"alias_kind":"pith_short_12","alias_value":"LSB7VMBPBX4X","created_at":"2026-07-05T02:01:30.951063+00:00"},{"alias_kind":"pith_short_16","alias_value":"LSB7VMBPBX4XZW4X","created_at":"2026-07-05T02:01:30.951063+00:00"},{"alias_kind":"pith_short_8","alias_value":"LSB7VMBP","created_at":"2026-07-05T02:01:30.951063+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LSB7VMBPBX4XZW4X33BG6LIIRN","json":"https://pith.science/pith/LSB7VMBPBX4XZW4X33BG6LIIRN.json","graph_json":"https://pith.science/api/pith-number/LSB7VMBPBX4XZW4X33BG6LIIRN/graph.json","events_json":"https://pith.science/api/pith-number/LSB7VMBPBX4XZW4X33BG6LIIRN/events.json","paper":"https://pith.science/paper/LSB7VMBP"},"agent_actions":{"view_html":"https://pith.science/pith/LSB7VMBPBX4XZW4X33BG6LIIRN","download_json":"https://pith.science/pith/LSB7VMBPBX4XZW4X33BG6LIIRN.json","view_paper":"https://pith.science/paper/LSB7VMBP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.12146&json=true","fetch_graph":"https://pith.science/api/pith-number/LSB7VMBPBX4XZW4X33BG6LIIRN/graph.json","fetch_events":"https://pith.science/api/pith-number/LSB7VMBPBX4XZW4X33BG6LIIRN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LSB7VMBPBX4XZW4X33BG6LIIRN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LSB7VMBPBX4XZW4X33BG6LIIRN/action/storage_attestation","attest_author":"https://pith.science/pith/LSB7VMBPBX4XZW4X33BG6LIIRN/action/author_attestation","sign_citation":"https://pith.science/pith/LSB7VMBPBX4XZW4X33BG6LIIRN/action/citation_signature","submit_replication":"https://pith.science/pith/LSB7VMBPBX4XZW4X33BG6LIIRN/action/replication_record"}},"created_at":"2026-07-05T02:01:30.951063+00:00","updated_at":"2026-07-05T02:01:30.951063+00:00"}