{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TPQ44CAWFASCQQKZZTMRV77MDZ","short_pith_number":"pith:TPQ44CAW","schema_version":"1.0","canonical_sha256":"9be1ce08162824284159ccd91affec1e5cab7e96feae0046057bdbd919b005dd","source":{"kind":"arxiv","id":"2205.08094","version":1},"attestation_state":"computed","paper":{"title":"MATrIX -- Modality-Aware Transformer for Information eXtraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Edouard Belval, Lei Chen, Luis Goncalves, Thomas Delteil, Vijay Mahadevan","submitted_at":"2022-05-17T05:06:59Z","abstract_excerpt":"We present MATrIX - a Modality-Aware Transformer for Information eXtraction in the Visual Document Understanding (VDU) domain. VDU covers information extraction from visually rich documents such as forms, invoices, receipts, tables, graphs, presentations, or advertisements. In these, text semantics and visual information supplement each other to provide a global understanding of the document. MATrIX is pre-trained in an unsupervised way with specifically designed tasks that require the use of multi-modal information (spatial, visual, or textual). We consider the spatial and text modalities all"},"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":"2205.08094","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-17T05:06:59Z","cross_cats_sorted":[],"title_canon_sha256":"7125e8adc56d9c84b8a3340d615abeab1bbc3e7b1d287800ecf6442b0d6bf4e8","abstract_canon_sha256":"10d259e81985b9f171a75f9bf553c7b842578be7ae569f623c959763281c825d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:23:59.229830Z","signature_b64":"wQ1rysQFhQ2khlemZp5U9PLtb6WHdGYbzgv+7XBpRFzwjnSX+V+qmyCGUwlU1q8SVU89iY4TmLWpxeQS7ZRrAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9be1ce08162824284159ccd91affec1e5cab7e96feae0046057bdbd919b005dd","last_reissued_at":"2026-07-05T04:23:59.229331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:23:59.229331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MATrIX -- Modality-Aware Transformer for Information eXtraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Edouard Belval, Lei Chen, Luis Goncalves, Thomas Delteil, Vijay Mahadevan","submitted_at":"2022-05-17T05:06:59Z","abstract_excerpt":"We present MATrIX - a Modality-Aware Transformer for Information eXtraction in the Visual Document Understanding (VDU) domain. VDU covers information extraction from visually rich documents such as forms, invoices, receipts, tables, graphs, presentations, or advertisements. In these, text semantics and visual information supplement each other to provide a global understanding of the document. MATrIX is pre-trained in an unsupervised way with specifically designed tasks that require the use of multi-modal information (spatial, visual, or textual). We consider the spatial and text modalities all"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.08094","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/2205.08094/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":"2205.08094","created_at":"2026-07-05T04:23:59.229391+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.08094v1","created_at":"2026-07-05T04:23:59.229391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.08094","created_at":"2026-07-05T04:23:59.229391+00:00"},{"alias_kind":"pith_short_12","alias_value":"TPQ44CAWFASC","created_at":"2026-07-05T04:23:59.229391+00:00"},{"alias_kind":"pith_short_16","alias_value":"TPQ44CAWFASCQQKZ","created_at":"2026-07-05T04:23:59.229391+00:00"},{"alias_kind":"pith_short_8","alias_value":"TPQ44CAW","created_at":"2026-07-05T04:23:59.229391+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/TPQ44CAWFASCQQKZZTMRV77MDZ","json":"https://pith.science/pith/TPQ44CAWFASCQQKZZTMRV77MDZ.json","graph_json":"https://pith.science/api/pith-number/TPQ44CAWFASCQQKZZTMRV77MDZ/graph.json","events_json":"https://pith.science/api/pith-number/TPQ44CAWFASCQQKZZTMRV77MDZ/events.json","paper":"https://pith.science/paper/TPQ44CAW"},"agent_actions":{"view_html":"https://pith.science/pith/TPQ44CAWFASCQQKZZTMRV77MDZ","download_json":"https://pith.science/pith/TPQ44CAWFASCQQKZZTMRV77MDZ.json","view_paper":"https://pith.science/paper/TPQ44CAW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.08094&json=true","fetch_graph":"https://pith.science/api/pith-number/TPQ44CAWFASCQQKZZTMRV77MDZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TPQ44CAWFASCQQKZZTMRV77MDZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TPQ44CAWFASCQQKZZTMRV77MDZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TPQ44CAWFASCQQKZZTMRV77MDZ/action/storage_attestation","attest_author":"https://pith.science/pith/TPQ44CAWFASCQQKZZTMRV77MDZ/action/author_attestation","sign_citation":"https://pith.science/pith/TPQ44CAWFASCQQKZZTMRV77MDZ/action/citation_signature","submit_replication":"https://pith.science/pith/TPQ44CAWFASCQQKZZTMRV77MDZ/action/replication_record"}},"created_at":"2026-07-05T04:23:59.229391+00:00","updated_at":"2026-07-05T04:23:59.229391+00:00"}