{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:223ZEFVPLB47PVGICQYQX4VNIT","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":"4d6dcc6b2c0d0cde64d1b4a0483c56391da551a57bbb0057ebbcb5ec1a2c20d8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-22T04:28:07Z","title_canon_sha256":"7cc3bcb6e3d547115ff772b55d65da902f3027d266c106f2f1400170dd9a8033"},"schema_version":"1.0","source":{"id":"2106.11539","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.11539","created_at":"2026-07-05T03:15:34Z"},{"alias_kind":"arxiv_version","alias_value":"2106.11539v2","created_at":"2026-07-05T03:15:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.11539","created_at":"2026-07-05T03:15:34Z"},{"alias_kind":"pith_short_12","alias_value":"223ZEFVPLB47","created_at":"2026-07-05T03:15:34Z"},{"alias_kind":"pith_short_16","alias_value":"223ZEFVPLB47PVGI","created_at":"2026-07-05T03:15:34Z"},{"alias_kind":"pith_short_8","alias_value":"223ZEFVP","created_at":"2026-07-05T03:15:34Z"}],"graph_snapshots":[{"event_id":"sha256:9af52ae6ba9db164bc1065cdf44d854a6716ae1dc8d412d88491c82a1620d2a8","target":"graph","created_at":"2026-07-05T03:15:34Z","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/2106.11539/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present DocFormer -- a multi-modal transformer based architecture for the task of Visual Document Understanding (VDU). VDU is a challenging problem which aims to understand documents in their varied formats (forms, receipts etc.) and layouts. In addition, DocFormer is pre-trained in an unsupervised fashion using carefully designed tasks which encourage multi-modal interaction. DocFormer uses text, vision and spatial features and combines them using a novel multi-modal self-attention layer. DocFormer also shares learned spatial embeddings across modalities which makes it easy for the model t","authors_text":"Bhargava Urala Kota, Bhavan Jasani, R. Manmatha, Srikar Appalaraju, Yusheng Xie","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-22T04:28:07Z","title":"DocFormer: End-to-End Transformer for Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.11539","kind":"arxiv","version":2},"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":"sha256:73293e168f437f207d47197f62bafd446aa0dd45804e7ac165ed9839fb767159","target":"record","created_at":"2026-07-05T03:15:34Z","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":"4d6dcc6b2c0d0cde64d1b4a0483c56391da551a57bbb0057ebbcb5ec1a2c20d8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-22T04:28:07Z","title_canon_sha256":"7cc3bcb6e3d547115ff772b55d65da902f3027d266c106f2f1400170dd9a8033"},"schema_version":"1.0","source":{"id":"2106.11539","kind":"arxiv","version":2}},"canonical_sha256":"d6b79216af5879f7d4c814310bf2ad44e10ab442876a4149dc31bdb4196828ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6b79216af5879f7d4c814310bf2ad44e10ab442876a4149dc31bdb4196828ea","first_computed_at":"2026-07-05T03:15:34.844623Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:15:34.844623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sm0H8Pm145DOGV4dxtehwobOBldpOqt0WMBHHwifbbEUkhYsxN4aCCbiPqmIvIWPQvrdTV46KMscFI6D++hFBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:15:34.845044Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.11539","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73293e168f437f207d47197f62bafd446aa0dd45804e7ac165ed9839fb767159","sha256:9af52ae6ba9db164bc1065cdf44d854a6716ae1dc8d412d88491c82a1620d2a8"],"state_sha256":"e72d3d860bfb447e8562913de9dca651398681cb8fc4a6fbaa582be89039f285"}