{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:F4NB5GMEFTNABLP6FVYIW72MAH","short_pith_number":"pith:F4NB5GME","canonical_record":{"source":{"id":"2203.02378","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-04T15:34:46Z","cross_cats_sorted":[],"title_canon_sha256":"4cdb7486bc9500ba73d9c62673414eceb61245d79661d10348d4c9b9709c8d7d","abstract_canon_sha256":"8c4b87e095ae4461d7d48e62ea35e14177371096616d1506a47514cc1bed90e9"},"schema_version":"1.0"},"canonical_sha256":"2f1a1e99842cda00adfe2d708b7f4c01ebe7653b3ecf371819de2886f5169256","source":{"kind":"arxiv","id":"2203.02378","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.02378","created_at":"2026-07-05T04:41:11Z"},{"alias_kind":"arxiv_version","alias_value":"2203.02378v3","created_at":"2026-07-05T04:41:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02378","created_at":"2026-07-05T04:41:11Z"},{"alias_kind":"pith_short_12","alias_value":"F4NB5GMEFTNA","created_at":"2026-07-05T04:41:11Z"},{"alias_kind":"pith_short_16","alias_value":"F4NB5GMEFTNABLP6","created_at":"2026-07-05T04:41:11Z"},{"alias_kind":"pith_short_8","alias_value":"F4NB5GME","created_at":"2026-07-05T04:41:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:F4NB5GMEFTNABLP6FVYIW72MAH","target":"record","payload":{"canonical_record":{"source":{"id":"2203.02378","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-04T15:34:46Z","cross_cats_sorted":[],"title_canon_sha256":"4cdb7486bc9500ba73d9c62673414eceb61245d79661d10348d4c9b9709c8d7d","abstract_canon_sha256":"8c4b87e095ae4461d7d48e62ea35e14177371096616d1506a47514cc1bed90e9"},"schema_version":"1.0"},"canonical_sha256":"2f1a1e99842cda00adfe2d708b7f4c01ebe7653b3ecf371819de2886f5169256","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:41:11.505258Z","signature_b64":"hVs44Qwbz71hPqF4z/gkiU5yZO3EGsPlYLKHFRiYFUr7uz+LzPHzA3+LEEVPrDYtlP9xQc+bEflxi7nkJVvxDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f1a1e99842cda00adfe2d708b7f4c01ebe7653b3ecf371819de2886f5169256","last_reissued_at":"2026-07-05T04:41:11.504802Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:41:11.504802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.02378","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:41:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4DH/v2aSRHcVyRVem24PfZRv2WLab68snS9B6Is4NCvVqYKbGjehps0YdMo7qz8pyrCtRnSLglxIVcSmUFn3CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T15:47:05.452516Z"},"content_sha256":"c6f2ceab4b31b2f5e217502d0c29e9abb7bb19e2293d2e0fe48e69936ad95b65","schema_version":"1.0","event_id":"sha256:c6f2ceab4b31b2f5e217502d0c29e9abb7bb19e2293d2e0fe48e69936ad95b65"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:F4NB5GMEFTNABLP6FVYIW72MAH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DiT: Self-supervised Pre-training for Document Image Transformer","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cha Zhang, Furu Wei, Junlong Li, Lei Cui, Tengchao Lv, Yiheng Xu","submitted_at":"2022-03-04T15:34:46Z","abstract_excerpt":"Image Transformer has recently achieved significant progress for natural image understanding, either using supervised (ViT, DeiT, etc.) or self-supervised (BEiT, MAE, etc.) pre-training techniques. In this paper, we propose \\textbf{DiT}, a self-supervised pre-trained \\textbf{D}ocument \\textbf{I}mage \\textbf{T}ransformer model using large-scale unlabeled text images for Document AI tasks, which is essential since no supervised counterparts ever exist due to the lack of human-labeled document images. We leverage DiT as the backbone network in a variety of vision-based Document AI tasks, includin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02378","kind":"arxiv","version":3},"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/2203.02378/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":"2026-07-05T04:41:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h5jzzM/kbHuW8tqVgN8K+8fdl4YBJSGnoS3zoeUd+E7JMJO+KrI4VPjRCNDt4HI9fOysERJqUrXuB0W/dXcSBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T15:47:05.453030Z"},"content_sha256":"6f48452be5bfba150ccaba6dc05ebf3481b8641b8393e048722d121f7988f24b","schema_version":"1.0","event_id":"sha256:6f48452be5bfba150ccaba6dc05ebf3481b8641b8393e048722d121f7988f24b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F4NB5GMEFTNABLP6FVYIW72MAH/bundle.json","state_url":"https://pith.science/pith/F4NB5GMEFTNABLP6FVYIW72MAH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F4NB5GMEFTNABLP6FVYIW72MAH/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":"2026-08-12T15:47:05Z","links":{"resolver":"https://pith.science/pith/F4NB5GMEFTNABLP6FVYIW72MAH","bundle":"https://pith.science/pith/F4NB5GMEFTNABLP6FVYIW72MAH/bundle.json","state":"https://pith.science/pith/F4NB5GMEFTNABLP6FVYIW72MAH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F4NB5GMEFTNABLP6FVYIW72MAH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:F4NB5GMEFTNABLP6FVYIW72MAH","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":"8c4b87e095ae4461d7d48e62ea35e14177371096616d1506a47514cc1bed90e9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-04T15:34:46Z","title_canon_sha256":"4cdb7486bc9500ba73d9c62673414eceb61245d79661d10348d4c9b9709c8d7d"},"schema_version":"1.0","source":{"id":"2203.02378","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.02378","created_at":"2026-07-05T04:41:11Z"},{"alias_kind":"arxiv_version","alias_value":"2203.02378v3","created_at":"2026-07-05T04:41:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02378","created_at":"2026-07-05T04:41:11Z"},{"alias_kind":"pith_short_12","alias_value":"F4NB5GMEFTNA","created_at":"2026-07-05T04:41:11Z"},{"alias_kind":"pith_short_16","alias_value":"F4NB5GMEFTNABLP6","created_at":"2026-07-05T04:41:11Z"},{"alias_kind":"pith_short_8","alias_value":"F4NB5GME","created_at":"2026-07-05T04:41:11Z"}],"graph_snapshots":[{"event_id":"sha256:6f48452be5bfba150ccaba6dc05ebf3481b8641b8393e048722d121f7988f24b","target":"graph","created_at":"2026-07-05T04:41:11Z","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/2203.02378/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image Transformer has recently achieved significant progress for natural image understanding, either using supervised (ViT, DeiT, etc.) or self-supervised (BEiT, MAE, etc.) pre-training techniques. In this paper, we propose \\textbf{DiT}, a self-supervised pre-trained \\textbf{D}ocument \\textbf{I}mage \\textbf{T}ransformer model using large-scale unlabeled text images for Document AI tasks, which is essential since no supervised counterparts ever exist due to the lack of human-labeled document images. We leverage DiT as the backbone network in a variety of vision-based Document AI tasks, includin","authors_text":"Cha Zhang, Furu Wei, Junlong Li, Lei Cui, Tengchao Lv, Yiheng Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-04T15:34:46Z","title":"DiT: Self-supervised Pre-training for Document Image Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02378","kind":"arxiv","version":3},"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:c6f2ceab4b31b2f5e217502d0c29e9abb7bb19e2293d2e0fe48e69936ad95b65","target":"record","created_at":"2026-07-05T04:41:11Z","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":"8c4b87e095ae4461d7d48e62ea35e14177371096616d1506a47514cc1bed90e9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-04T15:34:46Z","title_canon_sha256":"4cdb7486bc9500ba73d9c62673414eceb61245d79661d10348d4c9b9709c8d7d"},"schema_version":"1.0","source":{"id":"2203.02378","kind":"arxiv","version":3}},"canonical_sha256":"2f1a1e99842cda00adfe2d708b7f4c01ebe7653b3ecf371819de2886f5169256","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f1a1e99842cda00adfe2d708b7f4c01ebe7653b3ecf371819de2886f5169256","first_computed_at":"2026-07-05T04:41:11.504802Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:41:11.504802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hVs44Qwbz71hPqF4z/gkiU5yZO3EGsPlYLKHFRiYFUr7uz+LzPHzA3+LEEVPrDYtlP9xQc+bEflxi7nkJVvxDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:41:11.505258Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.02378","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6f2ceab4b31b2f5e217502d0c29e9abb7bb19e2293d2e0fe48e69936ad95b65","sha256:6f48452be5bfba150ccaba6dc05ebf3481b8641b8393e048722d121f7988f24b"],"state_sha256":"1857c4bcb799cdadf1d86b3081f0439f0a483d2f8b553d10edb14102bb8eef01"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QTYaJ/NxqfxW0FDXkSEHsZrixwp6CNt6AboNnwL2b28rLTJdZ1CJMR/TygnOqH9sJCxYcWZpPeJm8TDRFzNyDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T15:47:05.458524Z","bundle_sha256":"a284bc05f8ca318af1569d1bbd52ff300c79d8b6cb535214bbe2faf66857b3e5"}}