{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:3C6INQHXOVJ6GX376EWAREVQ3L","short_pith_number":"pith:3C6INQHX","canonical_record":{"source":{"id":"2106.03331","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-07T04:19:49Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8d9b3a30d59a6968c919b39bba1a15c5241d05c344ac005f12714cbd9c803368","abstract_canon_sha256":"be5999bf3ea68c64c1471ea700105c26169ac38b6a2a1cefda19f1a0e672f1d3"},"schema_version":"1.0"},"canonical_sha256":"d8bc86c0f77553e35f7ff12c0892b0dafb8d0795b75f16113d41cce6ea85d6e0","source":{"kind":"arxiv","id":"2106.03331","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.03331","created_at":"2026-07-05T02:46:48Z"},{"alias_kind":"arxiv_version","alias_value":"2106.03331v1","created_at":"2026-07-05T02:46:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03331","created_at":"2026-07-05T02:46:48Z"},{"alias_kind":"pith_short_12","alias_value":"3C6INQHXOVJ6","created_at":"2026-07-05T02:46:48Z"},{"alias_kind":"pith_short_16","alias_value":"3C6INQHXOVJ6GX37","created_at":"2026-07-05T02:46:48Z"},{"alias_kind":"pith_short_8","alias_value":"3C6INQHX","created_at":"2026-07-05T02:46:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:3C6INQHXOVJ6GX376EWAREVQ3L","target":"record","payload":{"canonical_record":{"source":{"id":"2106.03331","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-07T04:19:49Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8d9b3a30d59a6968c919b39bba1a15c5241d05c344ac005f12714cbd9c803368","abstract_canon_sha256":"be5999bf3ea68c64c1471ea700105c26169ac38b6a2a1cefda19f1a0e672f1d3"},"schema_version":"1.0"},"canonical_sha256":"d8bc86c0f77553e35f7ff12c0892b0dafb8d0795b75f16113d41cce6ea85d6e0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:48.569974Z","signature_b64":"+pARKsjByhQpr4j8XKAXYVFwFXdhrGWKm1OhZDw+PhYVmFLqzp8D3+egLDmQgRZfhCsVGnhYpWATI+vY6RqQAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8bc86c0f77553e35f7ff12c0892b0dafb8d0795b75f16113d41cce6ea85d6e0","last_reissued_at":"2026-07-05T02:46:48.569462Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:48.569462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.03331","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:46:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"63Ki+RgMUkWc8Ci1LNC5ojI3/a5qPbkmLV2NePZfHWLod8rmJiQ1XfmaBvI2OFzzyLNgSL9knO4dUV2Ef3VdDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:59:57.773149Z"},"content_sha256":"dd2ac0061b5422421f193e72246f8e017fd5762cf47440b19fb9401c86fac0f2","schema_version":"1.0","event_id":"sha256:dd2ac0061b5422421f193e72246f8e017fd5762cf47440b19fb9401c86fac0f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:3C6INQHXOVJ6GX376EWAREVQ3L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SelfDoc: Self-Supervised Document Representation Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Handong Zhao, Hongfu Liu, Jason Kuen, Jiuxiang Gu, Peizhao Li, Rajiv Jain, Varun Manjunatha, Vlad I. Morariu","submitted_at":"2021-06-07T04:19:49Z","abstract_excerpt":"We propose SelfDoc, a task-agnostic pre-training framework for document image understanding. Because documents are multimodal and are intended for sequential reading, our framework exploits the positional, textual, and visual information of every semantically meaningful component in a document, and it models the contextualization between each block of content. Unlike existing document pre-training models, our model is coarse-grained instead of treating individual words as input, therefore avoiding an overly fine-grained with excessive contextualization. Beyond that, we introduce cross-modal le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03331","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/2106.03331/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":"2026-07-05T02:46:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qdOl22Q+Az873Ha1KKJv5CxpHZYW0fklQ2iqp1+ermby4J+Rxi6ezU3YH/jTENIbAL9PwocU5blDwu2Ltr6aDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:59:57.773651Z"},"content_sha256":"81e259efb6139f03fc605f0f404099db1c4181fdc773740d0f205b88698d7017","schema_version":"1.0","event_id":"sha256:81e259efb6139f03fc605f0f404099db1c4181fdc773740d0f205b88698d7017"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3C6INQHXOVJ6GX376EWAREVQ3L/bundle.json","state_url":"https://pith.science/pith/3C6INQHXOVJ6GX376EWAREVQ3L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3C6INQHXOVJ6GX376EWAREVQ3L/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":"2026-08-14T19:59:57Z","links":{"resolver":"https://pith.science/pith/3C6INQHXOVJ6GX376EWAREVQ3L","bundle":"https://pith.science/pith/3C6INQHXOVJ6GX376EWAREVQ3L/bundle.json","state":"https://pith.science/pith/3C6INQHXOVJ6GX376EWAREVQ3L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3C6INQHXOVJ6GX376EWAREVQ3L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3C6INQHXOVJ6GX376EWAREVQ3L","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":"be5999bf3ea68c64c1471ea700105c26169ac38b6a2a1cefda19f1a0e672f1d3","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-07T04:19:49Z","title_canon_sha256":"8d9b3a30d59a6968c919b39bba1a15c5241d05c344ac005f12714cbd9c803368"},"schema_version":"1.0","source":{"id":"2106.03331","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.03331","created_at":"2026-07-05T02:46:48Z"},{"alias_kind":"arxiv_version","alias_value":"2106.03331v1","created_at":"2026-07-05T02:46:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03331","created_at":"2026-07-05T02:46:48Z"},{"alias_kind":"pith_short_12","alias_value":"3C6INQHXOVJ6","created_at":"2026-07-05T02:46:48Z"},{"alias_kind":"pith_short_16","alias_value":"3C6INQHXOVJ6GX37","created_at":"2026-07-05T02:46:48Z"},{"alias_kind":"pith_short_8","alias_value":"3C6INQHX","created_at":"2026-07-05T02:46:48Z"}],"graph_snapshots":[{"event_id":"sha256:81e259efb6139f03fc605f0f404099db1c4181fdc773740d0f205b88698d7017","target":"graph","created_at":"2026-07-05T02:46:48Z","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/2106.03331/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose SelfDoc, a task-agnostic pre-training framework for document image understanding. Because documents are multimodal and are intended for sequential reading, our framework exploits the positional, textual, and visual information of every semantically meaningful component in a document, and it models the contextualization between each block of content. Unlike existing document pre-training models, our model is coarse-grained instead of treating individual words as input, therefore avoiding an overly fine-grained with excessive contextualization. Beyond that, we introduce cross-modal le","authors_text":"Handong Zhao, Hongfu Liu, Jason Kuen, Jiuxiang Gu, Peizhao Li, Rajiv Jain, Varun Manjunatha, Vlad I. Morariu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-07T04:19:49Z","title":"SelfDoc: Self-Supervised Document Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03331","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:dd2ac0061b5422421f193e72246f8e017fd5762cf47440b19fb9401c86fac0f2","target":"record","created_at":"2026-07-05T02:46:48Z","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":"be5999bf3ea68c64c1471ea700105c26169ac38b6a2a1cefda19f1a0e672f1d3","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-07T04:19:49Z","title_canon_sha256":"8d9b3a30d59a6968c919b39bba1a15c5241d05c344ac005f12714cbd9c803368"},"schema_version":"1.0","source":{"id":"2106.03331","kind":"arxiv","version":1}},"canonical_sha256":"d8bc86c0f77553e35f7ff12c0892b0dafb8d0795b75f16113d41cce6ea85d6e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8bc86c0f77553e35f7ff12c0892b0dafb8d0795b75f16113d41cce6ea85d6e0","first_computed_at":"2026-07-05T02:46:48.569462Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:46:48.569462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+pARKsjByhQpr4j8XKAXYVFwFXdhrGWKm1OhZDw+PhYVmFLqzp8D3+egLDmQgRZfhCsVGnhYpWATI+vY6RqQAg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:46:48.569974Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.03331","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd2ac0061b5422421f193e72246f8e017fd5762cf47440b19fb9401c86fac0f2","sha256:81e259efb6139f03fc605f0f404099db1c4181fdc773740d0f205b88698d7017"],"state_sha256":"77de88cc0ca88fdd426d684a21123b07fb35b58d2a60bb172b79c9c114dff7f9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j0OB+xHKMguWumvLvBT3wnTmcSs1Zey+fSWNnlvmOSS+t+ew9gi9R8Fdbkipp+Q54d2wEVU2cqaba789Tam/Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T19:59:57.777250Z","bundle_sha256":"b6927fbcec8caf846889190322bac66b1f3c701891353b2a54785435ac1796e4"}}