{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:Q6EKSC5GFHXRLVVFQMM7EKSKIR","short_pith_number":"pith:Q6EKSC5G","canonical_record":{"source":{"id":"2210.02849","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-06T12:07:18Z","cross_cats_sorted":[],"title_canon_sha256":"a6c9c834cb611a0cccd613e1fbf3e22427289dd35e93b98c69c5d6e65da260ea","abstract_canon_sha256":"18cd0d556e10713410445e3a7ef7c79e4809571a4a54bf8bcc46e12feaf78fd5"},"schema_version":"1.0"},"canonical_sha256":"8788a90ba629ef15d6a58319f22a4a444df178cb31e67c333617d4ff59bd7b33","source":{"kind":"arxiv","id":"2210.02849","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.02849","created_at":"2026-07-05T05:04:04Z"},{"alias_kind":"arxiv_version","alias_value":"2210.02849v1","created_at":"2026-07-05T05:04:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02849","created_at":"2026-07-05T05:04:04Z"},{"alias_kind":"pith_short_12","alias_value":"Q6EKSC5GFHXR","created_at":"2026-07-05T05:04:04Z"},{"alias_kind":"pith_short_16","alias_value":"Q6EKSC5GFHXRLVVF","created_at":"2026-07-05T05:04:04Z"},{"alias_kind":"pith_short_8","alias_value":"Q6EKSC5G","created_at":"2026-07-05T05:04:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:Q6EKSC5GFHXRLVVFQMM7EKSKIR","target":"record","payload":{"canonical_record":{"source":{"id":"2210.02849","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-06T12:07:18Z","cross_cats_sorted":[],"title_canon_sha256":"a6c9c834cb611a0cccd613e1fbf3e22427289dd35e93b98c69c5d6e65da260ea","abstract_canon_sha256":"18cd0d556e10713410445e3a7ef7c79e4809571a4a54bf8bcc46e12feaf78fd5"},"schema_version":"1.0"},"canonical_sha256":"8788a90ba629ef15d6a58319f22a4a444df178cb31e67c333617d4ff59bd7b33","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:04.598289Z","signature_b64":"rHdNLMQXGW2USValtJA69p/PBubPo5jPCfc+7wz8osaeeUEK6xGZd8794VetxIuQP1BqMRXTdiPIm041MnmXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8788a90ba629ef15d6a58319f22a4a444df178cb31e67c333617d4ff59bd7b33","last_reissued_at":"2026-07-05T05:04:04.597898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:04.597898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.02849","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":"2026-07-05T05:04:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wjxh6GU+F3kJ+LdiNC/ARr2a+kOpAZrXV5GIlJ5yZho79CXDTkw2AXFfy3mms4Jr/0w2g6gHwIxUpwlKsH59DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:43:48.399276Z"},"content_sha256":"6036a84ae93fa5e98c58bef3cdbe6c1f0ba647be9ed0469d9a09010d55988306","schema_version":"1.0","event_id":"sha256:6036a84ae93fa5e98c58bef3cdbe6c1f0ba647be9ed0469d9a09010d55988306"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:Q6EKSC5GFHXRLVVFQMM7EKSKIR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"XDoc: Unified Pre-training for Cross-Format Document Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cha Zhang, Furu Wei, Jingye Chen, Lei Cui, Tengchao Lv","submitted_at":"2022-10-06T12:07:18Z","abstract_excerpt":"The surge of pre-training has witnessed the rapid development of document understanding recently. Pre-training and fine-tuning framework has been effectively used to tackle texts in various formats, including plain texts, document texts, and web texts. Despite achieving promising performance, existing pre-trained models usually target one specific document format at one time, making it difficult to combine knowledge from multiple document formats. To address this, we propose XDoc, a unified pre-trained model which deals with different document formats in a single model. For parameter efficienc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02849","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/2210.02849/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":"2026-07-05T05:04:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"++NetN17HuZhyxxPLxuyRlQQ94K6zgvTSasN8Y5IS5vcW3rSbbePpRYIlp/PSNr5cfAcXuFFIPyMZATN4H56Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:43:48.399802Z"},"content_sha256":"8f8681a59303597d8e3f4a85941677b58315d3aaf46b7a32ce1d64f6386f16a9","schema_version":"1.0","event_id":"sha256:8f8681a59303597d8e3f4a85941677b58315d3aaf46b7a32ce1d64f6386f16a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q6EKSC5GFHXRLVVFQMM7EKSKIR/bundle.json","state_url":"https://pith.science/pith/Q6EKSC5GFHXRLVVFQMM7EKSKIR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q6EKSC5GFHXRLVVFQMM7EKSKIR/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":"2026-08-16T22:43:48Z","links":{"resolver":"https://pith.science/pith/Q6EKSC5GFHXRLVVFQMM7EKSKIR","bundle":"https://pith.science/pith/Q6EKSC5GFHXRLVVFQMM7EKSKIR/bundle.json","state":"https://pith.science/pith/Q6EKSC5GFHXRLVVFQMM7EKSKIR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q6EKSC5GFHXRLVVFQMM7EKSKIR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:Q6EKSC5GFHXRLVVFQMM7EKSKIR","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":"18cd0d556e10713410445e3a7ef7c79e4809571a4a54bf8bcc46e12feaf78fd5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-06T12:07:18Z","title_canon_sha256":"a6c9c834cb611a0cccd613e1fbf3e22427289dd35e93b98c69c5d6e65da260ea"},"schema_version":"1.0","source":{"id":"2210.02849","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.02849","created_at":"2026-07-05T05:04:04Z"},{"alias_kind":"arxiv_version","alias_value":"2210.02849v1","created_at":"2026-07-05T05:04:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02849","created_at":"2026-07-05T05:04:04Z"},{"alias_kind":"pith_short_12","alias_value":"Q6EKSC5GFHXR","created_at":"2026-07-05T05:04:04Z"},{"alias_kind":"pith_short_16","alias_value":"Q6EKSC5GFHXRLVVF","created_at":"2026-07-05T05:04:04Z"},{"alias_kind":"pith_short_8","alias_value":"Q6EKSC5G","created_at":"2026-07-05T05:04:04Z"}],"graph_snapshots":[{"event_id":"sha256:8f8681a59303597d8e3f4a85941677b58315d3aaf46b7a32ce1d64f6386f16a9","target":"graph","created_at":"2026-07-05T05:04:04Z","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/2210.02849/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The surge of pre-training has witnessed the rapid development of document understanding recently. Pre-training and fine-tuning framework has been effectively used to tackle texts in various formats, including plain texts, document texts, and web texts. Despite achieving promising performance, existing pre-trained models usually target one specific document format at one time, making it difficult to combine knowledge from multiple document formats. To address this, we propose XDoc, a unified pre-trained model which deals with different document formats in a single model. For parameter efficienc","authors_text":"Cha Zhang, Furu Wei, Jingye Chen, Lei Cui, Tengchao Lv","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-06T12:07:18Z","title":"XDoc: Unified Pre-training for Cross-Format Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02849","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":"sha256:6036a84ae93fa5e98c58bef3cdbe6c1f0ba647be9ed0469d9a09010d55988306","target":"record","created_at":"2026-07-05T05:04:04Z","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":"18cd0d556e10713410445e3a7ef7c79e4809571a4a54bf8bcc46e12feaf78fd5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-06T12:07:18Z","title_canon_sha256":"a6c9c834cb611a0cccd613e1fbf3e22427289dd35e93b98c69c5d6e65da260ea"},"schema_version":"1.0","source":{"id":"2210.02849","kind":"arxiv","version":1}},"canonical_sha256":"8788a90ba629ef15d6a58319f22a4a444df178cb31e67c333617d4ff59bd7b33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8788a90ba629ef15d6a58319f22a4a444df178cb31e67c333617d4ff59bd7b33","first_computed_at":"2026-07-05T05:04:04.597898Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:04:04.597898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rHdNLMQXGW2USValtJA69p/PBubPo5jPCfc+7wz8osaeeUEK6xGZd8794VetxIuQP1BqMRXTdiPIm041MnmXAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:04:04.598289Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.02849","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6036a84ae93fa5e98c58bef3cdbe6c1f0ba647be9ed0469d9a09010d55988306","sha256:8f8681a59303597d8e3f4a85941677b58315d3aaf46b7a32ce1d64f6386f16a9"],"state_sha256":"4c70a88e64aefc17de55e49756998bb970d172b317a57c79208c67962786da51"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0EDcEbt2qjSVX6XfMqgLMnUYZyM5mS0UMDyNbi8qn7kpoUEMeTEPfcguS7icMhgWC5t09zYY7BxXT6r5f+yuDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T22:43:48.404613Z","bundle_sha256":"39acd3836f893d9f370c03c57c7627f2ac9aadea982b8880b43a1142c3b833c9"}}