{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IZR45QEIBM35XBGLYMTM5HGYEJ","short_pith_number":"pith:IZR45QEI","canonical_record":{"source":{"id":"2305.08719","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-15T15:29:06Z","cross_cats_sorted":[],"title_canon_sha256":"57a87b7fe4324b9f462a23df426466025582dbcbd44f4ce2a9dc8f4bd5591b4e","abstract_canon_sha256":"7ebbd3a6e91c0668c147c436cf37ab85a66c45d025269c30a241069cf6923d75"},"schema_version":"1.0"},"canonical_sha256":"4663cec0880b37db84cbc326ce9cd8226dc43e7b538aba7bebbb35266ba38b55","source":{"kind":"arxiv","id":"2305.08719","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.08719","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"arxiv_version","alias_value":"2305.08719v2","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08719","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"pith_short_12","alias_value":"IZR45QEIBM35","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"pith_short_16","alias_value":"IZR45QEIBM35XBGL","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"pith_short_8","alias_value":"IZR45QEI","created_at":"2026-07-05T06:12:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IZR45QEIBM35XBGLYMTM5HGYEJ","target":"record","payload":{"canonical_record":{"source":{"id":"2305.08719","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-15T15:29:06Z","cross_cats_sorted":[],"title_canon_sha256":"57a87b7fe4324b9f462a23df426466025582dbcbd44f4ce2a9dc8f4bd5591b4e","abstract_canon_sha256":"7ebbd3a6e91c0668c147c436cf37ab85a66c45d025269c30a241069cf6923d75"},"schema_version":"1.0"},"canonical_sha256":"4663cec0880b37db84cbc326ce9cd8226dc43e7b538aba7bebbb35266ba38b55","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:02.931628Z","signature_b64":"pN8J0rMuHTcVgZ33JqGfiP6MDEr7PHz74UqR0HLdMh8vSJRgd5eJmkRvQzrWkoz120J2G0XwV7Dw1bGn/Bl9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4663cec0880b37db84cbc326ce9cd8226dc43e7b538aba7bebbb35266ba38b55","last_reissued_at":"2026-07-05T06:12:02.931282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:02.931282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.08719","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:12:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pErhjAJoBtmz0NU1ri4uyssMakbEGa63KHbfhL4wcrgXkedrgHesuiI0/0TkEmJV2rO5QwLC/iPED3BX5LnoDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:49:28.187683Z"},"content_sha256":"bbfcd917d9b616b82e28b5e80ebe2ec10bb3ad192a111f6a42ea396eb0f10ab4","schema_version":"1.0","event_id":"sha256:bbfcd917d9b616b82e28b5e80ebe2ec10bb3ad192a111f6a42ea396eb0f10ab4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IZR45QEIBM35XBGLYMTM5HGYEJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"M$^{6}$Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hiuyi Cheng, Jiaxin Zhang, Jing Li, Kai Ding, Lianwen Jin, Peirong Zhang, Qiyuan Zhu, Sihang Wu, Zecheng Xie","submitted_at":"2023-05-15T15:29:06Z","abstract_excerpt":"Document layout analysis is a crucial prerequisite for document understanding, including document retrieval and conversion. Most public datasets currently contain only PDF documents and lack realistic documents. Models trained on these datasets may not generalize well to real-world scenarios. Therefore, this paper introduces a large and diverse document layout analysis dataset called $M^{6}Doc$. The $M^6$ designation represents six properties: (1) Multi-Format (including scanned, photographed, and PDF documents); (2) Multi-Type (such as scientific articles, textbooks, books, test papers, magaz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08719","kind":"arxiv","version":2},"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/2305.08719/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":"2026-07-05T06:12:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1SbhkKrOLhHwxJSJDdqt/i7PUVqjI/U721KwmT2yEbm1I5wGeJYnpwECDT0zqoHu4RWdzVnQCQwKh2qxIBFIAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:49:28.188178Z"},"content_sha256":"7870098ab41cdb173d8af5205c4b896b93cec14ba3fd9a74207b61e86a9decb5","schema_version":"1.0","event_id":"sha256:7870098ab41cdb173d8af5205c4b896b93cec14ba3fd9a74207b61e86a9decb5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IZR45QEIBM35XBGLYMTM5HGYEJ/bundle.json","state_url":"https://pith.science/pith/IZR45QEIBM35XBGLYMTM5HGYEJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IZR45QEIBM35XBGLYMTM5HGYEJ/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":"2026-08-07T05:49:28Z","links":{"resolver":"https://pith.science/pith/IZR45QEIBM35XBGLYMTM5HGYEJ","bundle":"https://pith.science/pith/IZR45QEIBM35XBGLYMTM5HGYEJ/bundle.json","state":"https://pith.science/pith/IZR45QEIBM35XBGLYMTM5HGYEJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IZR45QEIBM35XBGLYMTM5HGYEJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IZR45QEIBM35XBGLYMTM5HGYEJ","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":"7ebbd3a6e91c0668c147c436cf37ab85a66c45d025269c30a241069cf6923d75","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-15T15:29:06Z","title_canon_sha256":"57a87b7fe4324b9f462a23df426466025582dbcbd44f4ce2a9dc8f4bd5591b4e"},"schema_version":"1.0","source":{"id":"2305.08719","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.08719","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"arxiv_version","alias_value":"2305.08719v2","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08719","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"pith_short_12","alias_value":"IZR45QEIBM35","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"pith_short_16","alias_value":"IZR45QEIBM35XBGL","created_at":"2026-07-05T06:12:02Z"},{"alias_kind":"pith_short_8","alias_value":"IZR45QEI","created_at":"2026-07-05T06:12:02Z"}],"graph_snapshots":[{"event_id":"sha256:7870098ab41cdb173d8af5205c4b896b93cec14ba3fd9a74207b61e86a9decb5","target":"graph","created_at":"2026-07-05T06:12:02Z","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/2305.08719/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Document layout analysis is a crucial prerequisite for document understanding, including document retrieval and conversion. Most public datasets currently contain only PDF documents and lack realistic documents. Models trained on these datasets may not generalize well to real-world scenarios. Therefore, this paper introduces a large and diverse document layout analysis dataset called $M^{6}Doc$. The $M^6$ designation represents six properties: (1) Multi-Format (including scanned, photographed, and PDF documents); (2) Multi-Type (such as scientific articles, textbooks, books, test papers, magaz","authors_text":"Hiuyi Cheng, Jiaxin Zhang, Jing Li, Kai Ding, Lianwen Jin, Peirong Zhang, Qiyuan Zhu, Sihang Wu, Zecheng Xie","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-15T15:29:06Z","title":"M$^{6}$Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08719","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:bbfcd917d9b616b82e28b5e80ebe2ec10bb3ad192a111f6a42ea396eb0f10ab4","target":"record","created_at":"2026-07-05T06:12:02Z","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":"7ebbd3a6e91c0668c147c436cf37ab85a66c45d025269c30a241069cf6923d75","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-15T15:29:06Z","title_canon_sha256":"57a87b7fe4324b9f462a23df426466025582dbcbd44f4ce2a9dc8f4bd5591b4e"},"schema_version":"1.0","source":{"id":"2305.08719","kind":"arxiv","version":2}},"canonical_sha256":"4663cec0880b37db84cbc326ce9cd8226dc43e7b538aba7bebbb35266ba38b55","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4663cec0880b37db84cbc326ce9cd8226dc43e7b538aba7bebbb35266ba38b55","first_computed_at":"2026-07-05T06:12:02.931282Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:02.931282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pN8J0rMuHTcVgZ33JqGfiP6MDEr7PHz74UqR0HLdMh8vSJRgd5eJmkRvQzrWkoz120J2G0XwV7Dw1bGn/Bl9Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:02.931628Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.08719","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbfcd917d9b616b82e28b5e80ebe2ec10bb3ad192a111f6a42ea396eb0f10ab4","sha256:7870098ab41cdb173d8af5205c4b896b93cec14ba3fd9a74207b61e86a9decb5"],"state_sha256":"ec31eeebc719ecb4e19c510b9b2621a32fff423dfb2f00a716abf374f9b3cea7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9yxWG8Iwb4osZDkxdOtmp5r+QYsH+TlBSsoS49xQ6qDP/fsZScCg/kKS3c2NBje8lFVG3g+60sInw0pSqjw7Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T05:49:28.192281Z","bundle_sha256":"b34ce70bb794386653861eb62b71e3600cb00fe30bdd35ec7ae6086642134894"}}