{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:K2BIASC7R3XXEVUX45SDRUPYFH","short_pith_number":"pith:K2BIASC7","canonical_record":{"source":{"id":"2411.10068","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T09:33:13Z","cross_cats_sorted":[],"title_canon_sha256":"77408b469af53a757f681f448c57b5e06681b0aa66183915ff5005b0f0f0adec","abstract_canon_sha256":"257e18b9003ddf1e581ca3ba3e38ce640b9703ce96092528e1e4f74ccd3839b3"},"schema_version":"1.0"},"canonical_sha256":"568280485f8eef725697e76438d1f829dca4c3a0f31e36a8bffc078ceacd3b57","source":{"kind":"arxiv","id":"2411.10068","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10068","created_at":"2026-07-05T09:35:58Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10068v1","created_at":"2026-07-05T09:35:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10068","created_at":"2026-07-05T09:35:58Z"},{"alias_kind":"pith_short_12","alias_value":"K2BIASC7R3XX","created_at":"2026-07-05T09:35:58Z"},{"alias_kind":"pith_short_16","alias_value":"K2BIASC7R3XXEVUX","created_at":"2026-07-05T09:35:58Z"},{"alias_kind":"pith_short_8","alias_value":"K2BIASC7","created_at":"2026-07-05T09:35:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:K2BIASC7R3XXEVUX45SDRUPYFH","target":"record","payload":{"canonical_record":{"source":{"id":"2411.10068","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T09:33:13Z","cross_cats_sorted":[],"title_canon_sha256":"77408b469af53a757f681f448c57b5e06681b0aa66183915ff5005b0f0f0adec","abstract_canon_sha256":"257e18b9003ddf1e581ca3ba3e38ce640b9703ce96092528e1e4f74ccd3839b3"},"schema_version":"1.0"},"canonical_sha256":"568280485f8eef725697e76438d1f829dca4c3a0f31e36a8bffc078ceacd3b57","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:58.315897Z","signature_b64":"NtOFDCj+m+cmkng/7vXtB/RS8gLonQGdJVna5jXbdJyIyFcBkMNHYUi11y4MEMdYGxuGKwAkalpOKNBiKZyMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"568280485f8eef725697e76438d1f829dca4c3a0f31e36a8bffc078ceacd3b57","last_reissued_at":"2026-07-05T09:35:58.315282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:58.315282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.10068","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":"2026-07-05T09:35:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hqtph8rFAS9+5usNVwWLi9rE170RKV/SY+zTlu47O6DPnITqNDXWjlaETWCb9vfICS76nJ5r89DZoMS5vROrDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:57:32.649001Z"},"content_sha256":"9a52eb24d3236f4ad66295adca0c31f9fd5d7e40e3a5f8344fa1efe558582f62","schema_version":"1.0","event_id":"sha256:9a52eb24d3236f4ad66295adca0c31f9fd5d7e40e3a5f8344fa1efe558582f62"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:K2BIASC7R3XXEVUX45SDRUPYFH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diachronic Document Dataset for Semantic Layout Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Beno\\^it Sagot, DCIS), Florian Cafiero (PSL), Hugo Scheithauer, Juliette Janes (ALMAnaCH), Laurent Romary (ALMAnaCH, Sarah B\\'eni\\`ere (ALMAnaCH), Simon Gabay, Thibault Cl\\'erice (ALMAnaCH)","submitted_at":"2024-11-15T09:33:13Z","abstract_excerpt":"We present a novel, open-access dataset designed for semantic layout analysis, built to support document recreation workflows through mapping with the Text Encoding Initiative (TEI) standard. This dataset includes 7,254 annotated pages spanning a large temporal range (1600-2024) of digitised and born-digital materials across diverse document types (magazines, papers from sciences and humanities, PhD theses, monographs, plays, administrative reports, etc.) sorted into modular subsets. By incorporating content from different periods and genres, it addresses varying layout complexities and histor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10068","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/2411.10068/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":"2026-07-05T09:35:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SxSBaHhMBssBV1xUAE0NqY4DcYH5xuIqDE2Gu8wKnPj6VdTrhNGu5DVIc9XhyHgNKYrBrGNm+ABJ5RsIraUDCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:57:32.649580Z"},"content_sha256":"2027c9b24d78b69280dedc16739c5560ac1c2e2c92d10501b8f1c8f1b0501056","schema_version":"1.0","event_id":"sha256:2027c9b24d78b69280dedc16739c5560ac1c2e2c92d10501b8f1c8f1b0501056"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K2BIASC7R3XXEVUX45SDRUPYFH/bundle.json","state_url":"https://pith.science/pith/K2BIASC7R3XXEVUX45SDRUPYFH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K2BIASC7R3XXEVUX45SDRUPYFH/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":"2026-08-08T16:57:32Z","links":{"resolver":"https://pith.science/pith/K2BIASC7R3XXEVUX45SDRUPYFH","bundle":"https://pith.science/pith/K2BIASC7R3XXEVUX45SDRUPYFH/bundle.json","state":"https://pith.science/pith/K2BIASC7R3XXEVUX45SDRUPYFH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K2BIASC7R3XXEVUX45SDRUPYFH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:K2BIASC7R3XXEVUX45SDRUPYFH","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":"257e18b9003ddf1e581ca3ba3e38ce640b9703ce96092528e1e4f74ccd3839b3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T09:33:13Z","title_canon_sha256":"77408b469af53a757f681f448c57b5e06681b0aa66183915ff5005b0f0f0adec"},"schema_version":"1.0","source":{"id":"2411.10068","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10068","created_at":"2026-07-05T09:35:58Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10068v1","created_at":"2026-07-05T09:35:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10068","created_at":"2026-07-05T09:35:58Z"},{"alias_kind":"pith_short_12","alias_value":"K2BIASC7R3XX","created_at":"2026-07-05T09:35:58Z"},{"alias_kind":"pith_short_16","alias_value":"K2BIASC7R3XXEVUX","created_at":"2026-07-05T09:35:58Z"},{"alias_kind":"pith_short_8","alias_value":"K2BIASC7","created_at":"2026-07-05T09:35:58Z"}],"graph_snapshots":[{"event_id":"sha256:2027c9b24d78b69280dedc16739c5560ac1c2e2c92d10501b8f1c8f1b0501056","target":"graph","created_at":"2026-07-05T09:35:58Z","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/2411.10068/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a novel, open-access dataset designed for semantic layout analysis, built to support document recreation workflows through mapping with the Text Encoding Initiative (TEI) standard. This dataset includes 7,254 annotated pages spanning a large temporal range (1600-2024) of digitised and born-digital materials across diverse document types (magazines, papers from sciences and humanities, PhD theses, monographs, plays, administrative reports, etc.) sorted into modular subsets. By incorporating content from different periods and genres, it addresses varying layout complexities and histor","authors_text":"Beno\\^it Sagot, DCIS), Florian Cafiero (PSL), Hugo Scheithauer, Juliette Janes (ALMAnaCH), Laurent Romary (ALMAnaCH, Sarah B\\'eni\\`ere (ALMAnaCH), Simon Gabay, Thibault Cl\\'erice (ALMAnaCH)","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T09:33:13Z","title":"Diachronic Document Dataset for Semantic Layout Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10068","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":"sha256:9a52eb24d3236f4ad66295adca0c31f9fd5d7e40e3a5f8344fa1efe558582f62","target":"record","created_at":"2026-07-05T09:35:58Z","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":"257e18b9003ddf1e581ca3ba3e38ce640b9703ce96092528e1e4f74ccd3839b3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T09:33:13Z","title_canon_sha256":"77408b469af53a757f681f448c57b5e06681b0aa66183915ff5005b0f0f0adec"},"schema_version":"1.0","source":{"id":"2411.10068","kind":"arxiv","version":1}},"canonical_sha256":"568280485f8eef725697e76438d1f829dca4c3a0f31e36a8bffc078ceacd3b57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"568280485f8eef725697e76438d1f829dca4c3a0f31e36a8bffc078ceacd3b57","first_computed_at":"2026-07-05T09:35:58.315282Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:35:58.315282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NtOFDCj+m+cmkng/7vXtB/RS8gLonQGdJVna5jXbdJyIyFcBkMNHYUi11y4MEMdYGxuGKwAkalpOKNBiKZyMBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:35:58.315897Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.10068","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a52eb24d3236f4ad66295adca0c31f9fd5d7e40e3a5f8344fa1efe558582f62","sha256:2027c9b24d78b69280dedc16739c5560ac1c2e2c92d10501b8f1c8f1b0501056"],"state_sha256":"9f0a9a5c71e5aa7e201f7850cbc0044d186df6406a985e5add49203a42b80cb5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TLXrdGJubn5VtDg68Spcc+FXFtyPr01Z4BtsKEnJ5cS7dIKv72KsWRu9TF6C6mOQUto0ptbjKffS5q5ZPRhQAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:57:32.657666Z","bundle_sha256":"aafeea9ba5c3cd3fcd09361fae9f95c7f3cc50e09d4d2fd7a0150342d5e856a7"}}