{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VK2E3OJRCH2XL34LMIKUTA36NV","short_pith_number":"pith:VK2E3OJR","canonical_record":{"source":{"id":"2302.05658","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-11T11:32:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5a7a131084a3d7342dbaa95a315e228852c72833426983d12819c74b547488da","abstract_canon_sha256":"ea4613b629a2c39341f0e02ecaa5f972f25cc41243cfc789b32cca21f7ea3d62"},"schema_version":"1.0"},"canonical_sha256":"aab44db93111f575ef8b621549837e6d5d1c8ffbfa039b32cf04723497977652","source":{"kind":"arxiv","id":"2302.05658","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.05658","created_at":"2026-07-05T06:06:43Z"},{"alias_kind":"arxiv_version","alias_value":"2302.05658v2","created_at":"2026-07-05T06:06:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05658","created_at":"2026-07-05T06:06:43Z"},{"alias_kind":"pith_short_12","alias_value":"VK2E3OJRCH2X","created_at":"2026-07-05T06:06:43Z"},{"alias_kind":"pith_short_16","alias_value":"VK2E3OJRCH2XL34L","created_at":"2026-07-05T06:06:43Z"},{"alias_kind":"pith_short_8","alias_value":"VK2E3OJR","created_at":"2026-07-05T06:06:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VK2E3OJRCH2XL34LMIKUTA36NV","target":"record","payload":{"canonical_record":{"source":{"id":"2302.05658","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-11T11:32:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5a7a131084a3d7342dbaa95a315e228852c72833426983d12819c74b547488da","abstract_canon_sha256":"ea4613b629a2c39341f0e02ecaa5f972f25cc41243cfc789b32cca21f7ea3d62"},"schema_version":"1.0"},"canonical_sha256":"aab44db93111f575ef8b621549837e6d5d1c8ffbfa039b32cf04723497977652","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:06:43.215900Z","signature_b64":"VjxQF0kgU00uVnNSxS3t9Z1pzN/d0Uw6Y8crWv8leVHcFPQhBtg0hhLy/BJVyFs/B0kolycwPS/+jSoPB4iBCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aab44db93111f575ef8b621549837e6d5d1c8ffbfa039b32cf04723497977652","last_reissued_at":"2026-07-05T06:06:43.215551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:06:43.215551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.05658","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":"2026-07-05T06:06:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gqnN+a/qcnIW0GincsF9Lv8p109bmriQIUjMeDJobeB19kvrcbAzaPU2QLqOM5XyXDAF0V/1v5A+KVUiMchiCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:00:30.405920Z"},"content_sha256":"abca042aa62aebc3ca60b14443afe0f006c43fb174c687ca913939fc055bd28d","schema_version":"1.0","event_id":"sha256:abca042aa62aebc3ca60b14443afe0f006c43fb174c687ca913939fc055bd28d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VK2E3OJRCH2XL34LMIKUTA36NV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DocILE Benchmark for Document Information Localization and Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ahmed Hamdi, Antoine Doucet, Dimosthenis Karatzas, Ji\\v{r}\\'i Matas, Mat\\v{e}j Koci\\'an, Maty\\'a\\v{s} Skalick\\'y, Michal U\\v{r}i\\v{c}\\'a\\v{r}, Micka\\\"el Coustaty, Milan \\v{S}ulc, \\v{S}t\\v{e}p\\'an \\v{S}imsa, Yash Patel","submitted_at":"2023-02-11T11:32:10Z","abstract_excerpt":"This paper introduces the DocILE benchmark with the largest dataset of business documents for the tasks of Key Information Localization and Extraction and Line Item Recognition. It contains 6.7k annotated business documents, 100k synthetically generated documents, and nearly~1M unlabeled documents for unsupervised pre-training. The dataset has been built with knowledge of domain- and task-specific aspects, resulting in the following key features: (i) annotations in 55 classes, which surpasses the granularity of previously published key information extraction datasets by a large margin; (ii) Li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05658","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/2302.05658/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":"2026-07-05T06:06:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2RwtQ+GLFuj6BXnTAayG94u8+Sa/kTGzJ9+hfdXGqT2DlqoCHHHZO0qZYnfahaoqUGVTP3sqmBI0jPbi+2iIBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:00:30.406659Z"},"content_sha256":"937b12a0203bb02a77c869b1ff408954854a33eb949d2d20a28fe4f2cd8f1724","schema_version":"1.0","event_id":"sha256:937b12a0203bb02a77c869b1ff408954854a33eb949d2d20a28fe4f2cd8f1724"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VK2E3OJRCH2XL34LMIKUTA36NV/bundle.json","state_url":"https://pith.science/pith/VK2E3OJRCH2XL34LMIKUTA36NV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VK2E3OJRCH2XL34LMIKUTA36NV/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":"2026-08-19T23:00:30Z","links":{"resolver":"https://pith.science/pith/VK2E3OJRCH2XL34LMIKUTA36NV","bundle":"https://pith.science/pith/VK2E3OJRCH2XL34LMIKUTA36NV/bundle.json","state":"https://pith.science/pith/VK2E3OJRCH2XL34LMIKUTA36NV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VK2E3OJRCH2XL34LMIKUTA36NV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VK2E3OJRCH2XL34LMIKUTA36NV","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":"ea4613b629a2c39341f0e02ecaa5f972f25cc41243cfc789b32cca21f7ea3d62","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-11T11:32:10Z","title_canon_sha256":"5a7a131084a3d7342dbaa95a315e228852c72833426983d12819c74b547488da"},"schema_version":"1.0","source":{"id":"2302.05658","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.05658","created_at":"2026-07-05T06:06:43Z"},{"alias_kind":"arxiv_version","alias_value":"2302.05658v2","created_at":"2026-07-05T06:06:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05658","created_at":"2026-07-05T06:06:43Z"},{"alias_kind":"pith_short_12","alias_value":"VK2E3OJRCH2X","created_at":"2026-07-05T06:06:43Z"},{"alias_kind":"pith_short_16","alias_value":"VK2E3OJRCH2XL34L","created_at":"2026-07-05T06:06:43Z"},{"alias_kind":"pith_short_8","alias_value":"VK2E3OJR","created_at":"2026-07-05T06:06:43Z"}],"graph_snapshots":[{"event_id":"sha256:937b12a0203bb02a77c869b1ff408954854a33eb949d2d20a28fe4f2cd8f1724","target":"graph","created_at":"2026-07-05T06:06:43Z","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/2302.05658/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces the DocILE benchmark with the largest dataset of business documents for the tasks of Key Information Localization and Extraction and Line Item Recognition. It contains 6.7k annotated business documents, 100k synthetically generated documents, and nearly~1M unlabeled documents for unsupervised pre-training. The dataset has been built with knowledge of domain- and task-specific aspects, resulting in the following key features: (i) annotations in 55 classes, which surpasses the granularity of previously published key information extraction datasets by a large margin; (ii) Li","authors_text":"Ahmed Hamdi, Antoine Doucet, Dimosthenis Karatzas, Ji\\v{r}\\'i Matas, Mat\\v{e}j Koci\\'an, Maty\\'a\\v{s} Skalick\\'y, Michal U\\v{r}i\\v{c}\\'a\\v{r}, Micka\\\"el Coustaty, Milan \\v{S}ulc, \\v{S}t\\v{e}p\\'an \\v{S}imsa, Yash Patel","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-11T11:32:10Z","title":"DocILE Benchmark for Document Information Localization and Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05658","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:abca042aa62aebc3ca60b14443afe0f006c43fb174c687ca913939fc055bd28d","target":"record","created_at":"2026-07-05T06:06:43Z","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":"ea4613b629a2c39341f0e02ecaa5f972f25cc41243cfc789b32cca21f7ea3d62","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-11T11:32:10Z","title_canon_sha256":"5a7a131084a3d7342dbaa95a315e228852c72833426983d12819c74b547488da"},"schema_version":"1.0","source":{"id":"2302.05658","kind":"arxiv","version":2}},"canonical_sha256":"aab44db93111f575ef8b621549837e6d5d1c8ffbfa039b32cf04723497977652","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aab44db93111f575ef8b621549837e6d5d1c8ffbfa039b32cf04723497977652","first_computed_at":"2026-07-05T06:06:43.215551Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:06:43.215551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VjxQF0kgU00uVnNSxS3t9Z1pzN/d0Uw6Y8crWv8leVHcFPQhBtg0hhLy/BJVyFs/B0kolycwPS/+jSoPB4iBCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:06:43.215900Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.05658","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:abca042aa62aebc3ca60b14443afe0f006c43fb174c687ca913939fc055bd28d","sha256:937b12a0203bb02a77c869b1ff408954854a33eb949d2d20a28fe4f2cd8f1724"],"state_sha256":"7c37af38265f9d444b79ea8b58c7dd80065ea630acbb8d06d017192fd876fc94"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KXX5NwYpnlIEg7MRn7K9hjVq5iMDLXCXsSl/0z/dAL2+TAOncCvvADNLyhfJnUlYz70u68by467FOWp+YZnACA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T23:00:30.413558Z","bundle_sha256":"8b5b101b4fe3bf6531f7d9ee3f6fd3cf68819f0cc6dac9890e6105562e2ba79a"}}