{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QR3K53D72MTWXW66P4ABGAUTZ6","short_pith_number":"pith:QR3K53D7","canonical_record":{"source":{"id":"2301.12394","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-29T09:08:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d6c1cda509e76f203d55b1be7557d5ed85c52c844e53c7ec522c21e4dca88214","abstract_canon_sha256":"f112d2332e21dcac98c8a3e7747afd3a8fa698ab2278ebb85eb96619e1b5b274"},"schema_version":"1.0"},"canonical_sha256":"8476aeec7fd3276bdbde7f00130293cf819e55f17999b0728247e0ae09904cfb","source":{"kind":"arxiv","id":"2301.12394","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.12394","created_at":"2026-07-05T05:36:53Z"},{"alias_kind":"arxiv_version","alias_value":"2301.12394v1","created_at":"2026-07-05T05:36:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12394","created_at":"2026-07-05T05:36:53Z"},{"alias_kind":"pith_short_12","alias_value":"QR3K53D72MTW","created_at":"2026-07-05T05:36:53Z"},{"alias_kind":"pith_short_16","alias_value":"QR3K53D72MTWXW66","created_at":"2026-07-05T05:36:53Z"},{"alias_kind":"pith_short_8","alias_value":"QR3K53D7","created_at":"2026-07-05T05:36:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QR3K53D72MTWXW66P4ABGAUTZ6","target":"record","payload":{"canonical_record":{"source":{"id":"2301.12394","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-29T09:08:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d6c1cda509e76f203d55b1be7557d5ed85c52c844e53c7ec522c21e4dca88214","abstract_canon_sha256":"f112d2332e21dcac98c8a3e7747afd3a8fa698ab2278ebb85eb96619e1b5b274"},"schema_version":"1.0"},"canonical_sha256":"8476aeec7fd3276bdbde7f00130293cf819e55f17999b0728247e0ae09904cfb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:53.773340Z","signature_b64":"iZgbvgllN3aySUruamQ3zg1GKwI9UD8VjMkRXpVkDwd0IfZChIWqcOyjEqcqHVNDqZkDZQ+iAwSMRqXGv2x6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8476aeec7fd3276bdbde7f00130293cf819e55f17999b0728247e0ae09904cfb","last_reissued_at":"2026-07-05T05:36:53.772772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:53.772772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.12394","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":"2026-07-05T05:36:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vIiCrdj0cGPjdF1VyBmdLadcHfHTlOWkIfl7CyEePCX9INXbSaEWwcDsml6l30fFhLu+biiuho3idR6EQXMSDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:58:49.072518Z"},"content_sha256":"c1e2d0fd6b37c42a63e63dac715759d1eaeb1d5f8ac18c9b3cebf5ef6da55e71","schema_version":"1.0","event_id":"sha256:c1e2d0fd6b37c42a63e63dac715759d1eaeb1d5f8ac18c9b3cebf5ef6da55e71"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QR3K53D72MTWXW66P4ABGAUTZ6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DocILE 2023 Teaser: Document Information Localization and Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ahmed Hamdi, Maty\\'a\\v{s} Skalick\\'y, Milan \\v{S}ulc, \\v{S}t\\v{e}p\\'an \\v{S}imsa, Yash Patel","submitted_at":"2023-01-29T09:08:58Z","abstract_excerpt":"The lack of data for information extraction (IE) from semi-structured business documents is a real problem for the IE community. Publications relying on large-scale datasets use only proprietary, unpublished data due to the sensitive nature of such documents. Publicly available datasets are mostly small and domain-specific. The absence of a large-scale public dataset or benchmark hinders the reproducibility and cross-evaluation of published methods. The DocILE 2023 competition, hosted as a lab at the CLEF 2023 conference and as an ICDAR 2023 competition, will run the first major benchmark for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12394","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/2301.12394/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":"2026-07-05T05:36:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4bCOrzq1Tp1EQ6e1M0VTELCEz3Bmz9YtKqBuNRXRsWamBFlIiiYbsXs/QrJRb/C/3TOZS37TfM1qaqgbvYMkBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:58:49.073065Z"},"content_sha256":"276ee4e0832661aa480ebc4ff61adbdffa02ff20e3fc97eccaf6eaf022666b59","schema_version":"1.0","event_id":"sha256:276ee4e0832661aa480ebc4ff61adbdffa02ff20e3fc97eccaf6eaf022666b59"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QR3K53D72MTWXW66P4ABGAUTZ6/bundle.json","state_url":"https://pith.science/pith/QR3K53D72MTWXW66P4ABGAUTZ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QR3K53D72MTWXW66P4ABGAUTZ6/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":"2026-08-04T03:58:49Z","links":{"resolver":"https://pith.science/pith/QR3K53D72MTWXW66P4ABGAUTZ6","bundle":"https://pith.science/pith/QR3K53D72MTWXW66P4ABGAUTZ6/bundle.json","state":"https://pith.science/pith/QR3K53D72MTWXW66P4ABGAUTZ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QR3K53D72MTWXW66P4ABGAUTZ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QR3K53D72MTWXW66P4ABGAUTZ6","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":"f112d2332e21dcac98c8a3e7747afd3a8fa698ab2278ebb85eb96619e1b5b274","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-29T09:08:58Z","title_canon_sha256":"d6c1cda509e76f203d55b1be7557d5ed85c52c844e53c7ec522c21e4dca88214"},"schema_version":"1.0","source":{"id":"2301.12394","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.12394","created_at":"2026-07-05T05:36:53Z"},{"alias_kind":"arxiv_version","alias_value":"2301.12394v1","created_at":"2026-07-05T05:36:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12394","created_at":"2026-07-05T05:36:53Z"},{"alias_kind":"pith_short_12","alias_value":"QR3K53D72MTW","created_at":"2026-07-05T05:36:53Z"},{"alias_kind":"pith_short_16","alias_value":"QR3K53D72MTWXW66","created_at":"2026-07-05T05:36:53Z"},{"alias_kind":"pith_short_8","alias_value":"QR3K53D7","created_at":"2026-07-05T05:36:53Z"}],"graph_snapshots":[{"event_id":"sha256:276ee4e0832661aa480ebc4ff61adbdffa02ff20e3fc97eccaf6eaf022666b59","target":"graph","created_at":"2026-07-05T05:36:53Z","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/2301.12394/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The lack of data for information extraction (IE) from semi-structured business documents is a real problem for the IE community. Publications relying on large-scale datasets use only proprietary, unpublished data due to the sensitive nature of such documents. Publicly available datasets are mostly small and domain-specific. The absence of a large-scale public dataset or benchmark hinders the reproducibility and cross-evaluation of published methods. The DocILE 2023 competition, hosted as a lab at the CLEF 2023 conference and as an ICDAR 2023 competition, will run the first major benchmark for ","authors_text":"Ahmed Hamdi, Maty\\'a\\v{s} Skalick\\'y, Milan \\v{S}ulc, \\v{S}t\\v{e}p\\'an \\v{S}imsa, Yash Patel","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-29T09:08:58Z","title":"DocILE 2023 Teaser: Document Information Localization and Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12394","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:c1e2d0fd6b37c42a63e63dac715759d1eaeb1d5f8ac18c9b3cebf5ef6da55e71","target":"record","created_at":"2026-07-05T05:36:53Z","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":"f112d2332e21dcac98c8a3e7747afd3a8fa698ab2278ebb85eb96619e1b5b274","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-29T09:08:58Z","title_canon_sha256":"d6c1cda509e76f203d55b1be7557d5ed85c52c844e53c7ec522c21e4dca88214"},"schema_version":"1.0","source":{"id":"2301.12394","kind":"arxiv","version":1}},"canonical_sha256":"8476aeec7fd3276bdbde7f00130293cf819e55f17999b0728247e0ae09904cfb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8476aeec7fd3276bdbde7f00130293cf819e55f17999b0728247e0ae09904cfb","first_computed_at":"2026-07-05T05:36:53.772772Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:36:53.772772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iZgbvgllN3aySUruamQ3zg1GKwI9UD8VjMkRXpVkDwd0IfZChIWqcOyjEqcqHVNDqZkDZQ+iAwSMRqXGv2x6Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:36:53.773340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.12394","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1e2d0fd6b37c42a63e63dac715759d1eaeb1d5f8ac18c9b3cebf5ef6da55e71","sha256:276ee4e0832661aa480ebc4ff61adbdffa02ff20e3fc97eccaf6eaf022666b59"],"state_sha256":"263c8a9a34be9a8d10124ab2661988821757f1bdfa409b47b7a3e39feeca7dfc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SDB7CW9P11fC0QRKAQWRidtT5o6U2Xto42hOK9fR00M0cu6GfAsAqFUncK6frFslBGizZGG5W9s1PJ4M5EDeBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T03:58:49.076065Z","bundle_sha256":"addcf5b546c09c2f31a597c26c255df53a72be76fbdf7a6ed2f63ae6dd979020"}}