{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:UFXKGODZMBYDXHY2QDWBZATJKY","short_pith_number":"pith:UFXKGODZ","canonical_record":{"source":{"id":"2206.11229","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-06-20T15:23:49Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"d566ba48fcf5237f6616ce0c5e89eaf6404772f7192231918ccd80a6d93dbca9","abstract_canon_sha256":"12b41cbf0b889fcee31ccd84f4d5f5c8b3c978af50abf257fd4e1c52f93be20e"},"schema_version":"1.0"},"canonical_sha256":"a16ea3387960703b9f1a80ec1c82695627d81253a469209375858c7c7545d5ac","source":{"kind":"arxiv","id":"2206.11229","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.11229","created_at":"2026-07-05T04:34:10Z"},{"alias_kind":"arxiv_version","alias_value":"2206.11229v1","created_at":"2026-07-05T04:34:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.11229","created_at":"2026-07-05T04:34:10Z"},{"alias_kind":"pith_short_12","alias_value":"UFXKGODZMBYD","created_at":"2026-07-05T04:34:10Z"},{"alias_kind":"pith_short_16","alias_value":"UFXKGODZMBYDXHY2","created_at":"2026-07-05T04:34:10Z"},{"alias_kind":"pith_short_8","alias_value":"UFXKGODZ","created_at":"2026-07-05T04:34:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:UFXKGODZMBYDXHY2QDWBZATJKY","target":"record","payload":{"canonical_record":{"source":{"id":"2206.11229","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-06-20T15:23:49Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"d566ba48fcf5237f6616ce0c5e89eaf6404772f7192231918ccd80a6d93dbca9","abstract_canon_sha256":"12b41cbf0b889fcee31ccd84f4d5f5c8b3c978af50abf257fd4e1c52f93be20e"},"schema_version":"1.0"},"canonical_sha256":"a16ea3387960703b9f1a80ec1c82695627d81253a469209375858c7c7545d5ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:34:10.399160Z","signature_b64":"Zdgytd2dbl8sArEjDNgZYtCaS/VdfDLhchVB9ipshxArlYGdfQ5FtEEQSrr1vv2ZLtYq1fhSa1Xboli7QtmADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a16ea3387960703b9f1a80ec1c82695627d81253a469209375858c7c7545d5ac","last_reissued_at":"2026-07-05T04:34:10.398745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:34:10.398745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.11229","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":"2026-07-05T04:34:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/2uWaC18sAAYh08MfGMjZvbrmCObrkYfqhwTjmNK/TdNOhzjJNcxnrAl1ClO8WTiCy/ptVIDqi8ai7Q9v4+5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T15:48:53.965934Z"},"content_sha256":"e7750e18863e3d8ac8ab8552026731ce8e8429c046d40732b4137f1ec7bffa22","schema_version":"1.0","event_id":"sha256:e7750e18863e3d8ac8ab8552026731ce8e8429c046d40732b4137f1ec7bffa22"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:UFXKGODZMBYDXHY2QDWBZATJKY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Business Document Information Extraction: Towards Practical Benchmarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.IR","authors_text":"Maty\\'a\\v{s} Skalick\\'y, Michal U\\v{r}i\\v{c}\\'a\\v{r}, Milan \\v{S}ulc, \\v{S}t\\v{e}p\\'an \\v{S}imsa","submitted_at":"2022-06-20T15:23:49Z","abstract_excerpt":"Information extraction from semi-structured documents is crucial for frictionless business-to-business (B2B) communication. While machine learning problems related to Document Information Extraction (IE) have been studied for decades, many common problem definitions and benchmarks do not reflect domain-specific aspects and practical needs for automating B2B document communication. We review the landscape of Document IE problems, datasets and benchmarks. We highlight the practical aspects missing in the common definitions and define the Key Information Localization and Extraction (KILE) and Lin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.11229","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/2206.11229/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":"2026-07-05T04:34:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w+unYwwLicgtvLIBBT6aXFeR/9skBxMTo5MvlfXU2Li5tAwk79CkmGlagZ/Zaggjh0GKrqWOAhe4jHKP+2cmAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T15:48:53.966520Z"},"content_sha256":"49db98ec0826d3ecf654d4200c4c28e66809cf43490bcf76dacea9145b90e9f5","schema_version":"1.0","event_id":"sha256:49db98ec0826d3ecf654d4200c4c28e66809cf43490bcf76dacea9145b90e9f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UFXKGODZMBYDXHY2QDWBZATJKY/bundle.json","state_url":"https://pith.science/pith/UFXKGODZMBYDXHY2QDWBZATJKY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UFXKGODZMBYDXHY2QDWBZATJKY/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":"2026-08-12T15:48:53Z","links":{"resolver":"https://pith.science/pith/UFXKGODZMBYDXHY2QDWBZATJKY","bundle":"https://pith.science/pith/UFXKGODZMBYDXHY2QDWBZATJKY/bundle.json","state":"https://pith.science/pith/UFXKGODZMBYDXHY2QDWBZATJKY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UFXKGODZMBYDXHY2QDWBZATJKY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UFXKGODZMBYDXHY2QDWBZATJKY","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":"12b41cbf0b889fcee31ccd84f4d5f5c8b3c978af50abf257fd4e1c52f93be20e","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-06-20T15:23:49Z","title_canon_sha256":"d566ba48fcf5237f6616ce0c5e89eaf6404772f7192231918ccd80a6d93dbca9"},"schema_version":"1.0","source":{"id":"2206.11229","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.11229","created_at":"2026-07-05T04:34:10Z"},{"alias_kind":"arxiv_version","alias_value":"2206.11229v1","created_at":"2026-07-05T04:34:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.11229","created_at":"2026-07-05T04:34:10Z"},{"alias_kind":"pith_short_12","alias_value":"UFXKGODZMBYD","created_at":"2026-07-05T04:34:10Z"},{"alias_kind":"pith_short_16","alias_value":"UFXKGODZMBYDXHY2","created_at":"2026-07-05T04:34:10Z"},{"alias_kind":"pith_short_8","alias_value":"UFXKGODZ","created_at":"2026-07-05T04:34:10Z"}],"graph_snapshots":[{"event_id":"sha256:49db98ec0826d3ecf654d4200c4c28e66809cf43490bcf76dacea9145b90e9f5","target":"graph","created_at":"2026-07-05T04:34:10Z","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/2206.11229/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Information extraction from semi-structured documents is crucial for frictionless business-to-business (B2B) communication. While machine learning problems related to Document Information Extraction (IE) have been studied for decades, many common problem definitions and benchmarks do not reflect domain-specific aspects and practical needs for automating B2B document communication. We review the landscape of Document IE problems, datasets and benchmarks. We highlight the practical aspects missing in the common definitions and define the Key Information Localization and Extraction (KILE) and Lin","authors_text":"Maty\\'a\\v{s} Skalick\\'y, Michal U\\v{r}i\\v{c}\\'a\\v{r}, Milan \\v{S}ulc, \\v{S}t\\v{e}p\\'an \\v{S}imsa","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-06-20T15:23:49Z","title":"Business Document Information Extraction: Towards Practical Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.11229","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:e7750e18863e3d8ac8ab8552026731ce8e8429c046d40732b4137f1ec7bffa22","target":"record","created_at":"2026-07-05T04:34:10Z","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":"12b41cbf0b889fcee31ccd84f4d5f5c8b3c978af50abf257fd4e1c52f93be20e","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-06-20T15:23:49Z","title_canon_sha256":"d566ba48fcf5237f6616ce0c5e89eaf6404772f7192231918ccd80a6d93dbca9"},"schema_version":"1.0","source":{"id":"2206.11229","kind":"arxiv","version":1}},"canonical_sha256":"a16ea3387960703b9f1a80ec1c82695627d81253a469209375858c7c7545d5ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a16ea3387960703b9f1a80ec1c82695627d81253a469209375858c7c7545d5ac","first_computed_at":"2026-07-05T04:34:10.398745Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:34:10.398745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zdgytd2dbl8sArEjDNgZYtCaS/VdfDLhchVB9ipshxArlYGdfQ5FtEEQSrr1vv2ZLtYq1fhSa1Xboli7QtmADg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:34:10.399160Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.11229","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7750e18863e3d8ac8ab8552026731ce8e8429c046d40732b4137f1ec7bffa22","sha256:49db98ec0826d3ecf654d4200c4c28e66809cf43490bcf76dacea9145b90e9f5"],"state_sha256":"05ba69b48228ede8ee372cf4473ca1c4751b6f64b33d11a370fbd1ed5feb2ef5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fwIGmD+5KVe0KTgpGdElZ3HlxvHv3fos6h5h2a0cC+BjuiosEiayT/krqFQLGII0RZR7rgVjkPpIicCJeliOCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T15:48:53.970923Z","bundle_sha256":"43cfee30b55d59c7c686b578c6a44301458a836a0fe3c993ad4e037b2e9ea34e"}}