{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4AXANROPO53PTQWIVTLYHCBDO4","short_pith_number":"pith:4AXANROP","canonical_record":{"source":{"id":"2405.00505","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-05-01T13:37:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"308514915ec1c9d5fc8c361c7726874a0fc5abc9bc74a3c77955c70123f5fb6e","abstract_canon_sha256":"bb260a49f1c35b2e3306b014a7fac59058d673667c1826da54d6f2036f642868"},"schema_version":"1.0"},"canonical_sha256":"e02e06c5cf7776f9c2c8acd7838823773d3e90e13b0efe0360968c420a2c13d4","source":{"kind":"arxiv","id":"2405.00505","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.00505","created_at":"2026-07-05T08:14:14Z"},{"alias_kind":"arxiv_version","alias_value":"2405.00505v1","created_at":"2026-07-05T08:14:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00505","created_at":"2026-07-05T08:14:14Z"},{"alias_kind":"pith_short_12","alias_value":"4AXANROPO53P","created_at":"2026-07-05T08:14:14Z"},{"alias_kind":"pith_short_16","alias_value":"4AXANROPO53PTQWI","created_at":"2026-07-05T08:14:14Z"},{"alias_kind":"pith_short_8","alias_value":"4AXANROP","created_at":"2026-07-05T08:14:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4AXANROPO53PTQWIVTLYHCBDO4","target":"record","payload":{"canonical_record":{"source":{"id":"2405.00505","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-05-01T13:37:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"308514915ec1c9d5fc8c361c7726874a0fc5abc9bc74a3c77955c70123f5fb6e","abstract_canon_sha256":"bb260a49f1c35b2e3306b014a7fac59058d673667c1826da54d6f2036f642868"},"schema_version":"1.0"},"canonical_sha256":"e02e06c5cf7776f9c2c8acd7838823773d3e90e13b0efe0360968c420a2c13d4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:14.035568Z","signature_b64":"T5jxO58LfSc5IboTEi+9WkLDCD47/mJb4IX2kEDUCgWxN1Xepja3pjQbgsyB4em7RUye18CSscM+jk8TzLBkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e02e06c5cf7776f9c2c8acd7838823773d3e90e13b0efe0360968c420a2c13d4","last_reissued_at":"2026-07-05T08:14:14.035142Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:14.035142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.00505","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":"2026-07-05T08:14:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QV47iDSox7b2/TUoUKH1C8aNlJ3RvvyGpt0qZV3jqvY5PDrK4jnrwouaNaqLK5qsDl6kM4YYVL9PtXPdtIZ7AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T20:00:48.885553Z"},"content_sha256":"4933650c7846d94cd51a106cf5dea8579acec4a028417a1e139a207c0fcc9d89","schema_version":"1.0","event_id":"sha256:4933650c7846d94cd51a106cf5dea8579acec4a028417a1e139a207c0fcc9d89"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4AXANROPO53PTQWIVTLYHCBDO4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KVP10k : A Comprehensive Dataset for Key-Value Pair Extraction in Business Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Adi Raz Goldfarb, Ahmed Nassar, Christoph Auer, Elad Amrani, Foad Abo Dahood, Idan Friedman, Inbar Shapira, Maksym Lysak, Nadav Rubinstein, Nikolaos Livathinos, Ophir Azulai, Orit Prince, Oshri Naparstek, Peter Staar, Roi pony, Udi Barzelay, Yevgeny Burshtein, Yevgeny Yaroker","submitted_at":"2024-05-01T13:37:27Z","abstract_excerpt":"In recent years, the challenge of extracting information from business documents has emerged as a critical task, finding applications across numerous domains. This effort has attracted substantial interest from both industry and academy, highlighting its significance in the current technological landscape. Most datasets in this area are primarily focused on Key Information Extraction (KIE), where the extraction process revolves around extracting information using a specific, predefined set of keys. Unlike most existing datasets and benchmarks, our focus is on discovering key-value pairs (KVPs)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00505","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/2405.00505/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":"2026-07-05T08:14:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qIYqzWKmeTXiE5K904w9/pF391RPjkJ2feAXFUIxyZBTc2BpM4pRGp/OzQ2tdlcLyvOTeQYG9oAUoy38NJs/Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T20:00:48.885844Z"},"content_sha256":"a786ab2b759e6df4702c854b37eac808ad669b09d4a64ab7a5f927cf3fecdc2c","schema_version":"1.0","event_id":"sha256:a786ab2b759e6df4702c854b37eac808ad669b09d4a64ab7a5f927cf3fecdc2c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4AXANROPO53PTQWIVTLYHCBDO4/bundle.json","state_url":"https://pith.science/pith/4AXANROPO53PTQWIVTLYHCBDO4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4AXANROPO53PTQWIVTLYHCBDO4/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":"2026-07-31T20:00:48Z","links":{"resolver":"https://pith.science/pith/4AXANROPO53PTQWIVTLYHCBDO4","bundle":"https://pith.science/pith/4AXANROPO53PTQWIVTLYHCBDO4/bundle.json","state":"https://pith.science/pith/4AXANROPO53PTQWIVTLYHCBDO4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4AXANROPO53PTQWIVTLYHCBDO4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4AXANROPO53PTQWIVTLYHCBDO4","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":"bb260a49f1c35b2e3306b014a7fac59058d673667c1826da54d6f2036f642868","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-05-01T13:37:27Z","title_canon_sha256":"308514915ec1c9d5fc8c361c7726874a0fc5abc9bc74a3c77955c70123f5fb6e"},"schema_version":"1.0","source":{"id":"2405.00505","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.00505","created_at":"2026-07-05T08:14:14Z"},{"alias_kind":"arxiv_version","alias_value":"2405.00505v1","created_at":"2026-07-05T08:14:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00505","created_at":"2026-07-05T08:14:14Z"},{"alias_kind":"pith_short_12","alias_value":"4AXANROPO53P","created_at":"2026-07-05T08:14:14Z"},{"alias_kind":"pith_short_16","alias_value":"4AXANROPO53PTQWI","created_at":"2026-07-05T08:14:14Z"},{"alias_kind":"pith_short_8","alias_value":"4AXANROP","created_at":"2026-07-05T08:14:14Z"}],"graph_snapshots":[{"event_id":"sha256:a786ab2b759e6df4702c854b37eac808ad669b09d4a64ab7a5f927cf3fecdc2c","target":"graph","created_at":"2026-07-05T08:14:14Z","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/2405.00505/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, the challenge of extracting information from business documents has emerged as a critical task, finding applications across numerous domains. This effort has attracted substantial interest from both industry and academy, highlighting its significance in the current technological landscape. Most datasets in this area are primarily focused on Key Information Extraction (KIE), where the extraction process revolves around extracting information using a specific, predefined set of keys. Unlike most existing datasets and benchmarks, our focus is on discovering key-value pairs (KVPs)","authors_text":"Adi Raz Goldfarb, Ahmed Nassar, Christoph Auer, Elad Amrani, Foad Abo Dahood, Idan Friedman, Inbar Shapira, Maksym Lysak, Nadav Rubinstein, Nikolaos Livathinos, Ophir Azulai, Orit Prince, Oshri Naparstek, Peter Staar, Roi pony, Udi Barzelay, Yevgeny Burshtein, Yevgeny Yaroker","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-05-01T13:37:27Z","title":"KVP10k : A Comprehensive Dataset for Key-Value Pair Extraction in Business Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00505","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":"sha256:4933650c7846d94cd51a106cf5dea8579acec4a028417a1e139a207c0fcc9d89","target":"record","created_at":"2026-07-05T08:14:14Z","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":"bb260a49f1c35b2e3306b014a7fac59058d673667c1826da54d6f2036f642868","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-05-01T13:37:27Z","title_canon_sha256":"308514915ec1c9d5fc8c361c7726874a0fc5abc9bc74a3c77955c70123f5fb6e"},"schema_version":"1.0","source":{"id":"2405.00505","kind":"arxiv","version":1}},"canonical_sha256":"e02e06c5cf7776f9c2c8acd7838823773d3e90e13b0efe0360968c420a2c13d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e02e06c5cf7776f9c2c8acd7838823773d3e90e13b0efe0360968c420a2c13d4","first_computed_at":"2026-07-05T08:14:14.035142Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:14:14.035142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T5jxO58LfSc5IboTEi+9WkLDCD47/mJb4IX2kEDUCgWxN1Xepja3pjQbgsyB4em7RUye18CSscM+jk8TzLBkBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:14:14.035568Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.00505","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4933650c7846d94cd51a106cf5dea8579acec4a028417a1e139a207c0fcc9d89","sha256:a786ab2b759e6df4702c854b37eac808ad669b09d4a64ab7a5f927cf3fecdc2c"],"state_sha256":"9e4c846ffd263cbcc1102413ab7b4582d4b2501635ffbc27938bd9103efe34d8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bUwVduvlvJY+E8lUJ5CK5CZyCzRb13NMvBc08EXDKAJyDvjD3ooaMGBH9SyvZdBVFe4pbubdaLg08f67Zh0lAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T20:00:48.888328Z","bundle_sha256":"0174a98be841cdcda54ce1e0bdde77e3967798b1d170e03d9d44b0366aba8674"}}