{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZKAQIZ3ER34GZWGLWB7S6OM2G4","short_pith_number":"pith:ZKAQIZ3E","canonical_record":{"source":{"id":"2402.09916","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T12:39:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"01398902fbdea18910e023bf62c290026ca201090233e737562736d6735ede8e","abstract_canon_sha256":"1a6693ba567ee8222a169f9363c2e4e67855acffdc942464e1b49e664990f070"},"schema_version":"1.0"},"canonical_sha256":"ca810467648ef86cd8cbb07f2f399a37399b842e18d7a5c89160f73430d799a2","source":{"kind":"arxiv","id":"2402.09916","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.09916","created_at":"2026-07-05T07:45:38Z"},{"alias_kind":"arxiv_version","alias_value":"2402.09916v1","created_at":"2026-07-05T07:45:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09916","created_at":"2026-07-05T07:45:38Z"},{"alias_kind":"pith_short_12","alias_value":"ZKAQIZ3ER34G","created_at":"2026-07-05T07:45:38Z"},{"alias_kind":"pith_short_16","alias_value":"ZKAQIZ3ER34GZWGL","created_at":"2026-07-05T07:45:38Z"},{"alias_kind":"pith_short_8","alias_value":"ZKAQIZ3E","created_at":"2026-07-05T07:45:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZKAQIZ3ER34GZWGLWB7S6OM2G4","target":"record","payload":{"canonical_record":{"source":{"id":"2402.09916","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T12:39:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"01398902fbdea18910e023bf62c290026ca201090233e737562736d6735ede8e","abstract_canon_sha256":"1a6693ba567ee8222a169f9363c2e4e67855acffdc942464e1b49e664990f070"},"schema_version":"1.0"},"canonical_sha256":"ca810467648ef86cd8cbb07f2f399a37399b842e18d7a5c89160f73430d799a2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:38.625205Z","signature_b64":"oMLSd3AhXo8TISP4eFtE/PxLwUI7VOeJVbzdF+FzkMjzQOLSXTnHMNYCl9j/xXbwh9KuJXGTGyOaSN+hnK/6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca810467648ef86cd8cbb07f2f399a37399b842e18d7a5c89160f73430d799a2","last_reissued_at":"2026-07-05T07:45:38.624780Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:38.624780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.09916","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":"2026-07-05T07:45:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EnOX3VlyQuw9lB/I69XFTUa5sqV+H/Ymt2yUFtv7qR+9uL7bi977/VgyGpCYv0qmdQBFefykr2O/d1o9iEFgCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T23:46:01.264521Z"},"content_sha256":"01890667edd12c1d3b2699498cfcfdb82b52d308f379cc4e00fd6c6994a98e29","schema_version":"1.0","event_id":"sha256:01890667edd12c1d3b2699498cfcfdb82b52d308f379cc4e00fd6c6994a98e29"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZKAQIZ3ER34GZWGLWB7S6OM2G4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BUSTER: a \"BUSiness Transaction Entity Recognition\" dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andrea Zugarini, Andrew Zamai, Leonardo Rigutini, Marco Ernandes","submitted_at":"2024-02-15T12:39:57Z","abstract_excerpt":"Albeit Natural Language Processing has seen major breakthroughs in the last few years, transferring such advances into real-world business cases can be challenging. One of the reasons resides in the displacement between popular benchmarks and actual data. Lack of supervision, unbalanced classes, noisy data and long documents often affect real problems in vertical domains such as finance, law and health. To support industry-oriented research, we present BUSTER, a BUSiness Transaction Entity Recognition dataset. The dataset consists of 3779 manually annotated documents on financial transactions."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09916","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/2402.09916/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":"2026-07-05T07:45:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0YhWs/WfyeRLB22bWM8weVOamEJRLnrbeV2VYXF+rl2I0019fhGWCn9BVctRa0mTsZHhZtK8nYXKK0XhFttfDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T23:46:01.264805Z"},"content_sha256":"bbd6e5f8d9cb13a694fd1305e187a3cb246e00f248c69f2ec3a6ea13973f208e","schema_version":"1.0","event_id":"sha256:bbd6e5f8d9cb13a694fd1305e187a3cb246e00f248c69f2ec3a6ea13973f208e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZKAQIZ3ER34GZWGLWB7S6OM2G4/bundle.json","state_url":"https://pith.science/pith/ZKAQIZ3ER34GZWGLWB7S6OM2G4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZKAQIZ3ER34GZWGLWB7S6OM2G4/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":"2026-07-31T23:46:01Z","links":{"resolver":"https://pith.science/pith/ZKAQIZ3ER34GZWGLWB7S6OM2G4","bundle":"https://pith.science/pith/ZKAQIZ3ER34GZWGLWB7S6OM2G4/bundle.json","state":"https://pith.science/pith/ZKAQIZ3ER34GZWGLWB7S6OM2G4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZKAQIZ3ER34GZWGLWB7S6OM2G4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZKAQIZ3ER34GZWGLWB7S6OM2G4","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":"1a6693ba567ee8222a169f9363c2e4e67855acffdc942464e1b49e664990f070","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T12:39:57Z","title_canon_sha256":"01398902fbdea18910e023bf62c290026ca201090233e737562736d6735ede8e"},"schema_version":"1.0","source":{"id":"2402.09916","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.09916","created_at":"2026-07-05T07:45:38Z"},{"alias_kind":"arxiv_version","alias_value":"2402.09916v1","created_at":"2026-07-05T07:45:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09916","created_at":"2026-07-05T07:45:38Z"},{"alias_kind":"pith_short_12","alias_value":"ZKAQIZ3ER34G","created_at":"2026-07-05T07:45:38Z"},{"alias_kind":"pith_short_16","alias_value":"ZKAQIZ3ER34GZWGL","created_at":"2026-07-05T07:45:38Z"},{"alias_kind":"pith_short_8","alias_value":"ZKAQIZ3E","created_at":"2026-07-05T07:45:38Z"}],"graph_snapshots":[{"event_id":"sha256:bbd6e5f8d9cb13a694fd1305e187a3cb246e00f248c69f2ec3a6ea13973f208e","target":"graph","created_at":"2026-07-05T07:45:38Z","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/2402.09916/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Albeit Natural Language Processing has seen major breakthroughs in the last few years, transferring such advances into real-world business cases can be challenging. One of the reasons resides in the displacement between popular benchmarks and actual data. Lack of supervision, unbalanced classes, noisy data and long documents often affect real problems in vertical domains such as finance, law and health. To support industry-oriented research, we present BUSTER, a BUSiness Transaction Entity Recognition dataset. The dataset consists of 3779 manually annotated documents on financial transactions.","authors_text":"Andrea Zugarini, Andrew Zamai, Leonardo Rigutini, Marco Ernandes","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T12:39:57Z","title":"BUSTER: a \"BUSiness Transaction Entity Recognition\" dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09916","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":"sha256:01890667edd12c1d3b2699498cfcfdb82b52d308f379cc4e00fd6c6994a98e29","target":"record","created_at":"2026-07-05T07:45:38Z","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":"1a6693ba567ee8222a169f9363c2e4e67855acffdc942464e1b49e664990f070","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T12:39:57Z","title_canon_sha256":"01398902fbdea18910e023bf62c290026ca201090233e737562736d6735ede8e"},"schema_version":"1.0","source":{"id":"2402.09916","kind":"arxiv","version":1}},"canonical_sha256":"ca810467648ef86cd8cbb07f2f399a37399b842e18d7a5c89160f73430d799a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca810467648ef86cd8cbb07f2f399a37399b842e18d7a5c89160f73430d799a2","first_computed_at":"2026-07-05T07:45:38.624780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:45:38.624780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oMLSd3AhXo8TISP4eFtE/PxLwUI7VOeJVbzdF+FzkMjzQOLSXTnHMNYCl9j/xXbwh9KuJXGTGyOaSN+hnK/6CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:45:38.625205Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.09916","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01890667edd12c1d3b2699498cfcfdb82b52d308f379cc4e00fd6c6994a98e29","sha256:bbd6e5f8d9cb13a694fd1305e187a3cb246e00f248c69f2ec3a6ea13973f208e"],"state_sha256":"f615adcf73c1f2d749484b339b45d02ed00f72360ee5711a345907b300a690dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SoDD7A5/W4AILarUiTd/2XlnZdu9/mc7QWHMjJmuVjB8PLpD/VNOzxk+28CW1FOVD/WxsS1dr/D1Il11WAEiCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T23:46:01.267796Z","bundle_sha256":"0b9ce348c2aa2a92c4c324735c14ceb3fd01b2e24980a4721b00f9cfaa5f3e0e"}}