{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2X3PNGUREYS7RLFVHTJXFNR2ZZ","short_pith_number":"pith:2X3PNGUR","schema_version":"1.0","canonical_sha256":"d5f6f69a912625f8acb53cd372b63ace4491a0e078b95bdf4acdeed9817833d0","source":{"kind":"arxiv","id":"2607.21610","version":1},"attestation_state":"computed","paper":{"title":"SCOPE and SCION: A Benchmark and an Auditable Reference Pipeline for Schema Induction and Fusion from Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Bokun Wang, Daren Zha, Jun Xiao, Miaobo Hu, Rui Chen, Shuhao Hu, Xiaobo Guo, Xin Wang","submitted_at":"2026-05-20T04:43:02Z","abstract_excerpt":"Schema graphs are an upstream bottleneck of schema-grounded information extraction and knowledge graph construction, yet most extraction systems assume the schema is already available. We introduce SCOPE (Schema Construction and Ontology-induction Pipeline Evaluation), a train-text-only benchmark for corpus-to-schema induction and optional schema fusion from raw text, built from 24 public information extraction sources (15 RE and 9 EE) normalized into evaluation-only gold schema graphs; its core event-extraction target covers event types and within-event argument roles, with inter-event links "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.21610","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-20T04:43:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3cf4ce2251e555e74bcb94e0d850e7f950c90db9cf606f47265c84adacc969e7","abstract_canon_sha256":"779c38bfa837d29562738ea187650ebbaa720c1600a5873538414b3a2f859dc9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T00:20:10.964800Z","signature_b64":"OuU/a8r85xR8j13rcys/Aa3FFCtL90shFhSOsODtSu6Eq8EhlkoOrD9/t7GP3sXL3SyuKySDyL8GFNC1FYC8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5f6f69a912625f8acb53cd372b63ace4491a0e078b95bdf4acdeed9817833d0","last_reissued_at":"2026-07-27T00:20:10.963884Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T00:20:10.963884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SCOPE and SCION: A Benchmark and an Auditable Reference Pipeline for Schema Induction and Fusion from Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Bokun Wang, Daren Zha, Jun Xiao, Miaobo Hu, Rui Chen, Shuhao Hu, Xiaobo Guo, Xin Wang","submitted_at":"2026-05-20T04:43:02Z","abstract_excerpt":"Schema graphs are an upstream bottleneck of schema-grounded information extraction and knowledge graph construction, yet most extraction systems assume the schema is already available. We introduce SCOPE (Schema Construction and Ontology-induction Pipeline Evaluation), a train-text-only benchmark for corpus-to-schema induction and optional schema fusion from raw text, built from 24 public information extraction sources (15 RE and 9 EE) normalized into evaluation-only gold schema graphs; its core event-extraction target covers event types and within-event argument roles, with inter-event links "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21610","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/2607.21610/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.21610","created_at":"2026-07-27T00:20:10.964277+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.21610v1","created_at":"2026-07-27T00:20:10.964277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21610","created_at":"2026-07-27T00:20:10.964277+00:00"},{"alias_kind":"pith_short_12","alias_value":"2X3PNGUREYS7","created_at":"2026-07-27T00:20:10.964277+00:00"},{"alias_kind":"pith_short_16","alias_value":"2X3PNGUREYS7RLFV","created_at":"2026-07-27T00:20:10.964277+00:00"},{"alias_kind":"pith_short_8","alias_value":"2X3PNGUR","created_at":"2026-07-27T00:20:10.964277+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2X3PNGUREYS7RLFVHTJXFNR2ZZ","json":"https://pith.science/pith/2X3PNGUREYS7RLFVHTJXFNR2ZZ.json","graph_json":"https://pith.science/api/pith-number/2X3PNGUREYS7RLFVHTJXFNR2ZZ/graph.json","events_json":"https://pith.science/api/pith-number/2X3PNGUREYS7RLFVHTJXFNR2ZZ/events.json","paper":"https://pith.science/paper/2X3PNGUR"},"agent_actions":{"view_html":"https://pith.science/pith/2X3PNGUREYS7RLFVHTJXFNR2ZZ","download_json":"https://pith.science/pith/2X3PNGUREYS7RLFVHTJXFNR2ZZ.json","view_paper":"https://pith.science/paper/2X3PNGUR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.21610&json=true","fetch_graph":"https://pith.science/api/pith-number/2X3PNGUREYS7RLFVHTJXFNR2ZZ/graph.json","fetch_events":"https://pith.science/api/pith-number/2X3PNGUREYS7RLFVHTJXFNR2ZZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2X3PNGUREYS7RLFVHTJXFNR2ZZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2X3PNGUREYS7RLFVHTJXFNR2ZZ/action/storage_attestation","attest_author":"https://pith.science/pith/2X3PNGUREYS7RLFVHTJXFNR2ZZ/action/author_attestation","sign_citation":"https://pith.science/pith/2X3PNGUREYS7RLFVHTJXFNR2ZZ/action/citation_signature","submit_replication":"https://pith.science/pith/2X3PNGUREYS7RLFVHTJXFNR2ZZ/action/replication_record"}},"created_at":"2026-07-27T00:20:10.964277+00:00","updated_at":"2026-07-27T00:20:10.964277+00:00"}