{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6XUQWGJSOEHBKTGMAJKU3HOQ5V","short_pith_number":"pith:6XUQWGJS","schema_version":"1.0","canonical_sha256":"f5e90b1932710e154ccc02554d9dd0ed610d8ce36e35c7d587dec3b71a7d6a42","source":{"kind":"arxiv","id":"2507.18546","version":1},"attestation_state":"computed","paper":{"title":"GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ash Lewis, George Hurn-Maloney, Gil Pasternak, Oliver Boyd, Urchade Zaratiana","submitted_at":"2025-07-24T16:11:14Z","abstract_excerpt":"Information extraction (IE) is fundamental to numerous NLP applications, yet existing solutions often require specialized models for different tasks or rely on computationally expensive large language models. We present GLiNER2, a unified framework that enhances the original GLiNER architecture to support named entity recognition, text classification, and hierarchical structured data extraction within a single efficient model. Built pretrained transformer encoder architecture, GLiNER2 maintains CPU efficiency and compact size while introducing multi-task composition through an intuitive schema"},"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":"2507.18546","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T16:11:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8923cb98311ed719719ac288f924257e5e547717826a1c070fe29b1b870707fe","abstract_canon_sha256":"197e36bced5943b2c6538bad241165fec9c4ac3303eed103f0f2c935b8d2331b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:49.858847Z","signature_b64":"09fD3vO2nAViQ8BpcSQ9ruWQtU7m45gMp6zWfLPjcvu3mWeu/IuBNCKg4YC9bwKklYYvMBe48Cnj/5Y6VsWBDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5e90b1932710e154ccc02554d9dd0ed610d8ce36e35c7d587dec3b71a7d6a42","last_reissued_at":"2026-07-05T11:42:49.858443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:49.858443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ash Lewis, George Hurn-Maloney, Gil Pasternak, Oliver Boyd, Urchade Zaratiana","submitted_at":"2025-07-24T16:11:14Z","abstract_excerpt":"Information extraction (IE) is fundamental to numerous NLP applications, yet existing solutions often require specialized models for different tasks or rely on computationally expensive large language models. We present GLiNER2, a unified framework that enhances the original GLiNER architecture to support named entity recognition, text classification, and hierarchical structured data extraction within a single efficient model. Built pretrained transformer encoder architecture, GLiNER2 maintains CPU efficiency and compact size while introducing multi-task composition through an intuitive schema"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18546","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/2507.18546/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":"2507.18546","created_at":"2026-07-05T11:42:49.858494+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.18546v1","created_at":"2026-07-05T11:42:49.858494+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18546","created_at":"2026-07-05T11:42:49.858494+00:00"},{"alias_kind":"pith_short_12","alias_value":"6XUQWGJSOEHB","created_at":"2026-07-05T11:42:49.858494+00:00"},{"alias_kind":"pith_short_16","alias_value":"6XUQWGJSOEHBKTGM","created_at":"2026-07-05T11:42:49.858494+00:00"},{"alias_kind":"pith_short_8","alias_value":"6XUQWGJS","created_at":"2026-07-05T11:42:49.858494+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18782","citing_title":"RedactionBench","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05277","citing_title":"GLiNER Guard: Unified Encoder Family for Production LLM Safety and Privacy","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6XUQWGJSOEHBKTGMAJKU3HOQ5V","json":"https://pith.science/pith/6XUQWGJSOEHBKTGMAJKU3HOQ5V.json","graph_json":"https://pith.science/api/pith-number/6XUQWGJSOEHBKTGMAJKU3HOQ5V/graph.json","events_json":"https://pith.science/api/pith-number/6XUQWGJSOEHBKTGMAJKU3HOQ5V/events.json","paper":"https://pith.science/paper/6XUQWGJS"},"agent_actions":{"view_html":"https://pith.science/pith/6XUQWGJSOEHBKTGMAJKU3HOQ5V","download_json":"https://pith.science/pith/6XUQWGJSOEHBKTGMAJKU3HOQ5V.json","view_paper":"https://pith.science/paper/6XUQWGJS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.18546&json=true","fetch_graph":"https://pith.science/api/pith-number/6XUQWGJSOEHBKTGMAJKU3HOQ5V/graph.json","fetch_events":"https://pith.science/api/pith-number/6XUQWGJSOEHBKTGMAJKU3HOQ5V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6XUQWGJSOEHBKTGMAJKU3HOQ5V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6XUQWGJSOEHBKTGMAJKU3HOQ5V/action/storage_attestation","attest_author":"https://pith.science/pith/6XUQWGJSOEHBKTGMAJKU3HOQ5V/action/author_attestation","sign_citation":"https://pith.science/pith/6XUQWGJSOEHBKTGMAJKU3HOQ5V/action/citation_signature","submit_replication":"https://pith.science/pith/6XUQWGJSOEHBKTGMAJKU3HOQ5V/action/replication_record"}},"created_at":"2026-07-05T11:42:49.858494+00:00","updated_at":"2026-07-05T11:42:49.858494+00:00"}