{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7F7XDKMW2G475D4OOFSMWH3HV4","short_pith_number":"pith:7F7XDKMW","schema_version":"1.0","canonical_sha256":"f97f71a996d1b9fe8f8e7164cb1f67af33db3145610ca9e8776dcf0bfc51abfd","source":{"kind":"arxiv","id":"2406.12925","version":2},"attestation_state":"computed","paper":{"title":"GLiNER multi-task: Generalist Lightweight Model for Various Information Extraction Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR"],"primary_cat":"cs.LG","authors_text":"Ihor Stepanov, Mykhailo Shtopko","submitted_at":"2024-06-14T13:54:29Z","abstract_excerpt":"Information extraction tasks require both accurate, efficient, and generalisable models. Classical supervised deep learning approaches can achieve the required performance, but they need large datasets and are limited in their ability to adapt to different tasks. On the other hand, large language models (LLMs) demonstrate good generalization, meaning that they can adapt to many different tasks based on user requests. However, LLMs are computationally expensive and tend to fail to generate structured outputs. In this article, we will introduce a new kind of GLiNER model that can be used for var"},"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":"2406.12925","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-14T13:54:29Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"title_canon_sha256":"30107dbe8e1d997d3975dce26a8729d0a3944ffe2c175dce453a5f6135ded224","abstract_canon_sha256":"bb795d67bb266ecd31b48ce4a1965a1fce9f7a767db03aaaa5e194df141014c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:57.161497Z","signature_b64":"K0l7sdxshJTtXLaN4IVN58lJdMl/tx9OpshBkIXnev8Tpd+UABnFPAUOyTEQWO6ny9ycOqOcjaiao0Ly2lbHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f97f71a996d1b9fe8f8e7164cb1f67af33db3145610ca9e8776dcf0bfc51abfd","last_reissued_at":"2026-07-05T08:50:57.161056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:57.161056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GLiNER multi-task: Generalist Lightweight Model for Various Information Extraction Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR"],"primary_cat":"cs.LG","authors_text":"Ihor Stepanov, Mykhailo Shtopko","submitted_at":"2024-06-14T13:54:29Z","abstract_excerpt":"Information extraction tasks require both accurate, efficient, and generalisable models. Classical supervised deep learning approaches can achieve the required performance, but they need large datasets and are limited in their ability to adapt to different tasks. On the other hand, large language models (LLMs) demonstrate good generalization, meaning that they can adapt to many different tasks based on user requests. However, LLMs are computationally expensive and tend to fail to generate structured outputs. In this article, we will introduce a new kind of GLiNER model that can be used for var"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12925","kind":"arxiv","version":2},"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/2406.12925/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":"2406.12925","created_at":"2026-07-05T08:50:57.161109+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12925v2","created_at":"2026-07-05T08:50:57.161109+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12925","created_at":"2026-07-05T08:50:57.161109+00:00"},{"alias_kind":"pith_short_12","alias_value":"7F7XDKMW2G47","created_at":"2026-07-05T08:50:57.161109+00:00"},{"alias_kind":"pith_short_16","alias_value":"7F7XDKMW2G475D4O","created_at":"2026-07-05T08:50:57.161109+00:00"},{"alias_kind":"pith_short_8","alias_value":"7F7XDKMW","created_at":"2026-07-05T08:50:57.161109+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29659","citing_title":"Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10108","citing_title":"GLiNER-Relex: A Unified Framework for Joint Named Entity Recognition and Relation Extraction","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7F7XDKMW2G475D4OOFSMWH3HV4","json":"https://pith.science/pith/7F7XDKMW2G475D4OOFSMWH3HV4.json","graph_json":"https://pith.science/api/pith-number/7F7XDKMW2G475D4OOFSMWH3HV4/graph.json","events_json":"https://pith.science/api/pith-number/7F7XDKMW2G475D4OOFSMWH3HV4/events.json","paper":"https://pith.science/paper/7F7XDKMW"},"agent_actions":{"view_html":"https://pith.science/pith/7F7XDKMW2G475D4OOFSMWH3HV4","download_json":"https://pith.science/pith/7F7XDKMW2G475D4OOFSMWH3HV4.json","view_paper":"https://pith.science/paper/7F7XDKMW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12925&json=true","fetch_graph":"https://pith.science/api/pith-number/7F7XDKMW2G475D4OOFSMWH3HV4/graph.json","fetch_events":"https://pith.science/api/pith-number/7F7XDKMW2G475D4OOFSMWH3HV4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7F7XDKMW2G475D4OOFSMWH3HV4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7F7XDKMW2G475D4OOFSMWH3HV4/action/storage_attestation","attest_author":"https://pith.science/pith/7F7XDKMW2G475D4OOFSMWH3HV4/action/author_attestation","sign_citation":"https://pith.science/pith/7F7XDKMW2G475D4OOFSMWH3HV4/action/citation_signature","submit_replication":"https://pith.science/pith/7F7XDKMW2G475D4OOFSMWH3HV4/action/replication_record"}},"created_at":"2026-07-05T08:50:57.161109+00:00","updated_at":"2026-07-05T08:50:57.161109+00:00"}