{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UJRYQESLAER4URISDGK4WLPTZE","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":"32ef96de54ddc3ff7c1fe1b1404d49c890f2ab59677531a9080a7569dd55fd6d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-21T18:06:54Z","title_canon_sha256":"665f6615023587acc5a277285a37e5277791681a09b639cf1f89cdcef5ef8b11"},"schema_version":"1.0","source":{"id":"2501.12332","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.12332","created_at":"2026-07-05T10:03:34Z"},{"alias_kind":"arxiv_version","alias_value":"2501.12332v1","created_at":"2026-07-05T10:03:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12332","created_at":"2026-07-05T10:03:34Z"},{"alias_kind":"pith_short_12","alias_value":"UJRYQESLAER4","created_at":"2026-07-05T10:03:34Z"},{"alias_kind":"pith_short_16","alias_value":"UJRYQESLAER4URIS","created_at":"2026-07-05T10:03:34Z"},{"alias_kind":"pith_short_8","alias_value":"UJRYQESL","created_at":"2026-07-05T10:03:34Z"}],"graph_snapshots":[{"event_id":"sha256:785d939213936e4686e85ade461e6c2a3f524c5763643d0cbbaef38abe48cb00","target":"graph","created_at":"2026-07-05T10:03:34Z","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/2501.12332/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Acquiring labelled training data remains a costly task in real world machine learning projects to meet quantity and quality requirements. Recently Large Language Models (LLMs), notably GPT-4, have shown great promises in labelling data with high accuracy. However, privacy and cost concerns prevent the ubiquitous use of GPT-4. In this work, we explore effectively leveraging open-source models for automatic labelling. We identify integrating label schema as a promising technology but found that naively using the label description for classification leads to poor performance on high cardinality t","authors_text":"Chunyang Xiao, Fran Silavong, Sae Young Moon, Thomas Walshe, Yawwani Gunawardana","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-21T18:06:54Z","title":"Automatic Labelling with Open-source LLMs using Dynamic Label Schema Integration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12332","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":"sha256:879d0bcf590d89e32ce5d7a7ce6217157bd0f8305df81f1ff1a5351fddbf0292","target":"record","created_at":"2026-07-05T10:03:34Z","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":"32ef96de54ddc3ff7c1fe1b1404d49c890f2ab59677531a9080a7569dd55fd6d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-21T18:06:54Z","title_canon_sha256":"665f6615023587acc5a277285a37e5277791681a09b639cf1f89cdcef5ef8b11"},"schema_version":"1.0","source":{"id":"2501.12332","kind":"arxiv","version":1}},"canonical_sha256":"a26388124b0123ca45121995cb2df3c92406b3229094622aff2111c3a283bdb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a26388124b0123ca45121995cb2df3c92406b3229094622aff2111c3a283bdb2","first_computed_at":"2026-07-05T10:03:34.706366Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:03:34.706366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sdYxNClJ+ILzVd2CrE6wcHrAhbWLyHTg2COtZPdZSWWiDXml9r8cIXQitSmFV/PTwp/Y2GWpoC8mvWe1AiwiBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:03:34.706827Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.12332","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:879d0bcf590d89e32ce5d7a7ce6217157bd0f8305df81f1ff1a5351fddbf0292","sha256:785d939213936e4686e85ade461e6c2a3f524c5763643d0cbbaef38abe48cb00"],"state_sha256":"cf5c597510a0dd50e080893002e903f3186ae34610fba36759eb866526394510"}