{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GUYM3LODM7DPDBPHMAGS2ICIJK","short_pith_number":"pith:GUYM3LOD","schema_version":"1.0","canonical_sha256":"3530cdadc367c6f185e7600d2d20484abee7261e0f9afa5d794d2ae55ce68da1","source":{"kind":"arxiv","id":"2606.01617","version":1},"attestation_state":"computed","paper":{"title":"EvoPool: Evolutionary Programmatic Annotation for Label-Efficient Specialized Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Huazheng Wang, Tianyi Xu, Xuan Ouyang, Yaolun Zhang","submitted_at":"2026-06-01T03:10:37Z","abstract_excerpt":"Large language models excel at general tasks but underperform smaller supervised models in specialized, high-stakes domains where training labels are costly. We address this regime with EvoPool, an evolutionary multi-agent framework inspired by Darwinian evolution. Three specialized agents iteratively propose executable annotator code, a small validation set provides a fitness signal, and a deterministic gate keeps only annotators that pass viability, diversity, and marginal-contribution checks across generations. Pool votes are mapped to soft training labels by EvoAgg, a text-aware aggregator"},"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":"2606.01617","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-01T03:10:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c4d391dbd1df2a2a7d22854a6f8039969a2750645e3dbeaf896c4a91f13bde6c","abstract_canon_sha256":"73f18c815d160aacff6637d60831bbb7116aafbf817f753d87cebf8434fe4524"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:38.147767Z","signature_b64":"cjUX5f3nZjjvUD5qcNENHCG2fKNp3e1Z1nW0l1vKqNqD9J55cj/2OwLqzwgdRcwx0s5c300m93R78ELqnRGEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3530cdadc367c6f185e7600d2d20484abee7261e0f9afa5d794d2ae55ce68da1","last_reissued_at":"2026-06-02T02:04:38.147345Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:38.147345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EvoPool: Evolutionary Programmatic Annotation for Label-Efficient Specialized Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Huazheng Wang, Tianyi Xu, Xuan Ouyang, Yaolun Zhang","submitted_at":"2026-06-01T03:10:37Z","abstract_excerpt":"Large language models excel at general tasks but underperform smaller supervised models in specialized, high-stakes domains where training labels are costly. We address this regime with EvoPool, an evolutionary multi-agent framework inspired by Darwinian evolution. Three specialized agents iteratively propose executable annotator code, a small validation set provides a fitness signal, and a deterministic gate keeps only annotators that pass viability, diversity, and marginal-contribution checks across generations. Pool votes are mapped to soft training labels by EvoAgg, a text-aware aggregator"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01617","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/2606.01617/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":"2606.01617","created_at":"2026-06-02T02:04:38.147406+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01617v1","created_at":"2026-06-02T02:04:38.147406+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01617","created_at":"2026-06-02T02:04:38.147406+00:00"},{"alias_kind":"pith_short_12","alias_value":"GUYM3LODM7DP","created_at":"2026-06-02T02:04:38.147406+00:00"},{"alias_kind":"pith_short_16","alias_value":"GUYM3LODM7DPDBPH","created_at":"2026-06-02T02:04:38.147406+00:00"},{"alias_kind":"pith_short_8","alias_value":"GUYM3LOD","created_at":"2026-06-02T02:04:38.147406+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/GUYM3LODM7DPDBPHMAGS2ICIJK","json":"https://pith.science/pith/GUYM3LODM7DPDBPHMAGS2ICIJK.json","graph_json":"https://pith.science/api/pith-number/GUYM3LODM7DPDBPHMAGS2ICIJK/graph.json","events_json":"https://pith.science/api/pith-number/GUYM3LODM7DPDBPHMAGS2ICIJK/events.json","paper":"https://pith.science/paper/GUYM3LOD"},"agent_actions":{"view_html":"https://pith.science/pith/GUYM3LODM7DPDBPHMAGS2ICIJK","download_json":"https://pith.science/pith/GUYM3LODM7DPDBPHMAGS2ICIJK.json","view_paper":"https://pith.science/paper/GUYM3LOD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01617&json=true","fetch_graph":"https://pith.science/api/pith-number/GUYM3LODM7DPDBPHMAGS2ICIJK/graph.json","fetch_events":"https://pith.science/api/pith-number/GUYM3LODM7DPDBPHMAGS2ICIJK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GUYM3LODM7DPDBPHMAGS2ICIJK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GUYM3LODM7DPDBPHMAGS2ICIJK/action/storage_attestation","attest_author":"https://pith.science/pith/GUYM3LODM7DPDBPHMAGS2ICIJK/action/author_attestation","sign_citation":"https://pith.science/pith/GUYM3LODM7DPDBPHMAGS2ICIJK/action/citation_signature","submit_replication":"https://pith.science/pith/GUYM3LODM7DPDBPHMAGS2ICIJK/action/replication_record"}},"created_at":"2026-06-02T02:04:38.147406+00:00","updated_at":"2026-06-02T02:04:38.147406+00:00"}