{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VWCELGOTHH6YBFZQ33DQPZ7GGY","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":"13dbbc23fa5112f830c963ea244472d6afb34447545b9d12e09def66661bb8e5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-29T03:51:00Z","title_canon_sha256":"b3e63a649166507a45089aced21858d9a6cf844afb597a75482ebd579ef630b8"},"schema_version":"1.0","source":{"id":"2507.21482","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.21482","created_at":"2026-07-05T11:45:00Z"},{"alias_kind":"arxiv_version","alias_value":"2507.21482v1","created_at":"2026-07-05T11:45:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21482","created_at":"2026-07-05T11:45:00Z"},{"alias_kind":"pith_short_12","alias_value":"VWCELGOTHH6Y","created_at":"2026-07-05T11:45:00Z"},{"alias_kind":"pith_short_16","alias_value":"VWCELGOTHH6YBFZQ","created_at":"2026-07-05T11:45:00Z"},{"alias_kind":"pith_short_8","alias_value":"VWCELGOT","created_at":"2026-07-05T11:45:00Z"}],"graph_snapshots":[{"event_id":"sha256:7ecf246a6566e714c54b15b5280af71428e82965085441537879a4c14e8979a5","target":"graph","created_at":"2026-07-05T11:45:00Z","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/2507.21482/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse domains, but developing high-performing models for specialized applications often requires substantial human annotation -- a process that is time-consuming, labor-intensive, and expensive. In this paper, we address the label-efficient learning problem for supervised finetuning (SFT) by leveraging task-diversity as a fundamental principle for effective data selection. This is markedly different from existing methods based on the prompt-diversity. Our approach is based on two key observations: 1) task labels fo","authors_text":"Abhinav Arabelly, Jagrut Nemade, Jifan Zhang, Robert D Nowak","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-29T03:51:00Z","title":"Improving Task Diversity in Label Efficient Supervised Finetuning of LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21482","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:c2039f459115af004983620923dffd27638ea940bbf1021f71fcee86076af60c","target":"record","created_at":"2026-07-05T11:45:00Z","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":"13dbbc23fa5112f830c963ea244472d6afb34447545b9d12e09def66661bb8e5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-29T03:51:00Z","title_canon_sha256":"b3e63a649166507a45089aced21858d9a6cf844afb597a75482ebd579ef630b8"},"schema_version":"1.0","source":{"id":"2507.21482","kind":"arxiv","version":1}},"canonical_sha256":"ad844599d339fd809730dec707e7e63610a5a2a3e745dc1cdd02b5341cf6a7e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad844599d339fd809730dec707e7e63610a5a2a3e745dc1cdd02b5341cf6a7e7","first_computed_at":"2026-07-05T11:45:00.839328Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:00.839328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TsHGKPGiCce11hGiZekOhseeA9P4ccEk5bap2NFa1UIb5jtYFrMIoVViJIz2F/RbE47uXYeJmefb7jYUYZtiAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:00.839678Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.21482","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2039f459115af004983620923dffd27638ea940bbf1021f71fcee86076af60c","sha256:7ecf246a6566e714c54b15b5280af71428e82965085441537879a4c14e8979a5"],"state_sha256":"b7a706ec097bf1930faa7120e97e828616f5fa2328ebae9c298d550b2a293e2b"}