{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GE64MTT34BPKXTIVHNXUAENW2D","short_pith_number":"pith:GE64MTT3","schema_version":"1.0","canonical_sha256":"313dc64e7be05eabcd153b6f4011b6d0c6e106fc6223ba12f80c780c224733f5","source":{"kind":"arxiv","id":"2605.29076","version":1},"attestation_state":"computed","paper":{"title":"Structured Prompt Optimization Meets Reinforcement Learning for Global and Local Interpretability over Complex Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Leman Akoglu, Pierre Jinghong Liang, Tianyang Zhou, Wenbo Chen","submitted_at":"2026-05-27T20:29:41Z","abstract_excerpt":"LLMs have advanced text classification, yet existing paradigms face a trade-off: supervised (label only) fine-tuning is scalable but offers limited reasoning on complex text and lacks broader model transparency, while discrete prompt optimization offers human-readable instructions but struggles with performance and scalability. We introduce eXTC (eXplainable Text Classifier) with three progressive stages: (1) learning a Standard Operating Procedure (SOP, or rulebook) in natural language via a new Structured Prompt Optimization algorithm; (2) SOP-grounded reasoning distillation from a large tea"},"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":"2605.29076","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T20:29:41Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"732a12351a111aca0d912f084cbb4576b33f2bd3bfd495ba5d6e827e6f78d67b","abstract_canon_sha256":"961480f78dbe53b7d5687f39c7d28dccb2f9362657409e4545462c8505f37967"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:17.127479Z","signature_b64":"gmziDQZHJub5FGsSpuqcsjofwDiIFPRkDrUCILVjPEv4NzRzlZhRKAsrOZXFZHAlajOcKqTWVofaYkl8NEnnBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"313dc64e7be05eabcd153b6f4011b6d0c6e106fc6223ba12f80c780c224733f5","last_reissued_at":"2026-05-29T01:05:17.126746Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:17.126746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structured Prompt Optimization Meets Reinforcement Learning for Global and Local Interpretability over Complex Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Leman Akoglu, Pierre Jinghong Liang, Tianyang Zhou, Wenbo Chen","submitted_at":"2026-05-27T20:29:41Z","abstract_excerpt":"LLMs have advanced text classification, yet existing paradigms face a trade-off: supervised (label only) fine-tuning is scalable but offers limited reasoning on complex text and lacks broader model transparency, while discrete prompt optimization offers human-readable instructions but struggles with performance and scalability. We introduce eXTC (eXplainable Text Classifier) with three progressive stages: (1) learning a Standard Operating Procedure (SOP, or rulebook) in natural language via a new Structured Prompt Optimization algorithm; (2) SOP-grounded reasoning distillation from a large tea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29076","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/2605.29076/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":"2605.29076","created_at":"2026-05-29T01:05:17.126839+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29076v1","created_at":"2026-05-29T01:05:17.126839+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29076","created_at":"2026-05-29T01:05:17.126839+00:00"},{"alias_kind":"pith_short_12","alias_value":"GE64MTT34BPK","created_at":"2026-05-29T01:05:17.126839+00:00"},{"alias_kind":"pith_short_16","alias_value":"GE64MTT34BPKXTIV","created_at":"2026-05-29T01:05:17.126839+00:00"},{"alias_kind":"pith_short_8","alias_value":"GE64MTT3","created_at":"2026-05-29T01:05:17.126839+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/GE64MTT34BPKXTIVHNXUAENW2D","json":"https://pith.science/pith/GE64MTT34BPKXTIVHNXUAENW2D.json","graph_json":"https://pith.science/api/pith-number/GE64MTT34BPKXTIVHNXUAENW2D/graph.json","events_json":"https://pith.science/api/pith-number/GE64MTT34BPKXTIVHNXUAENW2D/events.json","paper":"https://pith.science/paper/GE64MTT3"},"agent_actions":{"view_html":"https://pith.science/pith/GE64MTT34BPKXTIVHNXUAENW2D","download_json":"https://pith.science/pith/GE64MTT34BPKXTIVHNXUAENW2D.json","view_paper":"https://pith.science/paper/GE64MTT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29076&json=true","fetch_graph":"https://pith.science/api/pith-number/GE64MTT34BPKXTIVHNXUAENW2D/graph.json","fetch_events":"https://pith.science/api/pith-number/GE64MTT34BPKXTIVHNXUAENW2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GE64MTT34BPKXTIVHNXUAENW2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GE64MTT34BPKXTIVHNXUAENW2D/action/storage_attestation","attest_author":"https://pith.science/pith/GE64MTT34BPKXTIVHNXUAENW2D/action/author_attestation","sign_citation":"https://pith.science/pith/GE64MTT34BPKXTIVHNXUAENW2D/action/citation_signature","submit_replication":"https://pith.science/pith/GE64MTT34BPKXTIVHNXUAENW2D/action/replication_record"}},"created_at":"2026-05-29T01:05:17.126839+00:00","updated_at":"2026-05-29T01:05:17.126839+00:00"}