{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XAZ7KIAKXRZF6EGWEL7V2PTHIC","short_pith_number":"pith:XAZ7KIAK","schema_version":"1.0","canonical_sha256":"b833f5200abc725f10d622ff5d3e67408f94cb29a9f03d0508cc79da64f0c7f2","source":{"kind":"arxiv","id":"2605.28360","version":1},"attestation_state":"computed","paper":{"title":"Prompt Codebooks: Discrete Compositional Optimization for Language Model Instruction Refinement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Brejesh Lall, Jyotirmoy Nath, Neeraj Kumar","submitted_at":"2026-05-27T11:57:12Z","abstract_excerpt":"Automatic prompt optimization (APO) has driven significant gains in LLM-based agentic workflows. However, existing methods treat each task's prompt as a monolithic, instance-blind string optimized through global edits, producing brittle updates and preventing the reuse of learned sub-behaviors. We propose Prompt Codebooks (PCO), a novel compositional prompt optimization framework that recasts APO as discrete learning over a finite vocabulary of natural-language instincts - atomic, reusable instruction units. PCO organizes prompt-construction knowledge in a discrete codebook and routes each inp"},"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":"2605.28360","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T11:57:12Z","cross_cats_sorted":[],"title_canon_sha256":"ef1f88a817e0de32a9733254243441902214e7f6017b454258d00151ccf6154d","abstract_canon_sha256":"6362930107172c3142f1de5f9ce3f8951d73ae6aa7d36145e2d7ed25d43dbfb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:15.855650Z","signature_b64":"WdcFB/oIh3PEOXaX6h+o6j5i/jsx5y98uwtsqidjrpD3XIqM8/F6WKRrPUOqvFylsJ301c0MM1LKwQ42THkhCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b833f5200abc725f10d622ff5d3e67408f94cb29a9f03d0508cc79da64f0c7f2","last_reissued_at":"2026-05-28T01:05:15.855205Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:15.855205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompt Codebooks: Discrete Compositional Optimization for Language Model Instruction Refinement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Brejesh Lall, Jyotirmoy Nath, Neeraj Kumar","submitted_at":"2026-05-27T11:57:12Z","abstract_excerpt":"Automatic prompt optimization (APO) has driven significant gains in LLM-based agentic workflows. However, existing methods treat each task's prompt as a monolithic, instance-blind string optimized through global edits, producing brittle updates and preventing the reuse of learned sub-behaviors. We propose Prompt Codebooks (PCO), a novel compositional prompt optimization framework that recasts APO as discrete learning over a finite vocabulary of natural-language instincts - atomic, reusable instruction units. PCO organizes prompt-construction knowledge in a discrete codebook and routes each inp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28360","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/2605.28360/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":"2605.28360","created_at":"2026-05-28T01:05:15.855281+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28360v1","created_at":"2026-05-28T01:05:15.855281+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28360","created_at":"2026-05-28T01:05:15.855281+00:00"},{"alias_kind":"pith_short_12","alias_value":"XAZ7KIAKXRZF","created_at":"2026-05-28T01:05:15.855281+00:00"},{"alias_kind":"pith_short_16","alias_value":"XAZ7KIAKXRZF6EGW","created_at":"2026-05-28T01:05:15.855281+00:00"},{"alias_kind":"pith_short_8","alias_value":"XAZ7KIAK","created_at":"2026-05-28T01:05:15.855281+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/XAZ7KIAKXRZF6EGWEL7V2PTHIC","json":"https://pith.science/pith/XAZ7KIAKXRZF6EGWEL7V2PTHIC.json","graph_json":"https://pith.science/api/pith-number/XAZ7KIAKXRZF6EGWEL7V2PTHIC/graph.json","events_json":"https://pith.science/api/pith-number/XAZ7KIAKXRZF6EGWEL7V2PTHIC/events.json","paper":"https://pith.science/paper/XAZ7KIAK"},"agent_actions":{"view_html":"https://pith.science/pith/XAZ7KIAKXRZF6EGWEL7V2PTHIC","download_json":"https://pith.science/pith/XAZ7KIAKXRZF6EGWEL7V2PTHIC.json","view_paper":"https://pith.science/paper/XAZ7KIAK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28360&json=true","fetch_graph":"https://pith.science/api/pith-number/XAZ7KIAKXRZF6EGWEL7V2PTHIC/graph.json","fetch_events":"https://pith.science/api/pith-number/XAZ7KIAKXRZF6EGWEL7V2PTHIC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XAZ7KIAKXRZF6EGWEL7V2PTHIC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XAZ7KIAKXRZF6EGWEL7V2PTHIC/action/storage_attestation","attest_author":"https://pith.science/pith/XAZ7KIAKXRZF6EGWEL7V2PTHIC/action/author_attestation","sign_citation":"https://pith.science/pith/XAZ7KIAKXRZF6EGWEL7V2PTHIC/action/citation_signature","submit_replication":"https://pith.science/pith/XAZ7KIAKXRZF6EGWEL7V2PTHIC/action/replication_record"}},"created_at":"2026-05-28T01:05:15.855281+00:00","updated_at":"2026-05-28T01:05:15.855281+00:00"}