{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XUPCXYLYCI2ADMWSND3PLOPIQI","short_pith_number":"pith:XUPCXYLY","canonical_record":{"source":{"id":"2507.18618","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T17:54:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2890f729f0139fa184e9e3db3d01a0d16513ec920b35e9c39ea009221e746ecf","abstract_canon_sha256":"1a3a621b811ac430b7ee2c6b3b09d086f19af99fc2ea4ad8af47e7af162d876b"},"schema_version":"1.0"},"canonical_sha256":"bd1e2be178123401b2d268f6f5b9e8820d5666933f5efca532ec26c1de6c224a","source":{"kind":"arxiv","id":"2507.18618","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.18618","created_at":"2026-07-05T11:42:51Z"},{"alias_kind":"arxiv_version","alias_value":"2507.18618v1","created_at":"2026-07-05T11:42:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18618","created_at":"2026-07-05T11:42:51Z"},{"alias_kind":"pith_short_12","alias_value":"XUPCXYLYCI2A","created_at":"2026-07-05T11:42:51Z"},{"alias_kind":"pith_short_16","alias_value":"XUPCXYLYCI2ADMWS","created_at":"2026-07-05T11:42:51Z"},{"alias_kind":"pith_short_8","alias_value":"XUPCXYLY","created_at":"2026-07-05T11:42:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XUPCXYLYCI2ADMWSND3PLOPIQI","target":"record","payload":{"canonical_record":{"source":{"id":"2507.18618","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T17:54:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2890f729f0139fa184e9e3db3d01a0d16513ec920b35e9c39ea009221e746ecf","abstract_canon_sha256":"1a3a621b811ac430b7ee2c6b3b09d086f19af99fc2ea4ad8af47e7af162d876b"},"schema_version":"1.0"},"canonical_sha256":"bd1e2be178123401b2d268f6f5b9e8820d5666933f5efca532ec26c1de6c224a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:51.159269Z","signature_b64":"mEMtJCR7ObkaG4Yas4+R6wW2FXErydv37RQKyRT5oj4Zd4fjbqU5NZ+m/RTYqGAJFrSmirAK8AmA8Id+DA9iCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd1e2be178123401b2d268f6f5b9e8820d5666933f5efca532ec26c1de6c224a","last_reissued_at":"2026-07-05T11:42:51.158774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:51.158774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.18618","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:42:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZLBOr2A/HHa4d58GtwkvEsf/ql98bxKDlbilOCl9hD6bLYEqiyc2MjrI5oE+t3NkUcXf8GsDVyzHiw62zpOtBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:04:12.475542Z"},"content_sha256":"923a58644004392addd502954f4eee8b643bee5812e7f7c2791229528eb7f622","schema_version":"1.0","event_id":"sha256:923a58644004392addd502954f4eee8b643bee5812e7f7c2791229528eb7f622"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XUPCXYLYCI2ADMWSND3PLOPIQI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TRPrompt: Bootstrapping Query-Aware Prompt Optimization from Textual Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andreea Nica, Ivan Zakazov, Nicolas Mario Baldwin, Robert West, Saibo Geng","submitted_at":"2025-07-24T17:54:44Z","abstract_excerpt":"Prompt optimization improves the reasoning abilities of large language models (LLMs) without requiring parameter updates to the target model. Following heuristic-based \"Think step by step\" approaches, the field has evolved in two main directions: while one group of methods uses textual feedback to elicit improved prompts from general-purpose LLMs in a training-free way, a concurrent line of research relies on numerical rewards to train a special prompt model, tailored for providing optimal prompts to the target model. In this paper, we introduce the Textual Reward Prompt framework (TRPrompt), "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18618","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/2507.18618/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:42:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k7OXuhMUMoLohzqrnpjZmu7eKFctD+i62Kw32kPomd2RG84M8+3093/egRHnaahJEKwYh/WMzcpmtFWwtEnbBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:04:12.475917Z"},"content_sha256":"fae904e26afcfeec941c79e1dd37a20e6ae3868ee0cfede1021ecf85f2eef103","schema_version":"1.0","event_id":"sha256:fae904e26afcfeec941c79e1dd37a20e6ae3868ee0cfede1021ecf85f2eef103"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XUPCXYLYCI2ADMWSND3PLOPIQI/bundle.json","state_url":"https://pith.science/pith/XUPCXYLYCI2ADMWSND3PLOPIQI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XUPCXYLYCI2ADMWSND3PLOPIQI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T05:04:12Z","links":{"resolver":"https://pith.science/pith/XUPCXYLYCI2ADMWSND3PLOPIQI","bundle":"https://pith.science/pith/XUPCXYLYCI2ADMWSND3PLOPIQI/bundle.json","state":"https://pith.science/pith/XUPCXYLYCI2ADMWSND3PLOPIQI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XUPCXYLYCI2ADMWSND3PLOPIQI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XUPCXYLYCI2ADMWSND3PLOPIQI","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":"1a3a621b811ac430b7ee2c6b3b09d086f19af99fc2ea4ad8af47e7af162d876b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T17:54:44Z","title_canon_sha256":"2890f729f0139fa184e9e3db3d01a0d16513ec920b35e9c39ea009221e746ecf"},"schema_version":"1.0","source":{"id":"2507.18618","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.18618","created_at":"2026-07-05T11:42:51Z"},{"alias_kind":"arxiv_version","alias_value":"2507.18618v1","created_at":"2026-07-05T11:42:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18618","created_at":"2026-07-05T11:42:51Z"},{"alias_kind":"pith_short_12","alias_value":"XUPCXYLYCI2A","created_at":"2026-07-05T11:42:51Z"},{"alias_kind":"pith_short_16","alias_value":"XUPCXYLYCI2ADMWS","created_at":"2026-07-05T11:42:51Z"},{"alias_kind":"pith_short_8","alias_value":"XUPCXYLY","created_at":"2026-07-05T11:42:51Z"}],"graph_snapshots":[{"event_id":"sha256:fae904e26afcfeec941c79e1dd37a20e6ae3868ee0cfede1021ecf85f2eef103","target":"graph","created_at":"2026-07-05T11:42:51Z","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/2507.18618/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prompt optimization improves the reasoning abilities of large language models (LLMs) without requiring parameter updates to the target model. Following heuristic-based \"Think step by step\" approaches, the field has evolved in two main directions: while one group of methods uses textual feedback to elicit improved prompts from general-purpose LLMs in a training-free way, a concurrent line of research relies on numerical rewards to train a special prompt model, tailored for providing optimal prompts to the target model. In this paper, we introduce the Textual Reward Prompt framework (TRPrompt), ","authors_text":"Andreea Nica, Ivan Zakazov, Nicolas Mario Baldwin, Robert West, Saibo Geng","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T17:54:44Z","title":"TRPrompt: Bootstrapping Query-Aware Prompt Optimization from Textual Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18618","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":"sha256:923a58644004392addd502954f4eee8b643bee5812e7f7c2791229528eb7f622","target":"record","created_at":"2026-07-05T11:42:51Z","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":"1a3a621b811ac430b7ee2c6b3b09d086f19af99fc2ea4ad8af47e7af162d876b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T17:54:44Z","title_canon_sha256":"2890f729f0139fa184e9e3db3d01a0d16513ec920b35e9c39ea009221e746ecf"},"schema_version":"1.0","source":{"id":"2507.18618","kind":"arxiv","version":1}},"canonical_sha256":"bd1e2be178123401b2d268f6f5b9e8820d5666933f5efca532ec26c1de6c224a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd1e2be178123401b2d268f6f5b9e8820d5666933f5efca532ec26c1de6c224a","first_computed_at":"2026-07-05T11:42:51.158774Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:51.158774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mEMtJCR7ObkaG4Yas4+R6wW2FXErydv37RQKyRT5oj4Zd4fjbqU5NZ+m/RTYqGAJFrSmirAK8AmA8Id+DA9iCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:51.159269Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.18618","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:923a58644004392addd502954f4eee8b643bee5812e7f7c2791229528eb7f622","sha256:fae904e26afcfeec941c79e1dd37a20e6ae3868ee0cfede1021ecf85f2eef103"],"state_sha256":"101ec1a6d048eff48bb4a9a65a804ce0e00314c98f0a750c078351f8d41d070a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mhiVHZ2I3qX+CSXWSFbTleW9nKxaxlAZbtGKaBqiBKWkvuAD/WkAIRWWMn90f5zz0QlZtIUa2HPrHFPGM+x4Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:04:12.477867Z","bundle_sha256":"15d1ddc41f9706e4c50620eaa99802eb166676410c5e9265739207d4bdb7ce40"}}