{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZGODUGLCPA5FSEMMIUKW4EXLSH","short_pith_number":"pith:ZGODUGLC","canonical_record":{"source":{"id":"2402.08702","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-13T16:38:01Z","cross_cats_sorted":["cs.AI","cs.HC","cs.RO"],"title_canon_sha256":"5a48b192366ec27d67d58ec19626bc75b6ada0702b303d614586b943d56141ce","abstract_canon_sha256":"a6c038b403259186330fab183d2742b9f1cb484f7ba4864031e5e22967b09b9f"},"schema_version":"1.0"},"canonical_sha256":"c99c3a1962783a59118c45156e12eb91d8153e3eda1ee09054ca71fc4364c3ce","source":{"kind":"arxiv","id":"2402.08702","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08702","created_at":"2026-07-05T09:15:08Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08702v4","created_at":"2026-07-05T09:15:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08702","created_at":"2026-07-05T09:15:08Z"},{"alias_kind":"pith_short_12","alias_value":"ZGODUGLCPA5F","created_at":"2026-07-05T09:15:08Z"},{"alias_kind":"pith_short_16","alias_value":"ZGODUGLCPA5FSEMM","created_at":"2026-07-05T09:15:08Z"},{"alias_kind":"pith_short_8","alias_value":"ZGODUGLC","created_at":"2026-07-05T09:15:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZGODUGLCPA5FSEMMIUKW4EXLSH","target":"record","payload":{"canonical_record":{"source":{"id":"2402.08702","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-13T16:38:01Z","cross_cats_sorted":["cs.AI","cs.HC","cs.RO"],"title_canon_sha256":"5a48b192366ec27d67d58ec19626bc75b6ada0702b303d614586b943d56141ce","abstract_canon_sha256":"a6c038b403259186330fab183d2742b9f1cb484f7ba4864031e5e22967b09b9f"},"schema_version":"1.0"},"canonical_sha256":"c99c3a1962783a59118c45156e12eb91d8153e3eda1ee09054ca71fc4364c3ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:08.502823Z","signature_b64":"BMaePS/skFs5DIrrGwbbhalkztSAOw5zlHtuySewr3YEsNT+2EC3RFTHGsb7TQfH0BwAS56e2JvO5QejtRt8Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c99c3a1962783a59118c45156e12eb91d8153e3eda1ee09054ca71fc4364c3ce","last_reissued_at":"2026-07-05T09:15:08.502401Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:08.502401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.08702","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:15:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zJZEbpcDeWuNBwe31a2DZhZJ6miaE1Z8gbYVfH3hQRKjt8AAbz5ZcZGOIngWcTDwwwXR5JF4bUCSTwevMxQ8Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:44:49.654922Z"},"content_sha256":"ae3182217f5536766dd09192045175d274bd39685e41af2781f2dfcfc3be9f8d","schema_version":"1.0","event_id":"sha256:ae3182217f5536766dd09192045175d274bd39685e41af2781f2dfcfc3be9f8d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZGODUGLCPA5FSEMMIUKW4EXLSH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based Sampling","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.RO"],"primary_cat":"cs.CL","authors_text":"Chuchu Fan, Jacob Arkin, Nicholas Roy, Yang Zhang, Yilun Hao, Yongchao Chen","submitted_at":"2024-02-13T16:38:01Z","abstract_excerpt":"Prompt optimization aims to find the best prompt to a large language model (LLM) for a given task. LLMs have been successfully used to help find and improve prompt candidates for single-step tasks. However, realistic tasks for agents are multi-step and introduce new challenges: (1) Prompt content is likely to be more extensive and complex, making it more difficult for LLMs to analyze errors, (2) the impact of an individual step is difficult to evaluate, and (3) different people may have varied preferences about task execution. While humans struggle to optimize prompts, they are good at providi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08702","kind":"arxiv","version":4},"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/2402.08702/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":"2026-07-05T09:15:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AVyoXUJIGBB65QIsUhGDmvg6KA3kWnR8Sof09tLtO9mxGHsx7hzBBmSV2FvNBNGA4+2qFl86NkuDRF5rxhWnCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:44:49.655425Z"},"content_sha256":"77d01c6a1d001f3192c7fced53d0923552442fa0dd92c61cd606a05b37f7e5bd","schema_version":"1.0","event_id":"sha256:77d01c6a1d001f3192c7fced53d0923552442fa0dd92c61cd606a05b37f7e5bd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZGODUGLCPA5FSEMMIUKW4EXLSH/bundle.json","state_url":"https://pith.science/pith/ZGODUGLCPA5FSEMMIUKW4EXLSH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZGODUGLCPA5FSEMMIUKW4EXLSH/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":"2026-08-04T17:44:49Z","links":{"resolver":"https://pith.science/pith/ZGODUGLCPA5FSEMMIUKW4EXLSH","bundle":"https://pith.science/pith/ZGODUGLCPA5FSEMMIUKW4EXLSH/bundle.json","state":"https://pith.science/pith/ZGODUGLCPA5FSEMMIUKW4EXLSH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZGODUGLCPA5FSEMMIUKW4EXLSH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZGODUGLCPA5FSEMMIUKW4EXLSH","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":"a6c038b403259186330fab183d2742b9f1cb484f7ba4864031e5e22967b09b9f","cross_cats_sorted":["cs.AI","cs.HC","cs.RO"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-13T16:38:01Z","title_canon_sha256":"5a48b192366ec27d67d58ec19626bc75b6ada0702b303d614586b943d56141ce"},"schema_version":"1.0","source":{"id":"2402.08702","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08702","created_at":"2026-07-05T09:15:08Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08702v4","created_at":"2026-07-05T09:15:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08702","created_at":"2026-07-05T09:15:08Z"},{"alias_kind":"pith_short_12","alias_value":"ZGODUGLCPA5F","created_at":"2026-07-05T09:15:08Z"},{"alias_kind":"pith_short_16","alias_value":"ZGODUGLCPA5FSEMM","created_at":"2026-07-05T09:15:08Z"},{"alias_kind":"pith_short_8","alias_value":"ZGODUGLC","created_at":"2026-07-05T09:15:08Z"}],"graph_snapshots":[{"event_id":"sha256:77d01c6a1d001f3192c7fced53d0923552442fa0dd92c61cd606a05b37f7e5bd","target":"graph","created_at":"2026-07-05T09:15:08Z","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/2402.08702/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prompt optimization aims to find the best prompt to a large language model (LLM) for a given task. LLMs have been successfully used to help find and improve prompt candidates for single-step tasks. However, realistic tasks for agents are multi-step and introduce new challenges: (1) Prompt content is likely to be more extensive and complex, making it more difficult for LLMs to analyze errors, (2) the impact of an individual step is difficult to evaluate, and (3) different people may have varied preferences about task execution. While humans struggle to optimize prompts, they are good at providi","authors_text":"Chuchu Fan, Jacob Arkin, Nicholas Roy, Yang Zhang, Yilun Hao, Yongchao Chen","cross_cats":["cs.AI","cs.HC","cs.RO"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-13T16:38:01Z","title":"PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08702","kind":"arxiv","version":4},"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:ae3182217f5536766dd09192045175d274bd39685e41af2781f2dfcfc3be9f8d","target":"record","created_at":"2026-07-05T09:15:08Z","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":"a6c038b403259186330fab183d2742b9f1cb484f7ba4864031e5e22967b09b9f","cross_cats_sorted":["cs.AI","cs.HC","cs.RO"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-13T16:38:01Z","title_canon_sha256":"5a48b192366ec27d67d58ec19626bc75b6ada0702b303d614586b943d56141ce"},"schema_version":"1.0","source":{"id":"2402.08702","kind":"arxiv","version":4}},"canonical_sha256":"c99c3a1962783a59118c45156e12eb91d8153e3eda1ee09054ca71fc4364c3ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c99c3a1962783a59118c45156e12eb91d8153e3eda1ee09054ca71fc4364c3ce","first_computed_at":"2026-07-05T09:15:08.502401Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:08.502401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BMaePS/skFs5DIrrGwbbhalkztSAOw5zlHtuySewr3YEsNT+2EC3RFTHGsb7TQfH0BwAS56e2JvO5QejtRt8Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:08.502823Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.08702","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae3182217f5536766dd09192045175d274bd39685e41af2781f2dfcfc3be9f8d","sha256:77d01c6a1d001f3192c7fced53d0923552442fa0dd92c61cd606a05b37f7e5bd"],"state_sha256":"8fbe88ee50a85a2e999cda81e25595ec9b7dab10ee1034ac3bf73995bea27bcf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vPc8kxeVPW2gHGvxnKZL6Amwa5yf0RDl4jYcG0+IwC0nTl2r9eKrW3Da28NMCC6iQAKWCdMM54Aods0GNEkBDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:44:49.659468Z","bundle_sha256":"36141c98eab6bc8273c80e15dd7f5f5d8a3f81a389ed99ccd3c4eaf0bb770497"}}