{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PA4N2CQA7R6ISG2RYZIDCKAN2Y","short_pith_number":"pith:PA4N2CQA","canonical_record":{"source":{"id":"2410.08696","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-11T10:34:28Z","cross_cats_sorted":[],"title_canon_sha256":"d51e48435e8822a93f04db0a8ed7b997924931b38c73bc6bea780b844e6e9867","abstract_canon_sha256":"cdafd0ffb1b0458c647336e2401f7c7bd1da3553da947f131088a9b038246d4f"},"schema_version":"1.0"},"canonical_sha256":"7838dd0a00fc7c891b51c65031280dd61d7cabacd06fecb0eef9aaa2c773249a","source":{"kind":"arxiv","id":"2410.08696","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08696","created_at":"2026-07-05T09:19:16Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08696v1","created_at":"2026-07-05T09:19:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08696","created_at":"2026-07-05T09:19:16Z"},{"alias_kind":"pith_short_12","alias_value":"PA4N2CQA7R6I","created_at":"2026-07-05T09:19:16Z"},{"alias_kind":"pith_short_16","alias_value":"PA4N2CQA7R6ISG2R","created_at":"2026-07-05T09:19:16Z"},{"alias_kind":"pith_short_8","alias_value":"PA4N2CQA","created_at":"2026-07-05T09:19:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PA4N2CQA7R6ISG2RYZIDCKAN2Y","target":"record","payload":{"canonical_record":{"source":{"id":"2410.08696","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-11T10:34:28Z","cross_cats_sorted":[],"title_canon_sha256":"d51e48435e8822a93f04db0a8ed7b997924931b38c73bc6bea780b844e6e9867","abstract_canon_sha256":"cdafd0ffb1b0458c647336e2401f7c7bd1da3553da947f131088a9b038246d4f"},"schema_version":"1.0"},"canonical_sha256":"7838dd0a00fc7c891b51c65031280dd61d7cabacd06fecb0eef9aaa2c773249a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:16.245169Z","signature_b64":"zMvxeBaSdo8s1zdwya95WX/EyiUMNp4gTjq5gD5UdeEx9AIRttRHWBz+Y4M/TIb2mB3dr+hVQg6RWu8mOAVSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7838dd0a00fc7c891b51c65031280dd61d7cabacd06fecb0eef9aaa2c773249a","last_reissued_at":"2026-07-05T09:19:16.244756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:16.244756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.08696","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":"2026-07-05T09:19:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5ExE5Z6cqtFdIMFgqAfi9fVBju/UAHJoIrrJ+egvi+AKY3+GMK0pmh29bqXL0z55mf/UhS9Odu+zQgfJaAAYBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:16:40.815059Z"},"content_sha256":"fe0565faba99f9063c993bd8c361d135649d53bc15dff6b819d74d7dc9b0d3d3","schema_version":"1.0","event_id":"sha256:fe0565faba99f9063c993bd8c361d135649d53bc15dff6b819d74d7dc9b0d3d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PA4N2CQA7R6ISG2RYZIDCKAN2Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AMPO: Automatic Multi-Branched Prompt Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anbang Hu, Bin Benjamin Zhu, Jian-Guang Lou, Junyan Chen, Linjun Yang, Sheng Yang, Xiaodi Sun, Yan Gao, Yuan Fang, Yunsong Li, Yurong Wu, Zhiming Ding, Zineng Zhou","submitted_at":"2024-10-11T10:34:28Z","abstract_excerpt":"Prompt engineering is very important to enhance the performance of large language models (LLMs). When dealing with complex issues, prompt engineers tend to distill multiple patterns from examples and inject relevant solutions to optimize the prompts, achieving satisfying results. However, existing automatic prompt optimization techniques are only limited to producing single flow instructions, struggling with handling diverse patterns. In this paper, we present AMPO, an automatic prompt optimization method that can iteratively develop a multi-branched prompt using failure cases as feedback. Our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08696","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/2410.08696/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":"2026-07-05T09:19:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BqLeL+lrRrgjNMjH97u3Qi4p24vJgLuTHkdQoUIdljDsPb5AZ1MJ9KNIHGv+HbI4eTiYV1emEvmy91pbrL3iDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:16:40.815487Z"},"content_sha256":"ac6a7a54aa19b3eaa8dbe1e5d1d9af4d7acd87fc87e7d75782385b0d45912a99","schema_version":"1.0","event_id":"sha256:ac6a7a54aa19b3eaa8dbe1e5d1d9af4d7acd87fc87e7d75782385b0d45912a99"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PA4N2CQA7R6ISG2RYZIDCKAN2Y/bundle.json","state_url":"https://pith.science/pith/PA4N2CQA7R6ISG2RYZIDCKAN2Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PA4N2CQA7R6ISG2RYZIDCKAN2Y/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":"2026-07-07T05:16:40Z","links":{"resolver":"https://pith.science/pith/PA4N2CQA7R6ISG2RYZIDCKAN2Y","bundle":"https://pith.science/pith/PA4N2CQA7R6ISG2RYZIDCKAN2Y/bundle.json","state":"https://pith.science/pith/PA4N2CQA7R6ISG2RYZIDCKAN2Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PA4N2CQA7R6ISG2RYZIDCKAN2Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PA4N2CQA7R6ISG2RYZIDCKAN2Y","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":"cdafd0ffb1b0458c647336e2401f7c7bd1da3553da947f131088a9b038246d4f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-11T10:34:28Z","title_canon_sha256":"d51e48435e8822a93f04db0a8ed7b997924931b38c73bc6bea780b844e6e9867"},"schema_version":"1.0","source":{"id":"2410.08696","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08696","created_at":"2026-07-05T09:19:16Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08696v1","created_at":"2026-07-05T09:19:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08696","created_at":"2026-07-05T09:19:16Z"},{"alias_kind":"pith_short_12","alias_value":"PA4N2CQA7R6I","created_at":"2026-07-05T09:19:16Z"},{"alias_kind":"pith_short_16","alias_value":"PA4N2CQA7R6ISG2R","created_at":"2026-07-05T09:19:16Z"},{"alias_kind":"pith_short_8","alias_value":"PA4N2CQA","created_at":"2026-07-05T09:19:16Z"}],"graph_snapshots":[{"event_id":"sha256:ac6a7a54aa19b3eaa8dbe1e5d1d9af4d7acd87fc87e7d75782385b0d45912a99","target":"graph","created_at":"2026-07-05T09:19:16Z","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/2410.08696/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prompt engineering is very important to enhance the performance of large language models (LLMs). When dealing with complex issues, prompt engineers tend to distill multiple patterns from examples and inject relevant solutions to optimize the prompts, achieving satisfying results. However, existing automatic prompt optimization techniques are only limited to producing single flow instructions, struggling with handling diverse patterns. In this paper, we present AMPO, an automatic prompt optimization method that can iteratively develop a multi-branched prompt using failure cases as feedback. Our","authors_text":"Anbang Hu, Bin Benjamin Zhu, Jian-Guang Lou, Junyan Chen, Linjun Yang, Sheng Yang, Xiaodi Sun, Yan Gao, Yuan Fang, Yunsong Li, Yurong Wu, Zhiming Ding, Zineng Zhou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-11T10:34:28Z","title":"AMPO: Automatic Multi-Branched Prompt Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08696","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:fe0565faba99f9063c993bd8c361d135649d53bc15dff6b819d74d7dc9b0d3d3","target":"record","created_at":"2026-07-05T09:19:16Z","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":"cdafd0ffb1b0458c647336e2401f7c7bd1da3553da947f131088a9b038246d4f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-11T10:34:28Z","title_canon_sha256":"d51e48435e8822a93f04db0a8ed7b997924931b38c73bc6bea780b844e6e9867"},"schema_version":"1.0","source":{"id":"2410.08696","kind":"arxiv","version":1}},"canonical_sha256":"7838dd0a00fc7c891b51c65031280dd61d7cabacd06fecb0eef9aaa2c773249a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7838dd0a00fc7c891b51c65031280dd61d7cabacd06fecb0eef9aaa2c773249a","first_computed_at":"2026-07-05T09:19:16.244756Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:16.244756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zMvxeBaSdo8s1zdwya95WX/EyiUMNp4gTjq5gD5UdeEx9AIRttRHWBz+Y4M/TIb2mB3dr+hVQg6RWu8mOAVSAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:16.245169Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08696","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe0565faba99f9063c993bd8c361d135649d53bc15dff6b819d74d7dc9b0d3d3","sha256:ac6a7a54aa19b3eaa8dbe1e5d1d9af4d7acd87fc87e7d75782385b0d45912a99"],"state_sha256":"ff5028a971785d4f2e162be08ffca118e616d177d1c6c6c1a944f3fea3c12bea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fOJ1ZQaA/43Myo12tngG5jjzdqJp4JvyMSptsc31w1oVGbrUE68oO9+D97Oo3VrRWB85LIPhPEaOp8P0qtvFCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:16:40.817832Z","bundle_sha256":"965bc3b15c5db22fa2250e45ea60aee8efdd7fb7d2e260193c6840ed8eddef8d"}}