{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:M4S4SU6WLXW72RTFN4DQAV2MS6","short_pith_number":"pith:M4S4SU6W","canonical_record":{"source":{"id":"2407.12865","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-12T19:11:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"55d7cd8a0b04becdba402c651111a8f57aba9e1ada91b3868ee4b574c54344cd","abstract_canon_sha256":"27e3398d93b65c5e32a611bbbbde181ff3dfd4cf51ce912b993acf4a954019cd"},"schema_version":"1.0"},"canonical_sha256":"6725c953d65dedfd46656f0700574c978efc62fedc71aed4fac24dec81af2043","source":{"kind":"arxiv","id":"2407.12865","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12865","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12865v1","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12865","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"pith_short_12","alias_value":"M4S4SU6WLXW7","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"pith_short_16","alias_value":"M4S4SU6WLXW72RTF","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"pith_short_8","alias_value":"M4S4SU6W","created_at":"2026-07-05T08:45:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:M4S4SU6WLXW72RTFN4DQAV2MS6","target":"record","payload":{"canonical_record":{"source":{"id":"2407.12865","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-12T19:11:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"55d7cd8a0b04becdba402c651111a8f57aba9e1ada91b3868ee4b574c54344cd","abstract_canon_sha256":"27e3398d93b65c5e32a611bbbbde181ff3dfd4cf51ce912b993acf4a954019cd"},"schema_version":"1.0"},"canonical_sha256":"6725c953d65dedfd46656f0700574c978efc62fedc71aed4fac24dec81af2043","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:12.784858Z","signature_b64":"6esP38yHzv2h80zAL3IOue6Pp4iEkw7UbGYP0sstNGINAHXuWdy+8am1iH0SFyc4M1OeQ0jbXmd90LNwdKf5Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6725c953d65dedfd46656f0700574c978efc62fedc71aed4fac24dec81af2043","last_reissued_at":"2026-07-05T08:45:12.784395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:12.784395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.12865","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":"2026-07-05T08:45:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ge6OQVhs2aGxVC44JO+5TlpLOUO3CQ3PUa9IoLVvx8Tl3itFL2bicj4j8Ver8hfnleJHzsXMGdZdcAQjHXLLAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:09:25.882674Z"},"content_sha256":"469bcb6238ddafef4018b798dc554032a0463d4dfe64678c4771f4d34faf730f","schema_version":"1.0","event_id":"sha256:469bcb6238ddafef4018b798dc554032a0463d4dfe64678c4771f4d34faf730f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:M4S4SU6WLXW72RTFN4DQAV2MS6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GRAD-SUM: Leveraging Gradient Summarization for Optimal Prompt Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Derek Austin, Elliott Chartock","submitted_at":"2024-07-12T19:11:21Z","abstract_excerpt":"Prompt engineering for large language models (LLMs) is often a manual time-intensive process that involves generating, evaluating, and refining prompts iteratively to ensure high-quality outputs. While there has been work on automating prompt engineering, the solutions generally are either tuned to specific tasks with given answers or are quite costly. We introduce GRAD-SUM, a scalable and flexible method for automatic prompt engineering that builds on gradient-based optimization techniques. Our approach incorporates user-defined task descriptions and evaluation criteria, and features a novel "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12865","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/2407.12865/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":"2026-07-05T08:45:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pcfAWwQNUT2+MbGb3SxQxu2rjYwBKMRx23lk1o4Lqfjnbq/4AYwKA2scYepHetoB03txt5nA7EcfC1s/giHPAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:09:25.883046Z"},"content_sha256":"fbbd25ba9463db7c34509a073b876e53d00dd2f5af72ebf6eea5e70af1007a52","schema_version":"1.0","event_id":"sha256:fbbd25ba9463db7c34509a073b876e53d00dd2f5af72ebf6eea5e70af1007a52"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M4S4SU6WLXW72RTFN4DQAV2MS6/bundle.json","state_url":"https://pith.science/pith/M4S4SU6WLXW72RTFN4DQAV2MS6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M4S4SU6WLXW72RTFN4DQAV2MS6/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":"2026-07-07T11:09:25Z","links":{"resolver":"https://pith.science/pith/M4S4SU6WLXW72RTFN4DQAV2MS6","bundle":"https://pith.science/pith/M4S4SU6WLXW72RTFN4DQAV2MS6/bundle.json","state":"https://pith.science/pith/M4S4SU6WLXW72RTFN4DQAV2MS6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M4S4SU6WLXW72RTFN4DQAV2MS6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M4S4SU6WLXW72RTFN4DQAV2MS6","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":"27e3398d93b65c5e32a611bbbbde181ff3dfd4cf51ce912b993acf4a954019cd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-12T19:11:21Z","title_canon_sha256":"55d7cd8a0b04becdba402c651111a8f57aba9e1ada91b3868ee4b574c54344cd"},"schema_version":"1.0","source":{"id":"2407.12865","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12865","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12865v1","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12865","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"pith_short_12","alias_value":"M4S4SU6WLXW7","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"pith_short_16","alias_value":"M4S4SU6WLXW72RTF","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"pith_short_8","alias_value":"M4S4SU6W","created_at":"2026-07-05T08:45:12Z"}],"graph_snapshots":[{"event_id":"sha256:fbbd25ba9463db7c34509a073b876e53d00dd2f5af72ebf6eea5e70af1007a52","target":"graph","created_at":"2026-07-05T08:45:12Z","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/2407.12865/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prompt engineering for large language models (LLMs) is often a manual time-intensive process that involves generating, evaluating, and refining prompts iteratively to ensure high-quality outputs. While there has been work on automating prompt engineering, the solutions generally are either tuned to specific tasks with given answers or are quite costly. We introduce GRAD-SUM, a scalable and flexible method for automatic prompt engineering that builds on gradient-based optimization techniques. Our approach incorporates user-defined task descriptions and evaluation criteria, and features a novel ","authors_text":"Derek Austin, Elliott Chartock","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-12T19:11:21Z","title":"GRAD-SUM: Leveraging Gradient Summarization for Optimal Prompt Engineering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12865","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":"sha256:469bcb6238ddafef4018b798dc554032a0463d4dfe64678c4771f4d34faf730f","target":"record","created_at":"2026-07-05T08:45:12Z","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":"27e3398d93b65c5e32a611bbbbde181ff3dfd4cf51ce912b993acf4a954019cd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-12T19:11:21Z","title_canon_sha256":"55d7cd8a0b04becdba402c651111a8f57aba9e1ada91b3868ee4b574c54344cd"},"schema_version":"1.0","source":{"id":"2407.12865","kind":"arxiv","version":1}},"canonical_sha256":"6725c953d65dedfd46656f0700574c978efc62fedc71aed4fac24dec81af2043","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6725c953d65dedfd46656f0700574c978efc62fedc71aed4fac24dec81af2043","first_computed_at":"2026-07-05T08:45:12.784395Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:12.784395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6esP38yHzv2h80zAL3IOue6Pp4iEkw7UbGYP0sstNGINAHXuWdy+8am1iH0SFyc4M1OeQ0jbXmd90LNwdKf5Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:12.784858Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12865","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:469bcb6238ddafef4018b798dc554032a0463d4dfe64678c4771f4d34faf730f","sha256:fbbd25ba9463db7c34509a073b876e53d00dd2f5af72ebf6eea5e70af1007a52"],"state_sha256":"a0fe31217bd51e995e44fd8fe4539166ed6bc86eb4c308befa62313ffff18429"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SB/VpZ6hFS9/W8PlMNTzdoeRVer6/nXfIivcY+4bc0+ZVxcKAba06Teq7iPNaPAj3nrV8Yr3hnaX4zCy+OUNDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:09:25.884964Z","bundle_sha256":"34daf6b393ab3e511a7d0092b739fc5abc1b7080cea83c5c7fd73dc5fbb49793"}}