{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VNFKFKMLX4KHVGRGGVJLYKVRH7","short_pith_number":"pith:VNFKFKML","canonical_record":{"source":{"id":"2507.10326","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-14T14:34:15Z","cross_cats_sorted":[],"title_canon_sha256":"1e061094265ddab3e6ea8155090b53f5958c8bf4ccfe58b715cea698d288a65b","abstract_canon_sha256":"34181498d9ac0a24d138e99c81f9d271e211a4fb3c3d73bc950d050e7d4937d8"},"schema_version":"1.0"},"canonical_sha256":"ab4aa2a98bbf147a9a263552bc2ab13fcad02c127206b00ed0e2f165541d6b20","source":{"kind":"arxiv","id":"2507.10326","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10326","created_at":"2026-07-05T11:36:49Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10326v1","created_at":"2026-07-05T11:36:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10326","created_at":"2026-07-05T11:36:49Z"},{"alias_kind":"pith_short_12","alias_value":"VNFKFKMLX4KH","created_at":"2026-07-05T11:36:49Z"},{"alias_kind":"pith_short_16","alias_value":"VNFKFKMLX4KHVGRG","created_at":"2026-07-05T11:36:49Z"},{"alias_kind":"pith_short_8","alias_value":"VNFKFKML","created_at":"2026-07-05T11:36:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VNFKFKMLX4KHVGRGGVJLYKVRH7","target":"record","payload":{"canonical_record":{"source":{"id":"2507.10326","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-14T14:34:15Z","cross_cats_sorted":[],"title_canon_sha256":"1e061094265ddab3e6ea8155090b53f5958c8bf4ccfe58b715cea698d288a65b","abstract_canon_sha256":"34181498d9ac0a24d138e99c81f9d271e211a4fb3c3d73bc950d050e7d4937d8"},"schema_version":"1.0"},"canonical_sha256":"ab4aa2a98bbf147a9a263552bc2ab13fcad02c127206b00ed0e2f165541d6b20","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:49.571829Z","signature_b64":"maiQG6RcWLFDd914rJXVLJ6jbLBzNfetva/itOHT7ST7TQxehRSxJ9OGeggY7B9Z3Ld/80keoL/P6VM/reqUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab4aa2a98bbf147a9a263552bc2ab13fcad02c127206b00ed0e2f165541d6b20","last_reissued_at":"2026-07-05T11:36:49.571292Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:49.571292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.10326","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":"2026-07-05T11:36:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6KLO53XXizaZXMogMAM+sYsk/DUqphbBT1pKzqujXw6nHY1pIHsx30GjfUV5VBiZhzOI1dBPOG9Ev/zO/yJtDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:39:36.282499Z"},"content_sha256":"4fdd4154525b247128af32079c10c96a1b11d6ae10704153775ddfb37cfdcad2","schema_version":"1.0","event_id":"sha256:4fdd4154525b247128af32079c10c96a1b11d6ae10704153775ddfb37cfdcad2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VNFKFKMLX4KHVGRGGVJLYKVRH7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Grammar-Guided Evolutionary Search for Discrete Prompt Optimisation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aleksandar Milenovic, Alexandros Agapitos, David Lynch, Giorgio Cruciata, Goncalo Mordido, Hongmeng Song, Leonardo Custode, Minh-Khoi Pham, Muzhaffar Hazman, Pan Yue, Shweta Soundararajan, Wang Chao, Yucheng Shi","submitted_at":"2025-07-14T14:34:15Z","abstract_excerpt":"Prompt engineering has proven to be a crucial step in leveraging pretrained large language models (LLMs) in solving various real-world tasks. Numerous solutions have been proposed that seek to automate prompt engineering by using the model itself to edit prompts. However, the majority of state-of-the-art approaches are evaluated on tasks that require minimal prompt templates and on very large and highly capable LLMs. In contrast, solving complex tasks that require detailed information to be included in the prompt increases the amount of text that needs to be optimised. Furthermore, smaller mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10326","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/2507.10326/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":"2026-07-05T11:36:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rtoablA0HRQVq0Qwfn77AgFOgZY/SKCLHu0wVUJW8SKpWeNgsDNINTSI6HwVYetATF/DF/3QhUVeJS9zwyxHAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:39:36.283179Z"},"content_sha256":"454fba382da7ba286e78456923619e097a670aa286ba832c030a38a811cb9498","schema_version":"1.0","event_id":"sha256:454fba382da7ba286e78456923619e097a670aa286ba832c030a38a811cb9498"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VNFKFKMLX4KHVGRGGVJLYKVRH7/bundle.json","state_url":"https://pith.science/pith/VNFKFKMLX4KHVGRGGVJLYKVRH7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VNFKFKMLX4KHVGRGGVJLYKVRH7/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":"2026-08-07T10:39:36Z","links":{"resolver":"https://pith.science/pith/VNFKFKMLX4KHVGRGGVJLYKVRH7","bundle":"https://pith.science/pith/VNFKFKMLX4KHVGRGGVJLYKVRH7/bundle.json","state":"https://pith.science/pith/VNFKFKMLX4KHVGRGGVJLYKVRH7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VNFKFKMLX4KHVGRGGVJLYKVRH7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VNFKFKMLX4KHVGRGGVJLYKVRH7","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":"34181498d9ac0a24d138e99c81f9d271e211a4fb3c3d73bc950d050e7d4937d8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-14T14:34:15Z","title_canon_sha256":"1e061094265ddab3e6ea8155090b53f5958c8bf4ccfe58b715cea698d288a65b"},"schema_version":"1.0","source":{"id":"2507.10326","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10326","created_at":"2026-07-05T11:36:49Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10326v1","created_at":"2026-07-05T11:36:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10326","created_at":"2026-07-05T11:36:49Z"},{"alias_kind":"pith_short_12","alias_value":"VNFKFKMLX4KH","created_at":"2026-07-05T11:36:49Z"},{"alias_kind":"pith_short_16","alias_value":"VNFKFKMLX4KHVGRG","created_at":"2026-07-05T11:36:49Z"},{"alias_kind":"pith_short_8","alias_value":"VNFKFKML","created_at":"2026-07-05T11:36:49Z"}],"graph_snapshots":[{"event_id":"sha256:454fba382da7ba286e78456923619e097a670aa286ba832c030a38a811cb9498","target":"graph","created_at":"2026-07-05T11:36:49Z","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/2507.10326/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prompt engineering has proven to be a crucial step in leveraging pretrained large language models (LLMs) in solving various real-world tasks. Numerous solutions have been proposed that seek to automate prompt engineering by using the model itself to edit prompts. However, the majority of state-of-the-art approaches are evaluated on tasks that require minimal prompt templates and on very large and highly capable LLMs. In contrast, solving complex tasks that require detailed information to be included in the prompt increases the amount of text that needs to be optimised. Furthermore, smaller mod","authors_text":"Aleksandar Milenovic, Alexandros Agapitos, David Lynch, Giorgio Cruciata, Goncalo Mordido, Hongmeng Song, Leonardo Custode, Minh-Khoi Pham, Muzhaffar Hazman, Pan Yue, Shweta Soundararajan, Wang Chao, Yucheng Shi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-14T14:34:15Z","title":"Grammar-Guided Evolutionary Search for Discrete Prompt Optimisation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10326","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":"sha256:4fdd4154525b247128af32079c10c96a1b11d6ae10704153775ddfb37cfdcad2","target":"record","created_at":"2026-07-05T11:36:49Z","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":"34181498d9ac0a24d138e99c81f9d271e211a4fb3c3d73bc950d050e7d4937d8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-14T14:34:15Z","title_canon_sha256":"1e061094265ddab3e6ea8155090b53f5958c8bf4ccfe58b715cea698d288a65b"},"schema_version":"1.0","source":{"id":"2507.10326","kind":"arxiv","version":1}},"canonical_sha256":"ab4aa2a98bbf147a9a263552bc2ab13fcad02c127206b00ed0e2f165541d6b20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab4aa2a98bbf147a9a263552bc2ab13fcad02c127206b00ed0e2f165541d6b20","first_computed_at":"2026-07-05T11:36:49.571292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:49.571292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"maiQG6RcWLFDd914rJXVLJ6jbLBzNfetva/itOHT7ST7TQxehRSxJ9OGeggY7B9Z3Ld/80keoL/P6VM/reqUCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:49.571829Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.10326","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fdd4154525b247128af32079c10c96a1b11d6ae10704153775ddfb37cfdcad2","sha256:454fba382da7ba286e78456923619e097a670aa286ba832c030a38a811cb9498"],"state_sha256":"8baae6aa706e216fb3ac56e02d9068c4e8ce6525b26dc2d87ac805bc70ee0113"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F0mNj861q6UPQmN4bBp75Xkb4fU1ktRmkkDbh1GaUb2GDLQslifnMupgNwBg0vHy70UGAxsf69FqfrVIXI7rBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T10:39:36.288457Z","bundle_sha256":"d3462d4cca48eb8f84197fd206ce70e7a94ec765e5465cd72f439c8374ed6542"}}