{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4HUUNJ3WEAZ4XJ4WJDE6T2VB5T","short_pith_number":"pith:4HUUNJ3W","canonical_record":{"source":{"id":"2607.28268","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T14:21:55Z","cross_cats_sorted":[],"title_canon_sha256":"1f8e2115557d8a8d7fc3cd36f32d1d2bc3bd05ffa1c5bcf3be446230aa7dfd85","abstract_canon_sha256":"03f5e3bfc6cb70ddf0cb2f0d5cbf14c33991610cc673d9465d697f035a998f13"},"schema_version":"1.0"},"canonical_sha256":"e1e946a7762033cba79648c9e9eaa1ecd13c5f4975e0fb80e8ca6c1256460118","source":{"kind":"arxiv","id":"2607.28268","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28268","created_at":"2026-07-31T01:37:03Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28268v1","created_at":"2026-07-31T01:37:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28268","created_at":"2026-07-31T01:37:03Z"},{"alias_kind":"pith_short_12","alias_value":"4HUUNJ3WEAZ4","created_at":"2026-07-31T01:37:03Z"},{"alias_kind":"pith_short_16","alias_value":"4HUUNJ3WEAZ4XJ4W","created_at":"2026-07-31T01:37:03Z"},{"alias_kind":"pith_short_8","alias_value":"4HUUNJ3W","created_at":"2026-07-31T01:37:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4HUUNJ3WEAZ4XJ4WJDE6T2VB5T","target":"record","payload":{"canonical_record":{"source":{"id":"2607.28268","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T14:21:55Z","cross_cats_sorted":[],"title_canon_sha256":"1f8e2115557d8a8d7fc3cd36f32d1d2bc3bd05ffa1c5bcf3be446230aa7dfd85","abstract_canon_sha256":"03f5e3bfc6cb70ddf0cb2f0d5cbf14c33991610cc673d9465d697f035a998f13"},"schema_version":"1.0"},"canonical_sha256":"e1e946a7762033cba79648c9e9eaa1ecd13c5f4975e0fb80e8ca6c1256460118","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1e946a7762033cba79648c9e9eaa1ecd13c5f4975e0fb80e8ca6c1256460118","last_reissued_at":"2026-07-31T01:37:03.823127Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:37:03.823127Z"},"source_kind":"arxiv","source_id":"2607.28268","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":"2026-07-31T01:37:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y60ZBAguXbIDZgguvV2sDBwpDgqpTFzeSQj362RSCnk99cbZtLL2NYyPKyN/6xqDgW2kU70w4Msr4E5a3Y8TAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T06:03:28.850477Z"},"content_sha256":"4fa4171edf520f189a31f480360402df224b2c682c1670f02f398ea29092fefd","schema_version":"1.0","event_id":"sha256:4fa4171edf520f189a31f480360402df224b2c682c1670f02f398ea29092fefd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4HUUNJ3WEAZ4XJ4WJDE6T2VB5T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM-Guided Evolutionary Search for Constraint Model Reformulation to Improve Solver Efficiency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dimos Tsouros, Kostis Michailidis, Nguyen Dang, Tias Guns","submitted_at":"2026-07-30T14:21:55Z","abstract_excerpt":"Combinatorial problems appear in numerous industrial applications. A common approach is to formulate these problems as declarative constraint models that can subsequently be compiled to and solved by a range of back-end solvers. Recent work shows that Large Language Models (LLMs) can produce correct models from natural language, but even a correct model can be expensive to solve because performance remains sensitive to modelling choices. In this work, we investigate whether LLMs can automate performance-oriented model reformulation. Inspired by Automatic Heuristic Design (AHD), we use an evolu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28268","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/2607.28268/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":"2026-07-31T01:37:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Wuxql+yyKcRZ8APROUMrG5oSzk0i1tEj0xXw4u1Av+39xqx+HcmnOxFuvTVn1jsQQD1gEOZvxlhdksamf3SCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T06:03:28.850846Z"},"content_sha256":"7babacba40cdcba96e0b8c18161ce277b0ca62dfa614297f9b5165e7230b902f","schema_version":"1.0","event_id":"sha256:7babacba40cdcba96e0b8c18161ce277b0ca62dfa614297f9b5165e7230b902f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4HUUNJ3WEAZ4XJ4WJDE6T2VB5T/bundle.json","state_url":"https://pith.science/pith/4HUUNJ3WEAZ4XJ4WJDE6T2VB5T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4HUUNJ3WEAZ4XJ4WJDE6T2VB5T/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":"2026-08-19T06:03:28Z","links":{"resolver":"https://pith.science/pith/4HUUNJ3WEAZ4XJ4WJDE6T2VB5T","bundle":"https://pith.science/pith/4HUUNJ3WEAZ4XJ4WJDE6T2VB5T/bundle.json","state":"https://pith.science/pith/4HUUNJ3WEAZ4XJ4WJDE6T2VB5T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4HUUNJ3WEAZ4XJ4WJDE6T2VB5T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4HUUNJ3WEAZ4XJ4WJDE6T2VB5T","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":"03f5e3bfc6cb70ddf0cb2f0d5cbf14c33991610cc673d9465d697f035a998f13","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T14:21:55Z","title_canon_sha256":"1f8e2115557d8a8d7fc3cd36f32d1d2bc3bd05ffa1c5bcf3be446230aa7dfd85"},"schema_version":"1.0","source":{"id":"2607.28268","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28268","created_at":"2026-07-31T01:37:03Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28268v1","created_at":"2026-07-31T01:37:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28268","created_at":"2026-07-31T01:37:03Z"},{"alias_kind":"pith_short_12","alias_value":"4HUUNJ3WEAZ4","created_at":"2026-07-31T01:37:03Z"},{"alias_kind":"pith_short_16","alias_value":"4HUUNJ3WEAZ4XJ4W","created_at":"2026-07-31T01:37:03Z"},{"alias_kind":"pith_short_8","alias_value":"4HUUNJ3W","created_at":"2026-07-31T01:37:03Z"}],"graph_snapshots":[{"event_id":"sha256:7babacba40cdcba96e0b8c18161ce277b0ca62dfa614297f9b5165e7230b902f","target":"graph","created_at":"2026-07-31T01:37:03Z","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/2607.28268/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Combinatorial problems appear in numerous industrial applications. A common approach is to formulate these problems as declarative constraint models that can subsequently be compiled to and solved by a range of back-end solvers. Recent work shows that Large Language Models (LLMs) can produce correct models from natural language, but even a correct model can be expensive to solve because performance remains sensitive to modelling choices. In this work, we investigate whether LLMs can automate performance-oriented model reformulation. Inspired by Automatic Heuristic Design (AHD), we use an evolu","authors_text":"Dimos Tsouros, Kostis Michailidis, Nguyen Dang, Tias Guns","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T14:21:55Z","title":"LLM-Guided Evolutionary Search for Constraint Model Reformulation to Improve Solver Efficiency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28268","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":"sha256:4fa4171edf520f189a31f480360402df224b2c682c1670f02f398ea29092fefd","target":"record","created_at":"2026-07-31T01:37:03Z","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":"03f5e3bfc6cb70ddf0cb2f0d5cbf14c33991610cc673d9465d697f035a998f13","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T14:21:55Z","title_canon_sha256":"1f8e2115557d8a8d7fc3cd36f32d1d2bc3bd05ffa1c5bcf3be446230aa7dfd85"},"schema_version":"1.0","source":{"id":"2607.28268","kind":"arxiv","version":1}},"canonical_sha256":"e1e946a7762033cba79648c9e9eaa1ecd13c5f4975e0fb80e8ca6c1256460118","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1e946a7762033cba79648c9e9eaa1ecd13c5f4975e0fb80e8ca6c1256460118","first_computed_at":"2026-07-31T01:37:03.823127Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:37:03.823127Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.28268","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fa4171edf520f189a31f480360402df224b2c682c1670f02f398ea29092fefd","sha256:7babacba40cdcba96e0b8c18161ce277b0ca62dfa614297f9b5165e7230b902f"],"state_sha256":"9336af185923ecd093cdc62e3fa42037901a3e73bb28fa9303170dac13fc2622"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KT53STpAeypIfNrwEIo/rUclicHRrb19vdFV5IETOAPtSE3ja28U/pjOLgApYPv7g+0fdVGqjQ3jk4oDOchnCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T06:03:28.854693Z","bundle_sha256":"d9c8de4a4f87e57e6f587e7942d51642d451b7a90edb8b1ffc7ae94764b71671"}}