{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OJFGO247KHCGU2TJXOUEL7AOBE","short_pith_number":"pith:OJFGO247","canonical_record":{"source":{"id":"2608.13333","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-13T15:01:03Z","cross_cats_sorted":[],"title_canon_sha256":"23397bf63269f33874790005330d0061d1a93a27715ddc0e3155f6ba0f9a3913","abstract_canon_sha256":"93b41aa344d3f083af3e3a7314a971443d21529330e087d015d91ea4b6970a4c"},"schema_version":"1.0"},"canonical_sha256":"724a676b9f51c46a6a69bba845fc0e090fa254d5fbcba371b56697d98104e48a","source":{"kind":"arxiv","id":"2608.13333","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.13333","created_at":"2026-08-14T01:04:14Z"},{"alias_kind":"arxiv_version","alias_value":"2608.13333v1","created_at":"2026-08-14T01:04:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13333","created_at":"2026-08-14T01:04:14Z"},{"alias_kind":"pith_short_12","alias_value":"OJFGO247KHCG","created_at":"2026-08-14T01:04:14Z"},{"alias_kind":"pith_short_16","alias_value":"OJFGO247KHCGU2TJ","created_at":"2026-08-14T01:04:14Z"},{"alias_kind":"pith_short_8","alias_value":"OJFGO247","created_at":"2026-08-14T01:04:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OJFGO247KHCGU2TJXOUEL7AOBE","target":"record","payload":{"canonical_record":{"source":{"id":"2608.13333","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-13T15:01:03Z","cross_cats_sorted":[],"title_canon_sha256":"23397bf63269f33874790005330d0061d1a93a27715ddc0e3155f6ba0f9a3913","abstract_canon_sha256":"93b41aa344d3f083af3e3a7314a971443d21529330e087d015d91ea4b6970a4c"},"schema_version":"1.0"},"canonical_sha256":"724a676b9f51c46a6a69bba845fc0e090fa254d5fbcba371b56697d98104e48a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T01:04:14.232549Z","signature_b64":"vv94XmhzAAJTg+HsKw0/Nj0fPXoppbRyYS+CMLc9IMiBxCiWMowARML3K7eDy9AIRPRjOHjCyWx6KqKDG2HfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"724a676b9f51c46a6a69bba845fc0e090fa254d5fbcba371b56697d98104e48a","last_reissued_at":"2026-08-14T01:04:14.230964Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T01:04:14.230964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.13333","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":"2026-08-14T01:04:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2hKbd4BW6rilFPXhfkhRIE4dmmndqAXRWOwON4p/tP8N2BBVylnaFf3SAUYaOgS1gkNYAOQAqM6IL/BB9MdtCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T22:12:01.142882Z"},"content_sha256":"280bc2bb01dfeb6c3174cd255588bba8928cb97ab483d445b69b2867fa0d1591","schema_version":"1.0","event_id":"sha256:280bc2bb01dfeb6c3174cd255588bba8928cb97ab483d445b69b2867fa0d1591"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OJFGO247KHCGU2TJXOUEL7AOBE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM-Guided Graph Generation for Structure-Based Local Improvement Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hai Xia, Stefan Szeider, Vaidyanathan Peruvemba Ramaswamy","submitted_at":"2026-08-13T15:01:03Z","abstract_excerpt":"Large neighborhood search normally selects a random subset of decision variables for iterative optimization. For efficiently solving different problems, researchers tend to design variable selection strategies by taking into account structural features from different domains. In this paper, we build an automatic pipeline that is problem-agnostic to all problems in the MiniZinc format. By prompting an LLM with our semantic guidelines, we guide the LLM to produce a graph generator that maps any instance of a problem type to a uniform weighted graph, where nodes represent decision variables and e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13333","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/2608.13333/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":"2026-08-14T01:04:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ZFIbNC+NDI3nJx5mgxnFaEE5Byxz6H9RBO8O6N0aDMQ0Lw96ZBV0+OkezC5vze4N6G22FkqVkAeB1Fb+2RPAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T22:12:01.143392Z"},"content_sha256":"467bdf248d211db89053c2e2a5a19a0198852c1c86a0c6f092ad0072646ec621","schema_version":"1.0","event_id":"sha256:467bdf248d211db89053c2e2a5a19a0198852c1c86a0c6f092ad0072646ec621"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:OJFGO247KHCGU2TJXOUEL7AOBE","target":"integrity","payload":{"note":"Identifier '10.1007/978-3-031-3402' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","snippet":"Syu - Ning Johnn, Victor - Alexandru Darvariu, Julia Handl, and J \\\" o rg Kalcsics. GRAPH reinforcement learning for operator selection in the ALNS metaheuristic. In Bernab \\' e Dorronsoro, Francisco Chicano, Gr \\' e goire Danoy, and El - G","arxiv_id":"2608.13333","detector":"doi_compliance","evidence":{"doi":"10.1007/978-3-031-3402","arxiv_id":null,"ref_index":8,"raw_excerpt":"Syu - Ning Johnn, Victor - Alexandru Darvariu, Julia Handl, and J \\\" o rg Kalcsics. GRAPH reinforcement learning for operator selection in the ALNS metaheuristic. In Bernab \\' e Dorronsoro, Francisco Chicano, Gr \\' e goire Danoy, and El - Ghazali Talbi, editors, Optimization and Learning - 6th International Conference, OLA 2023, Malaga, Spain, May 3-5, 2023, Proceedings , volume 1824 of Communicat","parse_status":"well_formed","verdict_class":"cross_source","checked_sources":["crossref_by_doi","openalex_by_doi","doi_org_head"],"resolution_status":"hard_miss"},"severity":"critical","ref_index":8,"audited_at":"2026-08-14T13:38:15.768856Z","event_type":"pith.integrity.v1","detected_doi":"10.1007/978-3-031-3402","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"unresolvable_identifier","evidence_hash":"460e246782d8cfa1d8aaab2fad5f811c0a26d3cddd5f86bac8ba905f4638c883","paper_version":1,"verdict_class":"cross_source","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":19717,"payload_sha256":"0a7c6051be4ba8acec6aa7f5a9c1ef4578cb44829aa99f98bf82c6f67ba1ff37","signature_b64":"4p9hT1uDG5Z5oXElA+Av9Hoa40Y7NBnrF8ij+0u6H8x+oHt1VwUDGaTH0s5aKlAN7UJp5rW6U9m4vU3etLy2Bg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-14T13:38:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dohE7CyhVmACLOmGSbsiNLfKI2jBpn8RV6624im1chR5GIN1wqpn90kCbyAw/0vU42UuFvS8JzNrUiMAT+o3DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T22:12:01.145654Z"},"content_sha256":"58f9a5c24426e40d3dcf7c09b23029a5cf2674dec0a7fd01ced0e606a6cd0125","schema_version":"1.0","event_id":"sha256:58f9a5c24426e40d3dcf7c09b23029a5cf2674dec0a7fd01ced0e606a6cd0125"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OJFGO247KHCGU2TJXOUEL7AOBE/bundle.json","state_url":"https://pith.science/pith/OJFGO247KHCGU2TJXOUEL7AOBE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OJFGO247KHCGU2TJXOUEL7AOBE/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":"2026-08-14T22:12:01Z","links":{"resolver":"https://pith.science/pith/OJFGO247KHCGU2TJXOUEL7AOBE","bundle":"https://pith.science/pith/OJFGO247KHCGU2TJXOUEL7AOBE/bundle.json","state":"https://pith.science/pith/OJFGO247KHCGU2TJXOUEL7AOBE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OJFGO247KHCGU2TJXOUEL7AOBE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OJFGO247KHCGU2TJXOUEL7AOBE","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"93b41aa344d3f083af3e3a7314a971443d21529330e087d015d91ea4b6970a4c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-13T15:01:03Z","title_canon_sha256":"23397bf63269f33874790005330d0061d1a93a27715ddc0e3155f6ba0f9a3913"},"schema_version":"1.0","source":{"id":"2608.13333","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.13333","created_at":"2026-08-14T01:04:14Z"},{"alias_kind":"arxiv_version","alias_value":"2608.13333v1","created_at":"2026-08-14T01:04:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13333","created_at":"2026-08-14T01:04:14Z"},{"alias_kind":"pith_short_12","alias_value":"OJFGO247KHCG","created_at":"2026-08-14T01:04:14Z"},{"alias_kind":"pith_short_16","alias_value":"OJFGO247KHCGU2TJ","created_at":"2026-08-14T01:04:14Z"},{"alias_kind":"pith_short_8","alias_value":"OJFGO247","created_at":"2026-08-14T01:04:14Z"}],"graph_snapshots":[{"event_id":"sha256:467bdf248d211db89053c2e2a5a19a0198852c1c86a0c6f092ad0072646ec621","target":"graph","created_at":"2026-08-14T01:04:14Z","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/2608.13333/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large neighborhood search normally selects a random subset of decision variables for iterative optimization. For efficiently solving different problems, researchers tend to design variable selection strategies by taking into account structural features from different domains. In this paper, we build an automatic pipeline that is problem-agnostic to all problems in the MiniZinc format. By prompting an LLM with our semantic guidelines, we guide the LLM to produce a graph generator that maps any instance of a problem type to a uniform weighted graph, where nodes represent decision variables and e","authors_text":"Hai Xia, Stefan Szeider, Vaidyanathan Peruvemba Ramaswamy","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-13T15:01:03Z","title":"LLM-Guided Graph Generation for Structure-Based Local Improvement Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13333","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":"sha256:280bc2bb01dfeb6c3174cd255588bba8928cb97ab483d445b69b2867fa0d1591","target":"record","created_at":"2026-08-14T01:04:14Z","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":"93b41aa344d3f083af3e3a7314a971443d21529330e087d015d91ea4b6970a4c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-13T15:01:03Z","title_canon_sha256":"23397bf63269f33874790005330d0061d1a93a27715ddc0e3155f6ba0f9a3913"},"schema_version":"1.0","source":{"id":"2608.13333","kind":"arxiv","version":1}},"canonical_sha256":"724a676b9f51c46a6a69bba845fc0e090fa254d5fbcba371b56697d98104e48a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"724a676b9f51c46a6a69bba845fc0e090fa254d5fbcba371b56697d98104e48a","first_computed_at":"2026-08-14T01:04:14.230964Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-14T01:04:14.230964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vv94XmhzAAJTg+HsKw0/Nj0fPXoppbRyYS+CMLc9IMiBxCiWMowARML3K7eDy9AIRPRjOHjCyWx6KqKDG2HfBw==","signature_status":"signed_v1","signed_at":"2026-08-14T01:04:14.232549Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.13333","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:280bc2bb01dfeb6c3174cd255588bba8928cb97ab483d445b69b2867fa0d1591","sha256:467bdf248d211db89053c2e2a5a19a0198852c1c86a0c6f092ad0072646ec621","sha256:58f9a5c24426e40d3dcf7c09b23029a5cf2674dec0a7fd01ced0e606a6cd0125"],"state_sha256":"3e1cd6bbf52966b9f7b12b76e2437cbbe1e075ab33773e32507b3dda07a5c58c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rW2rpSf0Mpz3cpcwbSee8se/F3hewo1Qtf8Lge6BX5y+T6Ko+UPFbud4Az8v3lNlLIdI/4+1NrowPa+bkk8XDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T22:12:01.147785Z","bundle_sha256":"b425b8a108de83a2ed19555fce3a9470093abbb3b65d1588745fb747b6948f67"}}