{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:THRUUUT2W3YHJ5Q6ALD6SS4NJH","short_pith_number":"pith:THRUUUT2","schema_version":"1.0","canonical_sha256":"99e34a527ab6f074f61e02c7e94b8d49c047e8b69437de577f252f3458b9c479","source":{"kind":"arxiv","id":"2508.15204","version":1},"attestation_state":"computed","paper":{"title":"R-ConstraintBench: Evaluating LLMs on NP-Complete Scheduling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Marc Wetter, Raj Jain","submitted_at":"2025-08-21T03:35:58Z","abstract_excerpt":"Effective scheduling under tight resource, timing, and operational constraints underpins large-scale planning across sectors such as capital projects, manufacturing, logistics, and IT fleet transitions. However, the reliability of large language models (LLMs) when reasoning under high-constraint regimes is insufficiently characterized. To address this gap, we present R-ConstraintBench, a scalable framework that evaluates models on Resource-Constrained Project Scheduling Problems (RCPSP), an NP-Complete feasibility class, while difficulty increases via linear growth in constraints. R-Constraint"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2508.15204","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-21T03:35:58Z","cross_cats_sorted":[],"title_canon_sha256":"b83679f1064bcf92efde0cb052406c396e238a2ac3dec1c998571706ed4e968d","abstract_canon_sha256":"0c20a1eca02165192a8ca60a3e60ae6cbe468c8c179dafcb123714aa48959fa3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:08.236916Z","signature_b64":"J+uyT37ewWoaSJmykMpKMDPFHYagosKWZ+vUywvwFYcnrmlxEd2LcxdlX5oOeKHmyiYgUf7Ol2I0uoWRiD6bDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99e34a527ab6f074f61e02c7e94b8d49c047e8b69437de577f252f3458b9c479","last_reissued_at":"2026-07-05T11:57:08.236552Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:08.236552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"R-ConstraintBench: Evaluating LLMs on NP-Complete Scheduling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Marc Wetter, Raj Jain","submitted_at":"2025-08-21T03:35:58Z","abstract_excerpt":"Effective scheduling under tight resource, timing, and operational constraints underpins large-scale planning across sectors such as capital projects, manufacturing, logistics, and IT fleet transitions. However, the reliability of large language models (LLMs) when reasoning under high-constraint regimes is insufficiently characterized. To address this gap, we present R-ConstraintBench, a scalable framework that evaluates models on Resource-Constrained Project Scheduling Problems (RCPSP), an NP-Complete feasibility class, while difficulty increases via linear growth in constraints. R-Constraint"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15204","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/2508.15204/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2508.15204","created_at":"2026-07-05T11:57:08.236608+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.15204v1","created_at":"2026-07-05T11:57:08.236608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15204","created_at":"2026-07-05T11:57:08.236608+00:00"},{"alias_kind":"pith_short_12","alias_value":"THRUUUT2W3YH","created_at":"2026-07-05T11:57:08.236608+00:00"},{"alias_kind":"pith_short_16","alias_value":"THRUUUT2W3YHJ5Q6","created_at":"2026-07-05T11:57:08.236608+00:00"},{"alias_kind":"pith_short_8","alias_value":"THRUUUT2","created_at":"2026-07-05T11:57:08.236608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.00991","citing_title":"SCHEDBench: A Benchmark for Evaluating LLM Constraint Faithfulness in Natural-Language Combinatorial Scheduling","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/THRUUUT2W3YHJ5Q6ALD6SS4NJH","json":"https://pith.science/pith/THRUUUT2W3YHJ5Q6ALD6SS4NJH.json","graph_json":"https://pith.science/api/pith-number/THRUUUT2W3YHJ5Q6ALD6SS4NJH/graph.json","events_json":"https://pith.science/api/pith-number/THRUUUT2W3YHJ5Q6ALD6SS4NJH/events.json","paper":"https://pith.science/paper/THRUUUT2"},"agent_actions":{"view_html":"https://pith.science/pith/THRUUUT2W3YHJ5Q6ALD6SS4NJH","download_json":"https://pith.science/pith/THRUUUT2W3YHJ5Q6ALD6SS4NJH.json","view_paper":"https://pith.science/paper/THRUUUT2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.15204&json=true","fetch_graph":"https://pith.science/api/pith-number/THRUUUT2W3YHJ5Q6ALD6SS4NJH/graph.json","fetch_events":"https://pith.science/api/pith-number/THRUUUT2W3YHJ5Q6ALD6SS4NJH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/THRUUUT2W3YHJ5Q6ALD6SS4NJH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/THRUUUT2W3YHJ5Q6ALD6SS4NJH/action/storage_attestation","attest_author":"https://pith.science/pith/THRUUUT2W3YHJ5Q6ALD6SS4NJH/action/author_attestation","sign_citation":"https://pith.science/pith/THRUUUT2W3YHJ5Q6ALD6SS4NJH/action/citation_signature","submit_replication":"https://pith.science/pith/THRUUUT2W3YHJ5Q6ALD6SS4NJH/action/replication_record"}},"created_at":"2026-07-05T11:57:08.236608+00:00","updated_at":"2026-07-05T11:57:08.236608+00:00"}