{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EHWSHNFHFNUFRFP3WEFRXBJSXM","short_pith_number":"pith:EHWSHNFH","schema_version":"1.0","canonical_sha256":"21ed23b4a72b685895fbb10b1b8532bb2c5eca6f011ccbe401be80cd77934ad2","source":{"kind":"arxiv","id":"2608.00991","version":1},"attestation_state":"computed","paper":{"title":"SCHEDBench: A Benchmark for Evaluating LLM Constraint Faithfulness in Natural-Language Combinatorial Scheduling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Avi Sharma, Shrenil Shaun Sharma","submitted_at":"2026-08-02T04:41:20Z","abstract_excerpt":"This paper introduces SCHEDBench, a natural-language benchmark for evaluating combinatorial scheduling constraint faithfulness under surface-form variation. Grounded in canonical scheduling instances and solver-derived feasibility and optimality, SCHEDBench assesses whether large language models (LLMs) generate schedules with the same constraint-feasible behavior across varied natural-language (NL) surface forms. SCHEDBench spans 1,132 instances across job-shop scheduling problems (JSP), single and multi-mode resource-constrained project scheduling problems (RCPSP), nurse rostering/scheduling,"},"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":"2608.00991","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-02T04:41:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4a32d91d74bb331cd6435ff96edbf8a47e31aed468297486560291ce24916fc5","abstract_canon_sha256":"5b18de1f43fcac6264abaf25e5a847fee12778c4d4970b4ca48353150e0843d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:56:10.630879Z","signature_b64":"CxFhHwKEig/JKAQuKnRSmVbwEpg8pO2pgW2XxPw1qtPe+7R9pUJymaQzQqu/Qsjxynp2JMVxcNoL2ZFYDt+dDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21ed23b4a72b685895fbb10b1b8532bb2c5eca6f011ccbe401be80cd77934ad2","last_reissued_at":"2026-08-04T01:56:10.629400Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:56:10.629400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SCHEDBench: A Benchmark for Evaluating LLM Constraint Faithfulness in Natural-Language Combinatorial Scheduling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Avi Sharma, Shrenil Shaun Sharma","submitted_at":"2026-08-02T04:41:20Z","abstract_excerpt":"This paper introduces SCHEDBench, a natural-language benchmark for evaluating combinatorial scheduling constraint faithfulness under surface-form variation. Grounded in canonical scheduling instances and solver-derived feasibility and optimality, SCHEDBench assesses whether large language models (LLMs) generate schedules with the same constraint-feasible behavior across varied natural-language (NL) surface forms. SCHEDBench spans 1,132 instances across job-shop scheduling problems (JSP), single and multi-mode resource-constrained project scheduling problems (RCPSP), nurse rostering/scheduling,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00991","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/2608.00991/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":"2608.00991","created_at":"2026-08-04T01:56:10.630664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00991v1","created_at":"2026-08-04T01:56:10.630664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00991","created_at":"2026-08-04T01:56:10.630664+00:00"},{"alias_kind":"pith_short_12","alias_value":"EHWSHNFHFNUF","created_at":"2026-08-04T01:56:10.630664+00:00"},{"alias_kind":"pith_short_16","alias_value":"EHWSHNFHFNUFRFP3","created_at":"2026-08-04T01:56:10.630664+00:00"},{"alias_kind":"pith_short_8","alias_value":"EHWSHNFH","created_at":"2026-08-04T01:56:10.630664+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EHWSHNFHFNUFRFP3WEFRXBJSXM","json":"https://pith.science/pith/EHWSHNFHFNUFRFP3WEFRXBJSXM.json","graph_json":"https://pith.science/api/pith-number/EHWSHNFHFNUFRFP3WEFRXBJSXM/graph.json","events_json":"https://pith.science/api/pith-number/EHWSHNFHFNUFRFP3WEFRXBJSXM/events.json","paper":"https://pith.science/paper/EHWSHNFH"},"agent_actions":{"view_html":"https://pith.science/pith/EHWSHNFHFNUFRFP3WEFRXBJSXM","download_json":"https://pith.science/pith/EHWSHNFHFNUFRFP3WEFRXBJSXM.json","view_paper":"https://pith.science/paper/EHWSHNFH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00991&json=true","fetch_graph":"https://pith.science/api/pith-number/EHWSHNFHFNUFRFP3WEFRXBJSXM/graph.json","fetch_events":"https://pith.science/api/pith-number/EHWSHNFHFNUFRFP3WEFRXBJSXM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EHWSHNFHFNUFRFP3WEFRXBJSXM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EHWSHNFHFNUFRFP3WEFRXBJSXM/action/storage_attestation","attest_author":"https://pith.science/pith/EHWSHNFHFNUFRFP3WEFRXBJSXM/action/author_attestation","sign_citation":"https://pith.science/pith/EHWSHNFHFNUFRFP3WEFRXBJSXM/action/citation_signature","submit_replication":"https://pith.science/pith/EHWSHNFHFNUFRFP3WEFRXBJSXM/action/replication_record"}},"created_at":"2026-08-04T01:56:10.630664+00:00","updated_at":"2026-08-04T01:56:10.630664+00:00"}