{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WKDEFPT64STFTAAUQSPIVWVDYF","short_pith_number":"pith:WKDEFPT6","canonical_record":{"source":{"id":"2606.23571","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-06-22T16:38:42Z","cross_cats_sorted":[],"title_canon_sha256":"2033a49db39300f6c6c83ccb89fcad312199759b333e4747e78c7f41aa0a183c","abstract_canon_sha256":"f8f698433bde8d5f12e025b9ee1d61dc623c37e15b9a1116aefdcd8a829d284e"},"schema_version":"1.0"},"canonical_sha256":"b28642be7ee4a6598014849e8adaa3c15250c572fb5923828823b1cd96a85aa1","source":{"kind":"arxiv","id":"2606.23571","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23571","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23571v1","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23571","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"pith_short_12","alias_value":"WKDEFPT64STF","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"pith_short_16","alias_value":"WKDEFPT64STFTAAU","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"pith_short_8","alias_value":"WKDEFPT6","created_at":"2026-06-23T03:14:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WKDEFPT64STFTAAUQSPIVWVDYF","target":"record","payload":{"canonical_record":{"source":{"id":"2606.23571","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-06-22T16:38:42Z","cross_cats_sorted":[],"title_canon_sha256":"2033a49db39300f6c6c83ccb89fcad312199759b333e4747e78c7f41aa0a183c","abstract_canon_sha256":"f8f698433bde8d5f12e025b9ee1d61dc623c37e15b9a1116aefdcd8a829d284e"},"schema_version":"1.0"},"canonical_sha256":"b28642be7ee4a6598014849e8adaa3c15250c572fb5923828823b1cd96a85aa1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:31.213111Z","signature_b64":"4E2a/l2uEWABqEURYp7lyfkQNVNVVAIF+xqyYGAKYC22dCHnFZ1tXWx/fn4Zaf2BDT01thYl7csQf/DdC1bNCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b28642be7ee4a6598014849e8adaa3c15250c572fb5923828823b1cd96a85aa1","last_reissued_at":"2026-06-23T03:14:31.212736Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:31.212736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.23571","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":"2026-06-23T03:14:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cRCPe8trfS2/B6hqGJ4QToes9SQCCiuitoSimz09i8sy8oPkLYUv9YT7UGcEboWngDl12ds9P3cNAQvAsPLdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T06:37:37.544830Z"},"content_sha256":"1bb57042b0a5de447f1f86aa97435ae065cd3370a520806109712a439b9ad815","schema_version":"1.0","event_id":"sha256:1bb57042b0a5de447f1f86aa97435ae065cd3370a520806109712a439b9ad815"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WKDEFPT64STFTAAUQSPIVWVDYF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"INCARBench: A Benchmark for Scientific Configuration in VASP INCAR by Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Baishun Yang, Bin Shao, Jixiang Li, Weichao Wang, Xinyue Zhang, Zhiyang Liu","submitted_at":"2026-06-22T16:38:42Z","abstract_excerpt":"Large language models (LLMs) are increasingly being integrated into first-principles computational workflows, yet their ability to configure scientific calculations remains poorly understood. Here, we introduce INCARBench, a benchmark for evaluating LLMs on input configuration for the Vienna Ab initio Simulation Package (VASP) through both configuration generation and repair tasks. Evaluating 19 model configurations reveals substantial capability differences among current frontier models. While several models achieve high semantic and policy accuracy, task-critical correctness remains substant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23571","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/2606.23571/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":"2026-06-23T03:14:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rlPz4YjsI8HY+JCrBDaHUyMK26dpTwUZWXpGqMMtEkeQTjYpS/bano2bMZcCcPkCJSUl3+xWI/V1NnTMcYinCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T06:37:37.545202Z"},"content_sha256":"f958bae90e4d81cd3c691090baa0383cd367ddbaaeebd35a843b86c989e28fb4","schema_version":"1.0","event_id":"sha256:f958bae90e4d81cd3c691090baa0383cd367ddbaaeebd35a843b86c989e28fb4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WKDEFPT64STFTAAUQSPIVWVDYF/bundle.json","state_url":"https://pith.science/pith/WKDEFPT64STFTAAUQSPIVWVDYF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WKDEFPT64STFTAAUQSPIVWVDYF/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":"2026-06-29T06:37:37Z","links":{"resolver":"https://pith.science/pith/WKDEFPT64STFTAAUQSPIVWVDYF","bundle":"https://pith.science/pith/WKDEFPT64STFTAAUQSPIVWVDYF/bundle.json","state":"https://pith.science/pith/WKDEFPT64STFTAAUQSPIVWVDYF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WKDEFPT64STFTAAUQSPIVWVDYF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WKDEFPT64STFTAAUQSPIVWVDYF","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":"f8f698433bde8d5f12e025b9ee1d61dc623c37e15b9a1116aefdcd8a829d284e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-06-22T16:38:42Z","title_canon_sha256":"2033a49db39300f6c6c83ccb89fcad312199759b333e4747e78c7f41aa0a183c"},"schema_version":"1.0","source":{"id":"2606.23571","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23571","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23571v1","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23571","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"pith_short_12","alias_value":"WKDEFPT64STF","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"pith_short_16","alias_value":"WKDEFPT64STFTAAU","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"pith_short_8","alias_value":"WKDEFPT6","created_at":"2026-06-23T03:14:31Z"}],"graph_snapshots":[{"event_id":"sha256:f958bae90e4d81cd3c691090baa0383cd367ddbaaeebd35a843b86c989e28fb4","target":"graph","created_at":"2026-06-23T03:14:31Z","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/2606.23571/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly being integrated into first-principles computational workflows, yet their ability to configure scientific calculations remains poorly understood. Here, we introduce INCARBench, a benchmark for evaluating LLMs on input configuration for the Vienna Ab initio Simulation Package (VASP) through both configuration generation and repair tasks. Evaluating 19 model configurations reveals substantial capability differences among current frontier models. While several models achieve high semantic and policy accuracy, task-critical correctness remains substant","authors_text":"Baishun Yang, Bin Shao, Jixiang Li, Weichao Wang, Xinyue Zhang, Zhiyang Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-06-22T16:38:42Z","title":"INCARBench: A Benchmark for Scientific Configuration in VASP INCAR by Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23571","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":"sha256:1bb57042b0a5de447f1f86aa97435ae065cd3370a520806109712a439b9ad815","target":"record","created_at":"2026-06-23T03:14:31Z","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":"f8f698433bde8d5f12e025b9ee1d61dc623c37e15b9a1116aefdcd8a829d284e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-06-22T16:38:42Z","title_canon_sha256":"2033a49db39300f6c6c83ccb89fcad312199759b333e4747e78c7f41aa0a183c"},"schema_version":"1.0","source":{"id":"2606.23571","kind":"arxiv","version":1}},"canonical_sha256":"b28642be7ee4a6598014849e8adaa3c15250c572fb5923828823b1cd96a85aa1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b28642be7ee4a6598014849e8adaa3c15250c572fb5923828823b1cd96a85aa1","first_computed_at":"2026-06-23T03:14:31.212736Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:14:31.212736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4E2a/l2uEWABqEURYp7lyfkQNVNVVAIF+xqyYGAKYC22dCHnFZ1tXWx/fn4Zaf2BDT01thYl7csQf/DdC1bNCg==","signature_status":"signed_v1","signed_at":"2026-06-23T03:14:31.213111Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.23571","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bb57042b0a5de447f1f86aa97435ae065cd3370a520806109712a439b9ad815","sha256:f958bae90e4d81cd3c691090baa0383cd367ddbaaeebd35a843b86c989e28fb4"],"state_sha256":"1cd31877ee3f78a6282b5d89a9e78a9a172092f5828f1e7d0e22dd243b9f177d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dhsL9M0u5bABRuRwvD7eXjP+n2io2yxiF65MPw6LvvTlLsB1vceENCrjEyZeqC5mxee3um1hV74whTP3BDhJDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T06:37:37.547164Z","bundle_sha256":"1092eb514a3897078b431cdf9e40706cabade39be54c3dbac55d7e8e1d99dfc3"}}