{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:X4XOBP2BPVS6IJTVMD57H2LCBW","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":"821feb0a44c190b412a2c725ec3265377542bb4869f1b9597bc5975cce9d507d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-03-06T15:36:06Z","title_canon_sha256":"e9fb3fd03ee9f4e609ff1955dd2728bded502ac4590ad05d05da6d5dc3fee7af"},"schema_version":"1.0","source":{"id":"2503.04550","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04550","created_at":"2026-07-05T10:25:41Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04550v1","created_at":"2026-07-05T10:25:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04550","created_at":"2026-07-05T10:25:41Z"},{"alias_kind":"pith_short_12","alias_value":"X4XOBP2BPVS6","created_at":"2026-07-05T10:25:41Z"},{"alias_kind":"pith_short_16","alias_value":"X4XOBP2BPVS6IJTV","created_at":"2026-07-05T10:25:41Z"},{"alias_kind":"pith_short_8","alias_value":"X4XOBP2B","created_at":"2026-07-05T10:25:41Z"}],"graph_snapshots":[{"event_id":"sha256:a4f144cfd7e588d57bb4f02e33edbda14674cd2c6bcf00048067c1b063ece012","target":"graph","created_at":"2026-07-05T10:25:41Z","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/2503.04550/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the recent success of large language models (LLMs) in reasoning such as DeepSeek, we for the first time identify a key dilemma in reasoning robustness and generalization: significant performance degradation on novel or incomplete data, suggesting a reliance on memorized patterns rather than systematic reasoning. Our closer examination reveals four key unique limitations underlying this issue:(1) Positional bias--models favor earlier queries in multi-query inputs but answering the wrong one in the latter (e.g., GPT-4o's accuracy drops from 75.8 percent to 72.8 percent); (2) Instruction ","authors_text":"Bo Du, Dacheng Tao, Tong Yu, Wenbin Hu, Wenjie Wu, Wentao Jiang, Xikun Zhang, Yingjie Wang, Yongcheng Jing","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-03-06T15:36:06Z","title":"Benchmarking Reasoning Robustness in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04550","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":"sha256:720b33f5146f7a2d29441f5f5cedb71b8d3c7bda1b980e0da7db3ae0282c008c","target":"record","created_at":"2026-07-05T10:25:41Z","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":"821feb0a44c190b412a2c725ec3265377542bb4869f1b9597bc5975cce9d507d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-03-06T15:36:06Z","title_canon_sha256":"e9fb3fd03ee9f4e609ff1955dd2728bded502ac4590ad05d05da6d5dc3fee7af"},"schema_version":"1.0","source":{"id":"2503.04550","kind":"arxiv","version":1}},"canonical_sha256":"bf2ee0bf417d65e4267560fbf3e9620d85e99709a63fd242c0177678e26098a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf2ee0bf417d65e4267560fbf3e9620d85e99709a63fd242c0177678e26098a9","first_computed_at":"2026-07-05T10:25:41.936838Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:25:41.936838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qFB0d2HO2hZYomjCsG/SqsRRUx5pwH5GWXqwOR+epS1OPUgqedUSRQ0MRMT9+h25q2NwcYvuPn6nBh4ZfVmBCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:25:41.937423Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.04550","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:720b33f5146f7a2d29441f5f5cedb71b8d3c7bda1b980e0da7db3ae0282c008c","sha256:a4f144cfd7e588d57bb4f02e33edbda14674cd2c6bcf00048067c1b063ece012"],"state_sha256":"b6792f0911f598d0c30a68d6dae0d7df1178b7ba096b0cc99be0c38faff656b8"}