{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WHGR3J2GD7LMP6ETSBHOWO6I7R","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":"bcf7e305fe07b3751bf9adc50dd7dd5663c90f343085c87764127eee51ce2b63","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T19:49:49Z","title_canon_sha256":"067de60ef25de845fcbdb5d354255fed9d687039ef6a475fca4f22a7d61dfe1c"},"schema_version":"1.0","source":{"id":"2607.01431","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01431","created_at":"2026-07-03T00:17:00Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01431v1","created_at":"2026-07-03T00:17:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01431","created_at":"2026-07-03T00:17:00Z"},{"alias_kind":"pith_short_12","alias_value":"WHGR3J2GD7LM","created_at":"2026-07-03T00:17:00Z"},{"alias_kind":"pith_short_16","alias_value":"WHGR3J2GD7LMP6ET","created_at":"2026-07-03T00:17:00Z"},{"alias_kind":"pith_short_8","alias_value":"WHGR3J2G","created_at":"2026-07-03T00:17:00Z"}],"graph_snapshots":[{"event_id":"sha256:dfdf43a6ca0ef78c30495a2c767931f10f6cdb4dadee9922ab6584b9d2409bd7","target":"graph","created_at":"2026-07-03T00:17:00Z","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/2607.01431/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce ISOSCI, a benchmark of isomorphic cross-domain science problem pairs that separates reasoning ability from domain knowledge retrieval in LLM evaluation. Each pair shares identical logical structure but requires different domain-specific knowledge, enabling controlled attribution of reasoning-mode gains. Across five model pairs spanning four model families, we find that 91.3% of reasoning-mode gains are knowledge-dependent rather than structure-invariant (63/69 gains; Wilson 95% CI [82.3%, 96.0%]), directly challenging the assumption that chain-of-thought reasoning improves short-h","authors_text":"Erchin Serpedin, Hasan Kurban, Samir Abdaljalil","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T19:49:49Z","title":"IsoSci: A Benchmark of Isomorphic Cross-Domain Science Problems for Evaluating Reasoning versus Knowledge Retrieval in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01431","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":"sha256:1191b24e6ca86404156235d7ce1aac0482725b9d5d5ff2cadf21a16149164b96","target":"record","created_at":"2026-07-03T00:17:00Z","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":"bcf7e305fe07b3751bf9adc50dd7dd5663c90f343085c87764127eee51ce2b63","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T19:49:49Z","title_canon_sha256":"067de60ef25de845fcbdb5d354255fed9d687039ef6a475fca4f22a7d61dfe1c"},"schema_version":"1.0","source":{"id":"2607.01431","kind":"arxiv","version":1}},"canonical_sha256":"b1cd1da7461fd6c7f893904eeb3bc8fc71eb5a482951a4dc75928b0abf5f1a3f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1cd1da7461fd6c7f893904eeb3bc8fc71eb5a482951a4dc75928b0abf5f1a3f","first_computed_at":"2026-07-03T00:17:00.067597Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T00:17:00.067597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9nZ3QSIXcyx1xkbPgZ0Xkn/wOt722JJkEdCRsC/pbRZ3+TkzMFG35ICOslrmt8R4jewf64VHFcX8r4ZPkULuDQ==","signature_status":"signed_v1","signed_at":"2026-07-03T00:17:00.067952Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.01431","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1191b24e6ca86404156235d7ce1aac0482725b9d5d5ff2cadf21a16149164b96","sha256:dfdf43a6ca0ef78c30495a2c767931f10f6cdb4dadee9922ab6584b9d2409bd7"],"state_sha256":"afb26a8b42aad63b7576ff4c23a531a5fcc4d58f4476956af8ed85aeb61642c0"}