{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TNBDJFV7HKDGLFASOSRKSVU33K","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":"3b7385f737de93f772dae5cc8688719f161d88a57b5109e81e26d52512a8219b","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T14:11:16Z","title_canon_sha256":"5029ddb83d65e259e379c9412f14eb5eb11165c5322d6390ba0787960a77e052"},"schema_version":"1.0","source":{"id":"2606.04915","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04915","created_at":"2026-06-04T01:09:55Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04915v1","created_at":"2026-06-04T01:09:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04915","created_at":"2026-06-04T01:09:55Z"},{"alias_kind":"pith_short_12","alias_value":"TNBDJFV7HKDG","created_at":"2026-06-04T01:09:55Z"},{"alias_kind":"pith_short_16","alias_value":"TNBDJFV7HKDGLFAS","created_at":"2026-06-04T01:09:55Z"},{"alias_kind":"pith_short_8","alias_value":"TNBDJFV7","created_at":"2026-06-04T01:09:55Z"}],"graph_snapshots":[{"event_id":"sha256:362458ad0aae11ea463f5e2535f79615d47227e4a283791e072dfe9f83c266c9","target":"graph","created_at":"2026-06-04T01:09:55Z","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/2606.04915/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models reach 50 to 70% accuracy on causal reasoning benchmarks such as CLadder, but it is unclear whether this reflects structural reasoning or lexical pattern matching. We introduce Caliper, a controlled perturbation that replaces semantic variable names with placeholder tokens while preserving the causal graph and probabilistic specification of each question. Across nine instruction-tuned LLMs from 3.8B to 671B and three causal reasoning benchmarks, lexical anonymization yields robust accuracy drops of +7.6, +27.0, and +11.1 pp on a local 3.8B-14B set, rising to +29.6 and +18.","authors_text":"Shuigeng Zhou, Zhenyu Yu","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T14:11:16Z","title":"Caliper: Probing Lexical Anchors versus Causal Structure in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04915","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":"sha256:8e7d232ff00d49b2fd294bc782f34347c6d7e55628bf353e22422f906cfab335","target":"record","created_at":"2026-06-04T01:09:55Z","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":"3b7385f737de93f772dae5cc8688719f161d88a57b5109e81e26d52512a8219b","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T14:11:16Z","title_canon_sha256":"5029ddb83d65e259e379c9412f14eb5eb11165c5322d6390ba0787960a77e052"},"schema_version":"1.0","source":{"id":"2606.04915","kind":"arxiv","version":1}},"canonical_sha256":"9b423496bf3a8665941274a2a9569bda84990584f32574996ee4c721cd7909b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b423496bf3a8665941274a2a9569bda84990584f32574996ee4c721cd7909b8","first_computed_at":"2026-06-04T01:09:55.335940Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:09:55.335940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NPL0uwva/QTyhJ71YiBcP8Wk7eiVPPARwviLhV/v00w8lV/zl+O42BAxvexpeEP4vMXOnGc1VbKFDGYQuheOBA==","signature_status":"signed_v1","signed_at":"2026-06-04T01:09:55.336647Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04915","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e7d232ff00d49b2fd294bc782f34347c6d7e55628bf353e22422f906cfab335","sha256:362458ad0aae11ea463f5e2535f79615d47227e4a283791e072dfe9f83c266c9"],"state_sha256":"3044b22ee4a64f4ec9db0e3a4e6bc7d3d30b4acbff699453ec19623c102e6de6"}