{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TPYHH5VBVRPYNKSQF5MTYMFFCQ","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":"3f2493404179f151e40bd5b51e05d86fccd0e29f3944e97166a0a02eea2529b5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-18T13:35:47Z","title_canon_sha256":"fa9aba88658bc95ca134b87fa845115b2192f92813ff476a60cbb66b4b2d4e5f"},"schema_version":"1.0","source":{"id":"2506.15455","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.15455","created_at":"2026-07-05T11:23:43Z"},{"alias_kind":"arxiv_version","alias_value":"2506.15455v1","created_at":"2026-07-05T11:23:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15455","created_at":"2026-07-05T11:23:43Z"},{"alias_kind":"pith_short_12","alias_value":"TPYHH5VBVRPY","created_at":"2026-07-05T11:23:43Z"},{"alias_kind":"pith_short_16","alias_value":"TPYHH5VBVRPYNKSQ","created_at":"2026-07-05T11:23:43Z"},{"alias_kind":"pith_short_8","alias_value":"TPYHH5VB","created_at":"2026-07-05T11:23:43Z"}],"graph_snapshots":[{"event_id":"sha256:4f73c9edce7eb635b42b52236ef963fee92f78beb683be223cda78128d6a8b96","target":"graph","created_at":"2026-07-05T11:23:43Z","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/2506.15455/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent Large Language Models (LLMs) have reported high accuracy on reasoning benchmarks. However, it is still unclear whether the observed results arise from true reasoning or from statistical recall of the training set. Inspired by the ladder of causation (Pearl, 2009) and its three levels (associations, interventions and counterfactuals), this paper introduces RE-IMAGINE, a framework to characterize a hierarchy of reasoning ability in LLMs, alongside an automated pipeline to generate problem variations at different levels of the hierarchy. By altering problems in an intermediate symbolic rep","authors_text":"Aditya V. Nori, Amit Sharma, Atharva Pandey, Fabian Falck, Javier Gonzalez, Kshitij Dubey, Rachel Lawrence, Rahul Sharma, Risa Ueno, Xinnuo Xu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-18T13:35:47Z","title":"RE-IMAGINE: Symbolic Benchmark Synthesis for Reasoning Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15455","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":"sha256:25032b7b97fa04c15e13b3f6217d7b574751721793c21bbbf1478f11ab0411fc","target":"record","created_at":"2026-07-05T11:23:43Z","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":"3f2493404179f151e40bd5b51e05d86fccd0e29f3944e97166a0a02eea2529b5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-18T13:35:47Z","title_canon_sha256":"fa9aba88658bc95ca134b87fa845115b2192f92813ff476a60cbb66b4b2d4e5f"},"schema_version":"1.0","source":{"id":"2506.15455","kind":"arxiv","version":1}},"canonical_sha256":"9bf073f6a1ac5f86aa502f593c30a51406541e53b5668a302ff372632a0696f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9bf073f6a1ac5f86aa502f593c30a51406541e53b5668a302ff372632a0696f7","first_computed_at":"2026-07-05T11:23:43.937406Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:43.937406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KqxpRVrsiX+J8ikPJmpNfFywRL7iu/E6Z1PN3Ojc3pxO1EcycJVu4n4F61Rer3xOhlIC3cPkcJmYOqlLCnhACA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:43.937907Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.15455","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25032b7b97fa04c15e13b3f6217d7b574751721793c21bbbf1478f11ab0411fc","sha256:4f73c9edce7eb635b42b52236ef963fee92f78beb683be223cda78128d6a8b96"],"state_sha256":"f2b838d14d82c43e89be974af84f207784f8dd70bd00731e04e255c84961a9c3"}