{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BKLO5P3S7Q7FNKPAKXN4OJUENT","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":"35848d992482ff432caeb4040e9630214a0b38362dffb4d7c5f77fbb313137d9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-19T17:23:20Z","title_canon_sha256":"0fb5937cd267d693afc8d7c2f237aeed006a69ec77d2d065622a61ef790ec36a"},"schema_version":"1.0","source":{"id":"2603.19167","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.19167","created_at":"2026-05-25T02:01:17Z"},{"alias_kind":"arxiv_version","alias_value":"2603.19167v2","created_at":"2026-05-25T02:01:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.19167","created_at":"2026-05-25T02:01:17Z"},{"alias_kind":"pith_short_12","alias_value":"BKLO5P3S7Q7F","created_at":"2026-05-25T02:01:17Z"},{"alias_kind":"pith_short_16","alias_value":"BKLO5P3S7Q7FNKPA","created_at":"2026-05-25T02:01:17Z"},{"alias_kind":"pith_short_8","alias_value":"BKLO5P3S","created_at":"2026-05-25T02:01:17Z"}],"graph_snapshots":[{"event_id":"sha256:c8b2722fe8771a2bfb2386ffcf3b2fa421617bee62ec9631b4c27c04b97df129","target":"graph","created_at":"2026-05-25T02:01:17Z","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/2603.19167/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We evaluate Large Language Models (LLMs) in repeated game-theoretic settings to assess whether strategic performance reflects genuine reasoning or reliance on memorized patterns. We consider two canonical games, Prisoner's Dilemma (PD) and Rock-Paper-Scissors (RPS), upon which we introduce counterfactual variants that alter payoff structures and action labels, breaking familiar symmetries and dominance relations. Our multi-metric evaluation framework compares default and counterfactual instantiations, showcasing LLM limitations in incentive sensitivity, structural generalization and strategic ","authors_text":"Angeliki Dimitriou, Dimitrios Georgousis, Giorgos Filandrianos, Giorgos Stamou, Maria Lymperaiou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-19T17:23:20Z","title":"Evaluating Counterfactual Strategic Reasoning in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.19167","kind":"arxiv","version":2},"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":"sha256:634c2da0f4081f6e156d79044a3df65407eca35469ade25b0e36f5a4e3825094","target":"record","created_at":"2026-05-25T02:01:17Z","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":"35848d992482ff432caeb4040e9630214a0b38362dffb4d7c5f77fbb313137d9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-19T17:23:20Z","title_canon_sha256":"0fb5937cd267d693afc8d7c2f237aeed006a69ec77d2d065622a61ef790ec36a"},"schema_version":"1.0","source":{"id":"2603.19167","kind":"arxiv","version":2}},"canonical_sha256":"0a96eebf72fc3e56a9e055dbc726846ce02a7ee125ffe166875adcb9e91687c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a96eebf72fc3e56a9e055dbc726846ce02a7ee125ffe166875adcb9e91687c8","first_computed_at":"2026-05-25T02:01:17.772254Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:17.772254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Kzcc13DiWT0QF91AaXHjyRP/+kuY8BRFFJbRWRYmAwyq7sbpgbJTKsIZm5FtBIm0K7NefUuq9qxPYGNzqEDIAg==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:17.772980Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.19167","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:634c2da0f4081f6e156d79044a3df65407eca35469ade25b0e36f5a4e3825094","sha256:c8b2722fe8771a2bfb2386ffcf3b2fa421617bee62ec9631b4c27c04b97df129"],"state_sha256":"a56fbe8fab7c7004ea8493d09ea3c0629426d116ceba096b0a7fa4dd654eac7e"}