{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IIMCECQBNUROEN72VRHXRZQKLB","short_pith_number":"pith:IIMCECQB","schema_version":"1.0","canonical_sha256":"4218220a016d22e237faac4f78e60a58657d00424984f2c4e7fe83240c9776af","source":{"kind":"arxiv","id":"2605.26242","version":1},"attestation_state":"computed","paper":{"title":"Can LLMs Introspect? A Reality Check","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Shashwat Singh, Shauli Ravfogel, Tal Linzen","submitted_at":"2026-05-25T18:07:49Z","abstract_excerpt":"Can large language models detect and report their own internal states? A number of studies have argued that the answer to this question is yes. We argue, based on lessons from human metacognition research, that this conclusion may be premature: to be convinced of this conclusion we need to distinguish genuine introspection from pattern matching based on surface-level cues. Furthermore, we argue that behavioral evidence alone is inherently insufficient to establish strong introspective claims.\n  We re-examine two recently introduced evaluation paradigms in light of this consideration. In the fi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.26242","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-25T18:07:49Z","cross_cats_sorted":[],"title_canon_sha256":"09e7def29f7569baf01ceb81b1c8f0e94d9c968cdddd33fcd8749be0d589a372","abstract_canon_sha256":"c4b01d65a1f9713136002ab438a96fbf3cf48f7b9cf3b2e5301da542a0c80dc5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:07.547279Z","signature_b64":"JljLaP9fKR5ZVAmwS2Iik7s++hVqcS7fzL6aS5/pWW7JpYPnw8QNdEV3rwx+N7hurpke7C++DNDtR3LWpB6/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4218220a016d22e237faac4f78e60a58657d00424984f2c4e7fe83240c9776af","last_reissued_at":"2026-05-27T01:05:07.546340Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:07.546340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can LLMs Introspect? A Reality Check","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Shashwat Singh, Shauli Ravfogel, Tal Linzen","submitted_at":"2026-05-25T18:07:49Z","abstract_excerpt":"Can large language models detect and report their own internal states? A number of studies have argued that the answer to this question is yes. We argue, based on lessons from human metacognition research, that this conclusion may be premature: to be convinced of this conclusion we need to distinguish genuine introspection from pattern matching based on surface-level cues. Furthermore, we argue that behavioral evidence alone is inherently insufficient to establish strong introspective claims.\n  We re-examine two recently introduced evaluation paradigms in light of this consideration. In the fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26242","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.26242/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.26242","created_at":"2026-05-27T01:05:07.546451+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26242v1","created_at":"2026-05-27T01:05:07.546451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26242","created_at":"2026-05-27T01:05:07.546451+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIMCECQBNURO","created_at":"2026-05-27T01:05:07.546451+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIMCECQBNUROEN72","created_at":"2026-05-27T01:05:07.546451+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIMCECQB","created_at":"2026-05-27T01:05:07.546451+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IIMCECQBNUROEN72VRHXRZQKLB","json":"https://pith.science/pith/IIMCECQBNUROEN72VRHXRZQKLB.json","graph_json":"https://pith.science/api/pith-number/IIMCECQBNUROEN72VRHXRZQKLB/graph.json","events_json":"https://pith.science/api/pith-number/IIMCECQBNUROEN72VRHXRZQKLB/events.json","paper":"https://pith.science/paper/IIMCECQB"},"agent_actions":{"view_html":"https://pith.science/pith/IIMCECQBNUROEN72VRHXRZQKLB","download_json":"https://pith.science/pith/IIMCECQBNUROEN72VRHXRZQKLB.json","view_paper":"https://pith.science/paper/IIMCECQB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26242&json=true","fetch_graph":"https://pith.science/api/pith-number/IIMCECQBNUROEN72VRHXRZQKLB/graph.json","fetch_events":"https://pith.science/api/pith-number/IIMCECQBNUROEN72VRHXRZQKLB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIMCECQBNUROEN72VRHXRZQKLB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIMCECQBNUROEN72VRHXRZQKLB/action/storage_attestation","attest_author":"https://pith.science/pith/IIMCECQBNUROEN72VRHXRZQKLB/action/author_attestation","sign_citation":"https://pith.science/pith/IIMCECQBNUROEN72VRHXRZQKLB/action/citation_signature","submit_replication":"https://pith.science/pith/IIMCECQBNUROEN72VRHXRZQKLB/action/replication_record"}},"created_at":"2026-05-27T01:05:07.546451+00:00","updated_at":"2026-05-27T01:05:07.546451+00:00"}