{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:56CYWUPJFF552P7IXSW2U4HCIB","short_pith_number":"pith:56CYWUPJ","schema_version":"1.0","canonical_sha256":"ef858b51e9297bdd3fe8bcadaa70e24060e0b0b12732e5f522cd1ff2949ff61d","source":{"kind":"arxiv","id":"2405.05285","version":1},"attestation_state":"computed","paper":{"title":"Generative AI as a metacognitive agent: A comparative mixed-method study with human participants on ICF-mimicking exam performance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Adrijana Milosavljevic, Djordje Babic, Faculty of Philosophy, Jelena Pavlovic (University of Belgrade, Jugoslav Krstic, Koucing centar Resarch Lab), Luka Mitrovic, Milena Nikolic, Tijana Karaklic, Tijana Mitrovic (Koucing centar Research Lab)","submitted_at":"2024-05-07T22:15:12Z","abstract_excerpt":"This study investigates the metacognitive capabilities of Large Language Models relative to human metacognition in the context of the International Coaching Federation ICF mimicking exam, a situational judgment test related to coaching competencies. Using a mixed method approach, we assessed the metacognitive performance, including sensitivity, accuracy in probabilistic predictions, and bias, of human participants and five advanced LLMs (GPT-4, Claude-3-Opus 3, Mistral Large, Llama 3, and Gemini 1.5 Pro). The results indicate that LLMs outperformed humans across all metacognitive metrics, part"},"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":"2405.05285","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-05-07T22:15:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b4fa5e677ab0335856f089c81e9ea1ac465bc37ec0f25e6d004c4b1db4fd0871","abstract_canon_sha256":"18237f0ded3b4e3df6021841fadbee33332fe63b4d5c96734a1bc138c4667d28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:16.216342Z","signature_b64":"1ugzNJy4JP7uyOpVrMtu1CgUi5RzVBMTTNMJvvEk+c2njTcLyJbKj3Wk+C0pChSrCDd/+Zj6fkJ7FeID+QPGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef858b51e9297bdd3fe8bcadaa70e24060e0b0b12732e5f522cd1ff2949ff61d","last_reissued_at":"2026-07-05T08:17:16.215915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:16.215915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative AI as a metacognitive agent: A comparative mixed-method study with human participants on ICF-mimicking exam performance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Adrijana Milosavljevic, Djordje Babic, Faculty of Philosophy, Jelena Pavlovic (University of Belgrade, Jugoslav Krstic, Koucing centar Resarch Lab), Luka Mitrovic, Milena Nikolic, Tijana Karaklic, Tijana Mitrovic (Koucing centar Research Lab)","submitted_at":"2024-05-07T22:15:12Z","abstract_excerpt":"This study investigates the metacognitive capabilities of Large Language Models relative to human metacognition in the context of the International Coaching Federation ICF mimicking exam, a situational judgment test related to coaching competencies. Using a mixed method approach, we assessed the metacognitive performance, including sensitivity, accuracy in probabilistic predictions, and bias, of human participants and five advanced LLMs (GPT-4, Claude-3-Opus 3, Mistral Large, Llama 3, and Gemini 1.5 Pro). The results indicate that LLMs outperformed humans across all metacognitive metrics, part"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.05285","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/2405.05285/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":"2405.05285","created_at":"2026-07-05T08:17:16.215968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.05285v1","created_at":"2026-07-05T08:17:16.215968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.05285","created_at":"2026-07-05T08:17:16.215968+00:00"},{"alias_kind":"pith_short_12","alias_value":"56CYWUPJFF55","created_at":"2026-07-05T08:17:16.215968+00:00"},{"alias_kind":"pith_short_16","alias_value":"56CYWUPJFF552P7I","created_at":"2026-07-05T08:17:16.215968+00:00"},{"alias_kind":"pith_short_8","alias_value":"56CYWUPJ","created_at":"2026-07-05T08:17:16.215968+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/56CYWUPJFF552P7IXSW2U4HCIB","json":"https://pith.science/pith/56CYWUPJFF552P7IXSW2U4HCIB.json","graph_json":"https://pith.science/api/pith-number/56CYWUPJFF552P7IXSW2U4HCIB/graph.json","events_json":"https://pith.science/api/pith-number/56CYWUPJFF552P7IXSW2U4HCIB/events.json","paper":"https://pith.science/paper/56CYWUPJ"},"agent_actions":{"view_html":"https://pith.science/pith/56CYWUPJFF552P7IXSW2U4HCIB","download_json":"https://pith.science/pith/56CYWUPJFF552P7IXSW2U4HCIB.json","view_paper":"https://pith.science/paper/56CYWUPJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.05285&json=true","fetch_graph":"https://pith.science/api/pith-number/56CYWUPJFF552P7IXSW2U4HCIB/graph.json","fetch_events":"https://pith.science/api/pith-number/56CYWUPJFF552P7IXSW2U4HCIB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/56CYWUPJFF552P7IXSW2U4HCIB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/56CYWUPJFF552P7IXSW2U4HCIB/action/storage_attestation","attest_author":"https://pith.science/pith/56CYWUPJFF552P7IXSW2U4HCIB/action/author_attestation","sign_citation":"https://pith.science/pith/56CYWUPJFF552P7IXSW2U4HCIB/action/citation_signature","submit_replication":"https://pith.science/pith/56CYWUPJFF552P7IXSW2U4HCIB/action/replication_record"}},"created_at":"2026-07-05T08:17:16.215968+00:00","updated_at":"2026-07-05T08:17:16.215968+00:00"}