{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OTFG2SJSR3DSOI4FJUNX3MGGGX","short_pith_number":"pith:OTFG2SJS","schema_version":"1.0","canonical_sha256":"74ca6d49328ec72723854d1b7db0c635ee80b4fc3585b42bd2a0228c8cbcb612","source":{"kind":"arxiv","id":"2505.20184","version":1},"attestation_state":"computed","paper":{"title":"THiNK: Can Large Language Models Think-aloud?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mengqian Wu, Nikki G. Lobczowski, Yiran Lin, Yongan Yu","submitted_at":"2025-05-26T16:27:02Z","abstract_excerpt":"Assessing higher-order thinking skills in large language models (LLMs) remains a fundamental challenge, especially in tasks that go beyond surface-level accuracy. In this work, we propose THiNK (Testing Higher-order Notion of Knowledge), a multi-agent, feedback-driven evaluation framework grounded in Bloom's Taxonomy. THiNK frames reasoning assessment as an iterative task of problem generation, critique, and revision, encouraging LLMs to think-aloud through step-by-step reflection and refinement. This enables a systematic evaluation of both lower-order (e.g., remember, understand) and higher-o"},"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":"2505.20184","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T16:27:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"70c0e0c0077e13d197d86774f15db7c10dfae191fb913fcb12c671bde08c5c2c","abstract_canon_sha256":"3f55e3ed24a344ea84cb21ebfef99841f9765653083c0d3e73d77d9ae0fe22dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:53.819736Z","signature_b64":"XsoX3YIzIFuU3Skh76x9p3Dy9GZvGspJg5oC7yIty8mk1XQAM/9tlR4BslIgiB8bfDQ3qdvnoLDP22C+/v+wAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74ca6d49328ec72723854d1b7db0c635ee80b4fc3585b42bd2a0228c8cbcb612","last_reissued_at":"2026-07-05T11:09:53.819257Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:53.819257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"THiNK: Can Large Language Models Think-aloud?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mengqian Wu, Nikki G. Lobczowski, Yiran Lin, Yongan Yu","submitted_at":"2025-05-26T16:27:02Z","abstract_excerpt":"Assessing higher-order thinking skills in large language models (LLMs) remains a fundamental challenge, especially in tasks that go beyond surface-level accuracy. In this work, we propose THiNK (Testing Higher-order Notion of Knowledge), a multi-agent, feedback-driven evaluation framework grounded in Bloom's Taxonomy. THiNK frames reasoning assessment as an iterative task of problem generation, critique, and revision, encouraging LLMs to think-aloud through step-by-step reflection and refinement. This enables a systematic evaluation of both lower-order (e.g., remember, understand) and higher-o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20184","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/2505.20184/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":"2505.20184","created_at":"2026-07-05T11:09:53.819313+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20184v1","created_at":"2026-07-05T11:09:53.819313+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20184","created_at":"2026-07-05T11:09:53.819313+00:00"},{"alias_kind":"pith_short_12","alias_value":"OTFG2SJSR3DS","created_at":"2026-07-05T11:09:53.819313+00:00"},{"alias_kind":"pith_short_16","alias_value":"OTFG2SJSR3DSOI4F","created_at":"2026-07-05T11:09:53.819313+00:00"},{"alias_kind":"pith_short_8","alias_value":"OTFG2SJS","created_at":"2026-07-05T11:09:53.819313+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/OTFG2SJSR3DSOI4FJUNX3MGGGX","json":"https://pith.science/pith/OTFG2SJSR3DSOI4FJUNX3MGGGX.json","graph_json":"https://pith.science/api/pith-number/OTFG2SJSR3DSOI4FJUNX3MGGGX/graph.json","events_json":"https://pith.science/api/pith-number/OTFG2SJSR3DSOI4FJUNX3MGGGX/events.json","paper":"https://pith.science/paper/OTFG2SJS"},"agent_actions":{"view_html":"https://pith.science/pith/OTFG2SJSR3DSOI4FJUNX3MGGGX","download_json":"https://pith.science/pith/OTFG2SJSR3DSOI4FJUNX3MGGGX.json","view_paper":"https://pith.science/paper/OTFG2SJS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20184&json=true","fetch_graph":"https://pith.science/api/pith-number/OTFG2SJSR3DSOI4FJUNX3MGGGX/graph.json","fetch_events":"https://pith.science/api/pith-number/OTFG2SJSR3DSOI4FJUNX3MGGGX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OTFG2SJSR3DSOI4FJUNX3MGGGX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OTFG2SJSR3DSOI4FJUNX3MGGGX/action/storage_attestation","attest_author":"https://pith.science/pith/OTFG2SJSR3DSOI4FJUNX3MGGGX/action/author_attestation","sign_citation":"https://pith.science/pith/OTFG2SJSR3DSOI4FJUNX3MGGGX/action/citation_signature","submit_replication":"https://pith.science/pith/OTFG2SJSR3DSOI4FJUNX3MGGGX/action/replication_record"}},"created_at":"2026-07-05T11:09:53.819313+00:00","updated_at":"2026-07-05T11:09:53.819313+00:00"}