{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OTFG2SJSR3DSOI4FJUNX3MGGGX","short_pith_number":"pith:OTFG2SJS","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"},"canonical_sha256":"74ca6d49328ec72723854d1b7db0c635ee80b4fc3585b42bd2a0228c8cbcb612","source":{"kind":"arxiv","id":"2505.20184","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20184","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20184v1","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20184","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"pith_short_12","alias_value":"OTFG2SJSR3DS","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"pith_short_16","alias_value":"OTFG2SJSR3DSOI4F","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"pith_short_8","alias_value":"OTFG2SJS","created_at":"2026-07-05T11:09:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OTFG2SJSR3DSOI4FJUNX3MGGGX","target":"record","payload":{"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"},"canonical_sha256":"74ca6d49328ec72723854d1b7db0c635ee80b4fc3585b42bd2a0228c8cbcb612","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"},"source_kind":"arxiv","source_id":"2505.20184","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WJFkzvddqiEoRM+7LUY2UA/rE/Es/DrYgLnACYH227ycQHYXTM8ta5PFx3wM1N5hDEJq7pISYkZJ/6FDlQBiBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:19:08.040907Z"},"content_sha256":"32a0a640fe19814c6a77e6ffd5effef6a78a6d5c74d66dbac3178a30eb733d42","schema_version":"1.0","event_id":"sha256:32a0a640fe19814c6a77e6ffd5effef6a78a6d5c74d66dbac3178a30eb733d42"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OTFG2SJSR3DSOI4FJUNX3MGGGX","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"owzSbWSVUeogtOnPVG3/rllJLSzlAUV17l5ww3DKw8Tqhbolx6Z7z4u1ur27FXM6Xq744vWbfWX1dNzGT5LyAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:19:08.041321Z"},"content_sha256":"d38d232917f126ed4b21a79fc5b065e4c8437077d0e3fd8bc458ee163f563aa6","schema_version":"1.0","event_id":"sha256:d38d232917f126ed4b21a79fc5b065e4c8437077d0e3fd8bc458ee163f563aa6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OTFG2SJSR3DSOI4FJUNX3MGGGX/bundle.json","state_url":"https://pith.science/pith/OTFG2SJSR3DSOI4FJUNX3MGGGX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OTFG2SJSR3DSOI4FJUNX3MGGGX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T07:19:08Z","links":{"resolver":"https://pith.science/pith/OTFG2SJSR3DSOI4FJUNX3MGGGX","bundle":"https://pith.science/pith/OTFG2SJSR3DSOI4FJUNX3MGGGX/bundle.json","state":"https://pith.science/pith/OTFG2SJSR3DSOI4FJUNX3MGGGX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OTFG2SJSR3DSOI4FJUNX3MGGGX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OTFG2SJSR3DSOI4FJUNX3MGGGX","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":"3f55e3ed24a344ea84cb21ebfef99841f9765653083c0d3e73d77d9ae0fe22dd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T16:27:02Z","title_canon_sha256":"70c0e0c0077e13d197d86774f15db7c10dfae191fb913fcb12c671bde08c5c2c"},"schema_version":"1.0","source":{"id":"2505.20184","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20184","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20184v1","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20184","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"pith_short_12","alias_value":"OTFG2SJSR3DS","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"pith_short_16","alias_value":"OTFG2SJSR3DSOI4F","created_at":"2026-07-05T11:09:53Z"},{"alias_kind":"pith_short_8","alias_value":"OTFG2SJS","created_at":"2026-07-05T11:09:53Z"}],"graph_snapshots":[{"event_id":"sha256:d38d232917f126ed4b21a79fc5b065e4c8437077d0e3fd8bc458ee163f563aa6","target":"graph","created_at":"2026-07-05T11:09:53Z","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/2505.20184/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Mengqian Wu, Nikki G. Lobczowski, Yiran Lin, Yongan Yu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T16:27:02Z","title":"THiNK: Can Large Language Models Think-aloud?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20184","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":"sha256:32a0a640fe19814c6a77e6ffd5effef6a78a6d5c74d66dbac3178a30eb733d42","target":"record","created_at":"2026-07-05T11:09:53Z","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":"3f55e3ed24a344ea84cb21ebfef99841f9765653083c0d3e73d77d9ae0fe22dd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T16:27:02Z","title_canon_sha256":"70c0e0c0077e13d197d86774f15db7c10dfae191fb913fcb12c671bde08c5c2c"},"schema_version":"1.0","source":{"id":"2505.20184","kind":"arxiv","version":1}},"canonical_sha256":"74ca6d49328ec72723854d1b7db0c635ee80b4fc3585b42bd2a0228c8cbcb612","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74ca6d49328ec72723854d1b7db0c635ee80b4fc3585b42bd2a0228c8cbcb612","first_computed_at":"2026-07-05T11:09:53.819257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:53.819257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XsoX3YIzIFuU3Skh76x9p3Dy9GZvGspJg5oC7yIty8mk1XQAM/9tlR4BslIgiB8bfDQ3qdvnoLDP22C+/v+wAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:53.819736Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20184","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32a0a640fe19814c6a77e6ffd5effef6a78a6d5c74d66dbac3178a30eb733d42","sha256:d38d232917f126ed4b21a79fc5b065e4c8437077d0e3fd8bc458ee163f563aa6"],"state_sha256":"a63ea2375dbc955b561ce09a9e40234f2f2efe3e8e1ca5b798fb3153ae7475cb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DonoVrL+NqYtkUUVIfYpdFqZKQeqc904G6LGJXF7nH1o/tIQ1W1KQTy6xe/2AAdDh5tu3/eJqpSPFuy8DLUSAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T07:19:08.044186Z","bundle_sha256":"8d9b96369b0ab9019f0bc40afc1195b8ec33af43071de4f259ff7d5c610d1ff5"}}