{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TIGPFGYRG3TORF7EWOXJGH2OL6","short_pith_number":"pith:TIGPFGYR","schema_version":"1.0","canonical_sha256":"9a0cf29b1136e6e897e4b3ae931f4e5f949b8b40c4292fb24081e306c3205928","source":{"kind":"arxiv","id":"2401.17882","version":2},"attestation_state":"computed","paper":{"title":"I Think, Therefore I am: Benchmarking Awareness of Large Language Models Using AwareBench","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lichao Sun, Siyuan Wu, Yao Wan, Yuan Li, Yue Huang, Yuli Lin","submitted_at":"2024-01-31T14:41:23Z","abstract_excerpt":"Do large language models (LLMs) exhibit any forms of awareness similar to humans? In this paper, we introduce AwareBench, a benchmark designed to evaluate awareness in LLMs. Drawing from theories in psychology and philosophy, we define awareness in LLMs as the ability to understand themselves as AI models and to exhibit social intelligence. Subsequently, we categorize awareness in LLMs into five dimensions, including capability, mission, emotion, culture, and perspective. Based on this taxonomy, we create a dataset called AwareEval, which contains binary, multiple-choice, and open-ended questi"},"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":"2401.17882","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T14:41:23Z","cross_cats_sorted":[],"title_canon_sha256":"ac7c949fc74bac690016dae041c0ce24179f0f7460b774be74c600fd1856c5de","abstract_canon_sha256":"0c01d321d52cc1ac80f609c19bae3045fe381a7abea96a92d255e7d9dbd0be08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:51.936374Z","signature_b64":"iubGZ6gNbBXs0HkFnhCn6alTZcwiuRiSwRJirBPy2G//wR+fBEMjBBPkvG+8DO6JywaO3nsivkuRcFKumYs0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a0cf29b1136e6e897e4b3ae931f4e5f949b8b40c4292fb24081e306c3205928","last_reissued_at":"2026-07-05T07:45:51.935978Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:51.935978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"I Think, Therefore I am: Benchmarking Awareness of Large Language Models Using AwareBench","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lichao Sun, Siyuan Wu, Yao Wan, Yuan Li, Yue Huang, Yuli Lin","submitted_at":"2024-01-31T14:41:23Z","abstract_excerpt":"Do large language models (LLMs) exhibit any forms of awareness similar to humans? In this paper, we introduce AwareBench, a benchmark designed to evaluate awareness in LLMs. Drawing from theories in psychology and philosophy, we define awareness in LLMs as the ability to understand themselves as AI models and to exhibit social intelligence. Subsequently, we categorize awareness in LLMs into five dimensions, including capability, mission, emotion, culture, and perspective. Based on this taxonomy, we create a dataset called AwareEval, which contains binary, multiple-choice, and open-ended questi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17882","kind":"arxiv","version":2},"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/2401.17882/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":"2401.17882","created_at":"2026-07-05T07:45:51.936029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.17882v2","created_at":"2026-07-05T07:45:51.936029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17882","created_at":"2026-07-05T07:45:51.936029+00:00"},{"alias_kind":"pith_short_12","alias_value":"TIGPFGYRG3TO","created_at":"2026-07-05T07:45:51.936029+00:00"},{"alias_kind":"pith_short_16","alias_value":"TIGPFGYRG3TORF7E","created_at":"2026-07-05T07:45:51.936029+00:00"},{"alias_kind":"pith_short_8","alias_value":"TIGPFGYR","created_at":"2026-07-05T07:45:51.936029+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":221,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":220,"is_internal_anchor":false},{"citing_arxiv_id":"2603.03332","citing_title":"Fragile Thoughts: How Large Language Models Handle Chain-of-Thought Perturbations","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08942","citing_title":"Decomposing and Steering Functional Metacognition in Large Language Models","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TIGPFGYRG3TORF7EWOXJGH2OL6","json":"https://pith.science/pith/TIGPFGYRG3TORF7EWOXJGH2OL6.json","graph_json":"https://pith.science/api/pith-number/TIGPFGYRG3TORF7EWOXJGH2OL6/graph.json","events_json":"https://pith.science/api/pith-number/TIGPFGYRG3TORF7EWOXJGH2OL6/events.json","paper":"https://pith.science/paper/TIGPFGYR"},"agent_actions":{"view_html":"https://pith.science/pith/TIGPFGYRG3TORF7EWOXJGH2OL6","download_json":"https://pith.science/pith/TIGPFGYRG3TORF7EWOXJGH2OL6.json","view_paper":"https://pith.science/paper/TIGPFGYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.17882&json=true","fetch_graph":"https://pith.science/api/pith-number/TIGPFGYRG3TORF7EWOXJGH2OL6/graph.json","fetch_events":"https://pith.science/api/pith-number/TIGPFGYRG3TORF7EWOXJGH2OL6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TIGPFGYRG3TORF7EWOXJGH2OL6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TIGPFGYRG3TORF7EWOXJGH2OL6/action/storage_attestation","attest_author":"https://pith.science/pith/TIGPFGYRG3TORF7EWOXJGH2OL6/action/author_attestation","sign_citation":"https://pith.science/pith/TIGPFGYRG3TORF7EWOXJGH2OL6/action/citation_signature","submit_replication":"https://pith.science/pith/TIGPFGYRG3TORF7EWOXJGH2OL6/action/replication_record"}},"created_at":"2026-07-05T07:45:51.936029+00:00","updated_at":"2026-07-05T07:45:51.936029+00:00"}