{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J7SY3POFYQJYLVYZY4UIAJF7P3","short_pith_number":"pith:J7SY3POF","schema_version":"1.0","canonical_sha256":"4fe58dbdc5c41385d719c7288024bf7ed2e5908677105e26f36656db81b75358","source":{"kind":"arxiv","id":"2408.05873","version":3},"attestation_state":"computed","paper":{"title":"Recognizing Limits: Investigating Infeasibility in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hengrui Cai, Wenbo Zhang, Zihang Xu","submitted_at":"2024-08-11T22:58:23Z","abstract_excerpt":"Large language models (LLMs) have shown remarkable performance in various tasks but often fail to handle queries that exceed their knowledge and capabilities, leading to incorrect or fabricated responses. This paper addresses the need for LLMs to recognize and refuse infeasible tasks due to the requests surpassing their capabilities. We conceptualize four main categories of infeasible tasks for LLMs, which cover a broad spectrum of hallucination-related challenges identified in prior literature. We develop and benchmark a new dataset comprising diverse infeasible and feasible tasks to evaluate"},"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":"2408.05873","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-11T22:58:23Z","cross_cats_sorted":[],"title_canon_sha256":"9b7365244a39968f27623d517c807e800e6d0f622f75d104de298493cf12dcdd","abstract_canon_sha256":"539fdc2112e5093a7ab011490cbcffa34e1eb31515bb361f06a603159fd15f0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:06.805333Z","signature_b64":"AGqLZWtPSvJPIoeQNpqaC+VhtLeRxd4lOam1TTyftnNZOWF/13YyJEzSyb8OWIwOVLUpPfVgjo1QyB+WH4FBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fe58dbdc5c41385d719c7288024bf7ed2e5908677105e26f36656db81b75358","last_reissued_at":"2026-07-05T11:59:06.804851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:06.804851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recognizing Limits: Investigating Infeasibility in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hengrui Cai, Wenbo Zhang, Zihang Xu","submitted_at":"2024-08-11T22:58:23Z","abstract_excerpt":"Large language models (LLMs) have shown remarkable performance in various tasks but often fail to handle queries that exceed their knowledge and capabilities, leading to incorrect or fabricated responses. This paper addresses the need for LLMs to recognize and refuse infeasible tasks due to the requests surpassing their capabilities. We conceptualize four main categories of infeasible tasks for LLMs, which cover a broad spectrum of hallucination-related challenges identified in prior literature. We develop and benchmark a new dataset comprising diverse infeasible and feasible tasks to evaluate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05873","kind":"arxiv","version":3},"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/2408.05873/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":"2408.05873","created_at":"2026-07-05T11:59:06.804908+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.05873v3","created_at":"2026-07-05T11:59:06.804908+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05873","created_at":"2026-07-05T11:59:06.804908+00:00"},{"alias_kind":"pith_short_12","alias_value":"J7SY3POFYQJY","created_at":"2026-07-05T11:59:06.804908+00:00"},{"alias_kind":"pith_short_16","alias_value":"J7SY3POFYQJYLVYZ","created_at":"2026-07-05T11:59:06.804908+00:00"},{"alias_kind":"pith_short_8","alias_value":"J7SY3POF","created_at":"2026-07-05T11:59:06.804908+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01456","citing_title":"From Anatomy to Smells: An Empirical Study of SKILL.md in Agent Skills","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30686","citing_title":"Position: Vision-Language-Action Models Cannot Be Verified to Perform Physical Reasoning","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J7SY3POFYQJYLVYZY4UIAJF7P3","json":"https://pith.science/pith/J7SY3POFYQJYLVYZY4UIAJF7P3.json","graph_json":"https://pith.science/api/pith-number/J7SY3POFYQJYLVYZY4UIAJF7P3/graph.json","events_json":"https://pith.science/api/pith-number/J7SY3POFYQJYLVYZY4UIAJF7P3/events.json","paper":"https://pith.science/paper/J7SY3POF"},"agent_actions":{"view_html":"https://pith.science/pith/J7SY3POFYQJYLVYZY4UIAJF7P3","download_json":"https://pith.science/pith/J7SY3POFYQJYLVYZY4UIAJF7P3.json","view_paper":"https://pith.science/paper/J7SY3POF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.05873&json=true","fetch_graph":"https://pith.science/api/pith-number/J7SY3POFYQJYLVYZY4UIAJF7P3/graph.json","fetch_events":"https://pith.science/api/pith-number/J7SY3POFYQJYLVYZY4UIAJF7P3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J7SY3POFYQJYLVYZY4UIAJF7P3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J7SY3POFYQJYLVYZY4UIAJF7P3/action/storage_attestation","attest_author":"https://pith.science/pith/J7SY3POFYQJYLVYZY4UIAJF7P3/action/author_attestation","sign_citation":"https://pith.science/pith/J7SY3POFYQJYLVYZY4UIAJF7P3/action/citation_signature","submit_replication":"https://pith.science/pith/J7SY3POFYQJYLVYZY4UIAJF7P3/action/replication_record"}},"created_at":"2026-07-05T11:59:06.804908+00:00","updated_at":"2026-07-05T11:59:06.804908+00:00"}