{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GVNWFQHEF3IZTTGFJBDJHKJEMY","short_pith_number":"pith:GVNWFQHE","schema_version":"1.0","canonical_sha256":"355b62c0e42ed199ccc5484693a924663e1e38ea0249dfe753e5fe611a1287fc","source":{"kind":"arxiv","id":"2606.13220","version":1},"attestation_state":"computed","paper":{"title":"LLM-as-an-Investigator: Evidence-First Reasoning for Robust Interactive Problem Diagnosis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CE","cs.ET","cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Fabrizio Marozzo, Pietro Li\\`o","submitted_at":"2026-06-11T11:37:07Z","abstract_excerpt":"Large language models (LLMs) are increasingly used as interactive assistants for technical problem solving. However, when users provide incomplete descriptions or plausible but unverified explanations, LLMs may prematurely align with these assumptions and propose solutions before collecting sufficient evidence. We refer to this behavior as user-driven sycophancy: the tendency of an LLM to reinforce a user-provided hypothesis instead of testing alternative explanations. This paper introduces LLM-as-an-Investigator, an evidence-first agentic AI methodology for robust problem diagnosis. The appro"},"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":"2606.13220","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-11T11:37:07Z","cross_cats_sorted":["cs.CE","cs.ET","cs.LG","cs.MA"],"title_canon_sha256":"a9173b4b5ff1859f76dd19beaf37acfef3ce00b2c9b75a28d826f39f48eacb53","abstract_canon_sha256":"b029e40246d48e29ab13f98041d01d2519215b5a89b15f9231b85ac6b1497c3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:47.263165Z","signature_b64":"uYnSIkd2RnN23RCubMVpYoLw9sFpe3fQQV7X/RQ/o6l1TGg+D62X/9MyR6jKPhlmAwiMOlfzbnM821JWKKDcBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"355b62c0e42ed199ccc5484693a924663e1e38ea0249dfe753e5fe611a1287fc","last_reissued_at":"2026-06-12T01:09:47.262334Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:47.262334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-as-an-Investigator: Evidence-First Reasoning for Robust Interactive Problem Diagnosis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CE","cs.ET","cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Fabrizio Marozzo, Pietro Li\\`o","submitted_at":"2026-06-11T11:37:07Z","abstract_excerpt":"Large language models (LLMs) are increasingly used as interactive assistants for technical problem solving. However, when users provide incomplete descriptions or plausible but unverified explanations, LLMs may prematurely align with these assumptions and propose solutions before collecting sufficient evidence. We refer to this behavior as user-driven sycophancy: the tendency of an LLM to reinforce a user-provided hypothesis instead of testing alternative explanations. This paper introduces LLM-as-an-Investigator, an evidence-first agentic AI methodology for robust problem diagnosis. The appro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13220","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/2606.13220/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":"2606.13220","created_at":"2026-06-12T01:09:47.262472+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.13220v1","created_at":"2026-06-12T01:09:47.262472+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13220","created_at":"2026-06-12T01:09:47.262472+00:00"},{"alias_kind":"pith_short_12","alias_value":"GVNWFQHEF3IZ","created_at":"2026-06-12T01:09:47.262472+00:00"},{"alias_kind":"pith_short_16","alias_value":"GVNWFQHEF3IZTTGF","created_at":"2026-06-12T01:09:47.262472+00:00"},{"alias_kind":"pith_short_8","alias_value":"GVNWFQHE","created_at":"2026-06-12T01:09:47.262472+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/GVNWFQHEF3IZTTGFJBDJHKJEMY","json":"https://pith.science/pith/GVNWFQHEF3IZTTGFJBDJHKJEMY.json","graph_json":"https://pith.science/api/pith-number/GVNWFQHEF3IZTTGFJBDJHKJEMY/graph.json","events_json":"https://pith.science/api/pith-number/GVNWFQHEF3IZTTGFJBDJHKJEMY/events.json","paper":"https://pith.science/paper/GVNWFQHE"},"agent_actions":{"view_html":"https://pith.science/pith/GVNWFQHEF3IZTTGFJBDJHKJEMY","download_json":"https://pith.science/pith/GVNWFQHEF3IZTTGFJBDJHKJEMY.json","view_paper":"https://pith.science/paper/GVNWFQHE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.13220&json=true","fetch_graph":"https://pith.science/api/pith-number/GVNWFQHEF3IZTTGFJBDJHKJEMY/graph.json","fetch_events":"https://pith.science/api/pith-number/GVNWFQHEF3IZTTGFJBDJHKJEMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GVNWFQHEF3IZTTGFJBDJHKJEMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GVNWFQHEF3IZTTGFJBDJHKJEMY/action/storage_attestation","attest_author":"https://pith.science/pith/GVNWFQHEF3IZTTGFJBDJHKJEMY/action/author_attestation","sign_citation":"https://pith.science/pith/GVNWFQHEF3IZTTGFJBDJHKJEMY/action/citation_signature","submit_replication":"https://pith.science/pith/GVNWFQHEF3IZTTGFJBDJHKJEMY/action/replication_record"}},"created_at":"2026-06-12T01:09:47.262472+00:00","updated_at":"2026-06-12T01:09:47.262472+00:00"}