{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YUL4QR7L6L63MWHQLZJN3W2Y4Y","short_pith_number":"pith:YUL4QR7L","schema_version":"1.0","canonical_sha256":"c517c847ebf2fdb658f05e52dddb58e61139315a3d7c02d2ec87e7d34156fa4e","source":{"kind":"arxiv","id":"2405.00708","version":2},"attestation_state":"computed","paper":{"title":"Understanding Large Language Model Behaviors through Interactive Counterfactual Generation and Analysis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Daniel F\\\"urst, Furui Cheng, Hendrik Strobelt, Mennatallah El-Assady, Robin Shing Moon Chan, Vil\\'em Zouhar","submitted_at":"2024-04-23T19:57:03Z","abstract_excerpt":"Understanding the behavior of large language models (LLMs) is crucial for ensuring their safe and reliable use. However, existing explainable AI (XAI) methods for LLMs primarily rely on word-level explanations, which are often computationally inefficient and misaligned with human reasoning processes. Moreover, these methods often treat explanation as a one-time output, overlooking its inherently interactive and iterative nature. In this paper, we present LLM Analyzer, an interactive visualization system that addresses these limitations by enabling intuitive and efficient exploration of LLM beh"},"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":"2405.00708","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T19:57:03Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"title_canon_sha256":"ef4776dabfaebee30b14377857ec7827ac1081514ba604acd0c464823dccd31e","abstract_canon_sha256":"f44af10c977824b517d254f0ec83550907202f3da169fcbfc89fd74f9eaa10a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:45.465709Z","signature_b64":"VPaL/LY5s8pTK4n+AN1aM4Ract3C2yyybRKotNqlr+wEoIxgV030kuqnxlavyh3ArQJzniK8HVBikQWBO+xPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c517c847ebf2fdb658f05e52dddb58e61139315a3d7c02d2ec87e7d34156fa4e","last_reissued_at":"2026-07-05T11:49:45.465236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:45.465236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Large Language Model Behaviors through Interactive Counterfactual Generation and Analysis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Daniel F\\\"urst, Furui Cheng, Hendrik Strobelt, Mennatallah El-Assady, Robin Shing Moon Chan, Vil\\'em Zouhar","submitted_at":"2024-04-23T19:57:03Z","abstract_excerpt":"Understanding the behavior of large language models (LLMs) is crucial for ensuring their safe and reliable use. However, existing explainable AI (XAI) methods for LLMs primarily rely on word-level explanations, which are often computationally inefficient and misaligned with human reasoning processes. Moreover, these methods often treat explanation as a one-time output, overlooking its inherently interactive and iterative nature. In this paper, we present LLM Analyzer, an interactive visualization system that addresses these limitations by enabling intuitive and efficient exploration of LLM beh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00708","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/2405.00708/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":"2405.00708","created_at":"2026-07-05T11:49:45.465291+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.00708v2","created_at":"2026-07-05T11:49:45.465291+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00708","created_at":"2026-07-05T11:49:45.465291+00:00"},{"alias_kind":"pith_short_12","alias_value":"YUL4QR7L6L63","created_at":"2026-07-05T11:49:45.465291+00:00"},{"alias_kind":"pith_short_16","alias_value":"YUL4QR7L6L63MWHQ","created_at":"2026-07-05T11:49:45.465291+00:00"},{"alias_kind":"pith_short_8","alias_value":"YUL4QR7L","created_at":"2026-07-05T11:49:45.465291+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.10915","citing_title":"Bias in Large Language Models: Origin, Evaluation, and Mitigation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04313","citing_title":"NoisyCausal: A Benchmark for Evaluating Causal Reasoning Under Structured Noise","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YUL4QR7L6L63MWHQLZJN3W2Y4Y","json":"https://pith.science/pith/YUL4QR7L6L63MWHQLZJN3W2Y4Y.json","graph_json":"https://pith.science/api/pith-number/YUL4QR7L6L63MWHQLZJN3W2Y4Y/graph.json","events_json":"https://pith.science/api/pith-number/YUL4QR7L6L63MWHQLZJN3W2Y4Y/events.json","paper":"https://pith.science/paper/YUL4QR7L"},"agent_actions":{"view_html":"https://pith.science/pith/YUL4QR7L6L63MWHQLZJN3W2Y4Y","download_json":"https://pith.science/pith/YUL4QR7L6L63MWHQLZJN3W2Y4Y.json","view_paper":"https://pith.science/paper/YUL4QR7L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.00708&json=true","fetch_graph":"https://pith.science/api/pith-number/YUL4QR7L6L63MWHQLZJN3W2Y4Y/graph.json","fetch_events":"https://pith.science/api/pith-number/YUL4QR7L6L63MWHQLZJN3W2Y4Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YUL4QR7L6L63MWHQLZJN3W2Y4Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YUL4QR7L6L63MWHQLZJN3W2Y4Y/action/storage_attestation","attest_author":"https://pith.science/pith/YUL4QR7L6L63MWHQLZJN3W2Y4Y/action/author_attestation","sign_citation":"https://pith.science/pith/YUL4QR7L6L63MWHQLZJN3W2Y4Y/action/citation_signature","submit_replication":"https://pith.science/pith/YUL4QR7L6L63MWHQLZJN3W2Y4Y/action/replication_record"}},"created_at":"2026-07-05T11:49:45.465291+00:00","updated_at":"2026-07-05T11:49:45.465291+00:00"}