{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EGJNKZV27LDJRNWQUWX7AFFH2S","short_pith_number":"pith:EGJNKZV2","schema_version":"1.0","canonical_sha256":"2192d566bafac698b6d0a5aff014a7d4ae48b93695d249340926de3e8ecea100","source":{"kind":"arxiv","id":"2402.01761","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Interpretability in the Era of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chandan Singh, Jeevana Priya Inala, Jianfeng Gao, Michel Galley, Rich Caruana","submitted_at":"2024-01-30T17:38:54Z","abstract_excerpt":"Interpretable machine learning has exploded as an area of interest over the last decade, sparked by the rise of increasingly large datasets and deep neural networks. Simultaneously, large language models (LLMs) have demonstrated remarkable capabilities across a wide array of tasks, offering a chance to rethink opportunities in interpretable machine learning. Notably, the capability to explain in natural language allows LLMs to expand the scale and complexity of patterns that can be given to a human. However, these new capabilities raise new challenges, such as hallucinated explanations and imm"},"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":"2402.01761","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-30T17:38:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6c30d396948cc32641645992aa92f07cca4fa3a2088d574b8ecd7c94d8394274","abstract_canon_sha256":"7c6e58d5dea5d4f899c95712733f3a3e5c925ce3a52488f02cbc253a81d94444"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:06.405826Z","signature_b64":"bQ4IBELWw8GvHz6fxueuPrx+t+zdk/qJ4Wro9NmCsd2anLDCRSBsr9Ih0w5KdOp1Kv+rp2kpPXGVtOZyYp4LAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2192d566bafac698b6d0a5aff014a7d4ae48b93695d249340926de3e8ecea100","last_reissued_at":"2026-07-05T07:41:06.405325Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:06.405325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Interpretability in the Era of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chandan Singh, Jeevana Priya Inala, Jianfeng Gao, Michel Galley, Rich Caruana","submitted_at":"2024-01-30T17:38:54Z","abstract_excerpt":"Interpretable machine learning has exploded as an area of interest over the last decade, sparked by the rise of increasingly large datasets and deep neural networks. Simultaneously, large language models (LLMs) have demonstrated remarkable capabilities across a wide array of tasks, offering a chance to rethink opportunities in interpretable machine learning. Notably, the capability to explain in natural language allows LLMs to expand the scale and complexity of patterns that can be given to a human. However, these new capabilities raise new challenges, such as hallucinated explanations and imm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01761","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/2402.01761/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":"2402.01761","created_at":"2026-07-05T07:41:06.405381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01761v1","created_at":"2026-07-05T07:41:06.405381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01761","created_at":"2026-07-05T07:41:06.405381+00:00"},{"alias_kind":"pith_short_12","alias_value":"EGJNKZV27LDJ","created_at":"2026-07-05T07:41:06.405381+00:00"},{"alias_kind":"pith_short_16","alias_value":"EGJNKZV27LDJRNWQ","created_at":"2026-07-05T07:41:06.405381+00:00"},{"alias_kind":"pith_short_8","alias_value":"EGJNKZV2","created_at":"2026-07-05T07:41:06.405381+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23840","citing_title":"Embodied Explainability and Ontological Obstacles: Why We Struggle to Explain the Answers of Large Language Models (LLMs)","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01686","citing_title":"WARP: Weight-Space Analysis for Recovering Training Data Portfolios","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10210","citing_title":"AnnotateThis: Analyzing a human-LLM system for annotating social media data with the concept of climate change mitigation pessimism","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01844","citing_title":"The Cylindrical Representation Hypothesis for Language Model Steering","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27970","citing_title":"Geometry of Human Perceptual Domains Emerges Transiently in LLM Representations","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10933","citing_title":"DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices","ref_index":121,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18801","citing_title":"Position: Let's Develop Data Probes to Fundamentally Understand How Data Affects LLM Performance","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2506.09749","citing_title":"Large Language Models for Combinatorial Optimization of Design Structure Matrix","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22403","citing_title":"MoveFM-R: Advancing Mobility Foundation Models via Language-driven Semantic Reasoning","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2602.19770","citing_title":"The Confusion is Real: GRAPHIC -- A Network Science Approach to Confusion Matrices in Deep Learning","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12639","citing_title":"OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2603.29025","citing_title":"The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03976","citing_title":"Quantifying Trust: Financial Risk Management for Trustworthy AI Agents","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10933","citing_title":"DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices","ref_index":121,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10933","citing_title":"DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices","ref_index":121,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10172","citing_title":"Wearable AI in the Era of Large Sensor Models","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04066","citing_title":"Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning","ref_index":136,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04065","citing_title":"Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs","ref_index":151,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EGJNKZV27LDJRNWQUWX7AFFH2S","json":"https://pith.science/pith/EGJNKZV27LDJRNWQUWX7AFFH2S.json","graph_json":"https://pith.science/api/pith-number/EGJNKZV27LDJRNWQUWX7AFFH2S/graph.json","events_json":"https://pith.science/api/pith-number/EGJNKZV27LDJRNWQUWX7AFFH2S/events.json","paper":"https://pith.science/paper/EGJNKZV2"},"agent_actions":{"view_html":"https://pith.science/pith/EGJNKZV27LDJRNWQUWX7AFFH2S","download_json":"https://pith.science/pith/EGJNKZV27LDJRNWQUWX7AFFH2S.json","view_paper":"https://pith.science/paper/EGJNKZV2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01761&json=true","fetch_graph":"https://pith.science/api/pith-number/EGJNKZV27LDJRNWQUWX7AFFH2S/graph.json","fetch_events":"https://pith.science/api/pith-number/EGJNKZV27LDJRNWQUWX7AFFH2S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EGJNKZV27LDJRNWQUWX7AFFH2S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EGJNKZV27LDJRNWQUWX7AFFH2S/action/storage_attestation","attest_author":"https://pith.science/pith/EGJNKZV27LDJRNWQUWX7AFFH2S/action/author_attestation","sign_citation":"https://pith.science/pith/EGJNKZV27LDJRNWQUWX7AFFH2S/action/citation_signature","submit_replication":"https://pith.science/pith/EGJNKZV27LDJRNWQUWX7AFFH2S/action/replication_record"}},"created_at":"2026-07-05T07:41:06.405381+00:00","updated_at":"2026-07-05T07:41:06.405381+00:00"}