{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LKLCRJX6HZCGH6FZWXUUOZI3WP","short_pith_number":"pith:LKLCRJX6","canonical_record":{"source":{"id":"2308.01157","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2023-08-02T13:59:35Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e8536c102b7b8c5c3de8aa69e4bb7f717220ab4c8fef1cacc8f63ead23e4c19d","abstract_canon_sha256":"2fbfdf1adc93297e79cec52d7e129368d4ff0f91644d45c4a3326cddfdcb4eef"},"schema_version":"1.0"},"canonical_sha256":"5a9628a6fe3e4463f8b9b5e947651bb3d4e032e542a22c7f89a3c125ca8246be","source":{"kind":"arxiv","id":"2308.01157","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.01157","created_at":"2026-07-05T06:38:03Z"},{"alias_kind":"arxiv_version","alias_value":"2308.01157v2","created_at":"2026-07-05T06:38:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.01157","created_at":"2026-07-05T06:38:03Z"},{"alias_kind":"pith_short_12","alias_value":"LKLCRJX6HZCG","created_at":"2026-07-05T06:38:03Z"},{"alias_kind":"pith_short_16","alias_value":"LKLCRJX6HZCGH6FZ","created_at":"2026-07-05T06:38:03Z"},{"alias_kind":"pith_short_8","alias_value":"LKLCRJX6","created_at":"2026-07-05T06:38:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LKLCRJX6HZCGH6FZWXUUOZI3WP","target":"record","payload":{"canonical_record":{"source":{"id":"2308.01157","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2023-08-02T13:59:35Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e8536c102b7b8c5c3de8aa69e4bb7f717220ab4c8fef1cacc8f63ead23e4c19d","abstract_canon_sha256":"2fbfdf1adc93297e79cec52d7e129368d4ff0f91644d45c4a3326cddfdcb4eef"},"schema_version":"1.0"},"canonical_sha256":"5a9628a6fe3e4463f8b9b5e947651bb3d4e032e542a22c7f89a3c125ca8246be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:38:03.086831Z","signature_b64":"FPG24uUz5YZpOqMJea1d7T6Iru5hlbF0RRG6eQGFoDstHYOmOl9ecmQTM3i2ep2+kjpF6eu7mB9AoOU1hpU8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a9628a6fe3e4463f8b9b5e947651bb3d4e032e542a22c7f89a3c125ca8246be","last_reissued_at":"2026-07-05T06:38:03.086372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:38:03.086372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.01157","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:38:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wONJwnTpSDD8ysk1cnS9KpaJfv12kU3+IJgeKKotF+hiaJNVILR8JdBJs6gyxI4ygNKVjA1CD1WE+WvUQ0WrBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T07:39:41.551412Z"},"content_sha256":"27ff9795c1732bfd80c01ac77a3b95ce30922b8ac98f5e7d7bfa7d1ed7901d7f","schema_version":"1.0","event_id":"sha256:27ff9795c1732bfd80c01ac77a3b95ce30922b8ac98f5e7d7bfa7d1ed7901d7f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LKLCRJX6HZCGH6FZWXUUOZI3WP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLMs Understand Glass-Box Models, Discover Surprises, and Suggest Repairs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Benjamin J. Lengerich, Harsha Nori, Manolis Kellis, Mark E. Nunnally, Rich Caruana, Sebastian Bordt, Yin Aphinyanaphongs","submitted_at":"2023-08-02T13:59:35Z","abstract_excerpt":"We show that large language models (LLMs) are remarkably good at working with interpretable models that decompose complex outcomes into univariate graph-represented components. By adopting a hierarchical approach to reasoning, LLMs can provide comprehensive model-level summaries without ever requiring the entire model to fit in context. This approach enables LLMs to apply their extensive background knowledge to automate common tasks in data science such as detecting anomalies that contradict prior knowledge, describing potential reasons for the anomalies, and suggesting repairs that would remo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.01157","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/2308.01157/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:38:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pBSfPkXOHN7UF1FEBpwbZ1CE3kVyAS42yR3qo09RUV2Im9pvSUJf29a6pB/oIFskW+/6caipqJEB/6Nq16vhAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T07:39:41.551952Z"},"content_sha256":"535568f2f08c17d5577a1614e5a40b335fce33df925ea16ec355153684a2ead2","schema_version":"1.0","event_id":"sha256:535568f2f08c17d5577a1614e5a40b335fce33df925ea16ec355153684a2ead2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LKLCRJX6HZCGH6FZWXUUOZI3WP/bundle.json","state_url":"https://pith.science/pith/LKLCRJX6HZCGH6FZWXUUOZI3WP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LKLCRJX6HZCGH6FZWXUUOZI3WP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-23T07:39:41Z","links":{"resolver":"https://pith.science/pith/LKLCRJX6HZCGH6FZWXUUOZI3WP","bundle":"https://pith.science/pith/LKLCRJX6HZCGH6FZWXUUOZI3WP/bundle.json","state":"https://pith.science/pith/LKLCRJX6HZCGH6FZWXUUOZI3WP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LKLCRJX6HZCGH6FZWXUUOZI3WP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LKLCRJX6HZCGH6FZWXUUOZI3WP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2fbfdf1adc93297e79cec52d7e129368d4ff0f91644d45c4a3326cddfdcb4eef","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2023-08-02T13:59:35Z","title_canon_sha256":"e8536c102b7b8c5c3de8aa69e4bb7f717220ab4c8fef1cacc8f63ead23e4c19d"},"schema_version":"1.0","source":{"id":"2308.01157","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.01157","created_at":"2026-07-05T06:38:03Z"},{"alias_kind":"arxiv_version","alias_value":"2308.01157v2","created_at":"2026-07-05T06:38:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.01157","created_at":"2026-07-05T06:38:03Z"},{"alias_kind":"pith_short_12","alias_value":"LKLCRJX6HZCG","created_at":"2026-07-05T06:38:03Z"},{"alias_kind":"pith_short_16","alias_value":"LKLCRJX6HZCGH6FZ","created_at":"2026-07-05T06:38:03Z"},{"alias_kind":"pith_short_8","alias_value":"LKLCRJX6","created_at":"2026-07-05T06:38:03Z"}],"graph_snapshots":[{"event_id":"sha256:535568f2f08c17d5577a1614e5a40b335fce33df925ea16ec355153684a2ead2","target":"graph","created_at":"2026-07-05T06:38:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2308.01157/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We show that large language models (LLMs) are remarkably good at working with interpretable models that decompose complex outcomes into univariate graph-represented components. By adopting a hierarchical approach to reasoning, LLMs can provide comprehensive model-level summaries without ever requiring the entire model to fit in context. This approach enables LLMs to apply their extensive background knowledge to automate common tasks in data science such as detecting anomalies that contradict prior knowledge, describing potential reasons for the anomalies, and suggesting repairs that would remo","authors_text":"Benjamin J. Lengerich, Harsha Nori, Manolis Kellis, Mark E. Nunnally, Rich Caruana, Sebastian Bordt, Yin Aphinyanaphongs","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2023-08-02T13:59:35Z","title":"LLMs Understand Glass-Box Models, Discover Surprises, and Suggest Repairs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.01157","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:27ff9795c1732bfd80c01ac77a3b95ce30922b8ac98f5e7d7bfa7d1ed7901d7f","target":"record","created_at":"2026-07-05T06:38:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2fbfdf1adc93297e79cec52d7e129368d4ff0f91644d45c4a3326cddfdcb4eef","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2023-08-02T13:59:35Z","title_canon_sha256":"e8536c102b7b8c5c3de8aa69e4bb7f717220ab4c8fef1cacc8f63ead23e4c19d"},"schema_version":"1.0","source":{"id":"2308.01157","kind":"arxiv","version":2}},"canonical_sha256":"5a9628a6fe3e4463f8b9b5e947651bb3d4e032e542a22c7f89a3c125ca8246be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a9628a6fe3e4463f8b9b5e947651bb3d4e032e542a22c7f89a3c125ca8246be","first_computed_at":"2026-07-05T06:38:03.086372Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:38:03.086372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FPG24uUz5YZpOqMJea1d7T6Iru5hlbF0RRG6eQGFoDstHYOmOl9ecmQTM3i2ep2+kjpF6eu7mB9AoOU1hpU8Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:38:03.086831Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.01157","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27ff9795c1732bfd80c01ac77a3b95ce30922b8ac98f5e7d7bfa7d1ed7901d7f","sha256:535568f2f08c17d5577a1614e5a40b335fce33df925ea16ec355153684a2ead2"],"state_sha256":"7efb396ce5a0b167d2084c467763f0696336f95775253a9342acb184b65dc039"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XKdsDu7HrOAQdkH69ysvPPPx77hyN+KTN27NjrldIl5N2hOL4A9clAdo1cW5/vfF5LSFBFTVy0UwvkGBYb7ICA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T07:39:41.556603Z","bundle_sha256":"e4c7eb30f61c69cef89bd292c42adba5d14255f991a514fadf9acb18a69198fc"}}