{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JANXLI64TDZ625CIGKQF7RW43J","short_pith_number":"pith:JANXLI64","canonical_record":{"source":{"id":"2501.09345","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T07:58:33Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"0a672e7225d44860cfb905a917f019ecfb74dfe5db49ae5b2f357254dba6a22d","abstract_canon_sha256":"0cc362a7ab8544df0175186ed725adb0d8c1f22180dd55d462362e5af763fe29"},"schema_version":"1.0"},"canonical_sha256":"481b75a3dc98f3ed744832a05fc6dcda6c24fcba879293b240a425bae3508381","source":{"kind":"arxiv","id":"2501.09345","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09345","created_at":"2026-07-05T11:17:39Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09345v4","created_at":"2026-07-05T11:17:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09345","created_at":"2026-07-05T11:17:39Z"},{"alias_kind":"pith_short_12","alias_value":"JANXLI64TDZ6","created_at":"2026-07-05T11:17:39Z"},{"alias_kind":"pith_short_16","alias_value":"JANXLI64TDZ625CI","created_at":"2026-07-05T11:17:39Z"},{"alias_kind":"pith_short_8","alias_value":"JANXLI64","created_at":"2026-07-05T11:17:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JANXLI64TDZ625CIGKQF7RW43J","target":"record","payload":{"canonical_record":{"source":{"id":"2501.09345","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T07:58:33Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"0a672e7225d44860cfb905a917f019ecfb74dfe5db49ae5b2f357254dba6a22d","abstract_canon_sha256":"0cc362a7ab8544df0175186ed725adb0d8c1f22180dd55d462362e5af763fe29"},"schema_version":"1.0"},"canonical_sha256":"481b75a3dc98f3ed744832a05fc6dcda6c24fcba879293b240a425bae3508381","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:39.844172Z","signature_b64":"TDRiIVvyVLoHEpb3kwiorOKvjT1OL+INIPQhYdF5S91/NeV8Jck5CA6on4HP43Q2h0Mq9k9iOdcGS9CHqUTSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"481b75a3dc98f3ed744832a05fc6dcda6c24fcba879293b240a425bae3508381","last_reissued_at":"2026-07-05T11:17:39.843704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:39.843704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.09345","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:17:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nubk8bhhifrJhJFsWkua4s8hKWXhIaLzTrU16KJKRaOWeeWMrgScfmJwYTBt+TOJi+9BFES+QNYUXuC+zc9UAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:21:10.248032Z"},"content_sha256":"0b532cfda40532533994ba5f1e52503af6317705e5a434d18a0b8fe41c63fe8b","schema_version":"1.0","event_id":"sha256:0b532cfda40532533994ba5f1e52503af6317705e5a434d18a0b8fe41c63fe8b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JANXLI64TDZ625CIGKQF7RW43J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rational Tuning of LLM Cascades via Probabilistic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Matt Thomson, Michael J. Zellinger","submitted_at":"2025-01-16T07:58:33Z","abstract_excerpt":"Understanding the reliability of large language models (LLMs) has recently garnered significant attention. Given LLMs' propensity to hallucinate, as well as their high sensitivity to prompt design, it is already challenging to predict the performance of an individual LLM. However, the problem becomes more complex for compound LLM systems such as cascades, where in addition to each model's standalone performance, we must understand how the error rates of different models interact. In this paper, we present a probabilistic model for the joint performance distribution of a sequence of LLMs, which"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09345","kind":"arxiv","version":4},"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/2501.09345/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":"2026-07-05T11:17:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3Usn8zTmtS/Ge5WLTmD/6R8li5o07aCHIqMDbhm8t/cGNSwzmngz9YjdmNaYurUzzVfZRxBtVv1pAvWwE0z5AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:21:10.248640Z"},"content_sha256":"34c4a9fb7fccde295ef1cb56ded28e50c5082b6a63b8147a123e9b7758210c8c","schema_version":"1.0","event_id":"sha256:34c4a9fb7fccde295ef1cb56ded28e50c5082b6a63b8147a123e9b7758210c8c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JANXLI64TDZ625CIGKQF7RW43J/bundle.json","state_url":"https://pith.science/pith/JANXLI64TDZ625CIGKQF7RW43J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JANXLI64TDZ625CIGKQF7RW43J/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":"2026-08-09T08:21:10Z","links":{"resolver":"https://pith.science/pith/JANXLI64TDZ625CIGKQF7RW43J","bundle":"https://pith.science/pith/JANXLI64TDZ625CIGKQF7RW43J/bundle.json","state":"https://pith.science/pith/JANXLI64TDZ625CIGKQF7RW43J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JANXLI64TDZ625CIGKQF7RW43J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JANXLI64TDZ625CIGKQF7RW43J","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":"0cc362a7ab8544df0175186ed725adb0d8c1f22180dd55d462362e5af763fe29","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T07:58:33Z","title_canon_sha256":"0a672e7225d44860cfb905a917f019ecfb74dfe5db49ae5b2f357254dba6a22d"},"schema_version":"1.0","source":{"id":"2501.09345","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09345","created_at":"2026-07-05T11:17:39Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09345v4","created_at":"2026-07-05T11:17:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09345","created_at":"2026-07-05T11:17:39Z"},{"alias_kind":"pith_short_12","alias_value":"JANXLI64TDZ6","created_at":"2026-07-05T11:17:39Z"},{"alias_kind":"pith_short_16","alias_value":"JANXLI64TDZ625CI","created_at":"2026-07-05T11:17:39Z"},{"alias_kind":"pith_short_8","alias_value":"JANXLI64","created_at":"2026-07-05T11:17:39Z"}],"graph_snapshots":[{"event_id":"sha256:34c4a9fb7fccde295ef1cb56ded28e50c5082b6a63b8147a123e9b7758210c8c","target":"graph","created_at":"2026-07-05T11:17:39Z","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/2501.09345/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding the reliability of large language models (LLMs) has recently garnered significant attention. Given LLMs' propensity to hallucinate, as well as their high sensitivity to prompt design, it is already challenging to predict the performance of an individual LLM. However, the problem becomes more complex for compound LLM systems such as cascades, where in addition to each model's standalone performance, we must understand how the error rates of different models interact. In this paper, we present a probabilistic model for the joint performance distribution of a sequence of LLMs, which","authors_text":"Matt Thomson, Michael J. Zellinger","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T07:58:33Z","title":"Rational Tuning of LLM Cascades via Probabilistic Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09345","kind":"arxiv","version":4},"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":"sha256:0b532cfda40532533994ba5f1e52503af6317705e5a434d18a0b8fe41c63fe8b","target":"record","created_at":"2026-07-05T11:17:39Z","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":"0cc362a7ab8544df0175186ed725adb0d8c1f22180dd55d462362e5af763fe29","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T07:58:33Z","title_canon_sha256":"0a672e7225d44860cfb905a917f019ecfb74dfe5db49ae5b2f357254dba6a22d"},"schema_version":"1.0","source":{"id":"2501.09345","kind":"arxiv","version":4}},"canonical_sha256":"481b75a3dc98f3ed744832a05fc6dcda6c24fcba879293b240a425bae3508381","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"481b75a3dc98f3ed744832a05fc6dcda6c24fcba879293b240a425bae3508381","first_computed_at":"2026-07-05T11:17:39.843704Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:39.843704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TDRiIVvyVLoHEpb3kwiorOKvjT1OL+INIPQhYdF5S91/NeV8Jck5CA6on4HP43Q2h0Mq9k9iOdcGS9CHqUTSCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:39.844172Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.09345","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b532cfda40532533994ba5f1e52503af6317705e5a434d18a0b8fe41c63fe8b","sha256:34c4a9fb7fccde295ef1cb56ded28e50c5082b6a63b8147a123e9b7758210c8c"],"state_sha256":"1a9a4dd43490d7cf764c41444a3cf4d9c7250c671b92e26b20abb4f71ebd7c84"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LZsal439sz1xI9m0toec+maa8pagUOlR1M5/xIzZymyWMf1XPxOL8BEEg078Vlc0m6ilRLx/tnVaNlY+4ODlCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T08:21:10.253931Z","bundle_sha256":"4eac836e895b1d43f1360ddca777eb1bcf70f0ca5cf93849375d2ced96ff1ebd"}}