{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Z3ZEWN7K3MHQDSEEPKJL5PS26L","short_pith_number":"pith:Z3ZEWN7K","canonical_record":{"source":{"id":"2412.07169","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-10T04:03:46Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"73b7477064df1abdf759f9cab2871967177a571d5df556aaa4b732cda01925f0","abstract_canon_sha256":"0d2a522bed09b73b5d746c69613bb3c01c0278e67127f77236c7dac9ab3e3b46"},"schema_version":"1.0"},"canonical_sha256":"cef24b37eadb0f01c8847a92bebe5af2c3a0f5767c83aec2d26a11e592988050","source":{"kind":"arxiv","id":"2412.07169","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.07169","created_at":"2026-07-05T11:15:18Z"},{"alias_kind":"arxiv_version","alias_value":"2412.07169v4","created_at":"2026-07-05T11:15:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07169","created_at":"2026-07-05T11:15:18Z"},{"alias_kind":"pith_short_12","alias_value":"Z3ZEWN7K3MHQ","created_at":"2026-07-05T11:15:18Z"},{"alias_kind":"pith_short_16","alias_value":"Z3ZEWN7K3MHQDSEE","created_at":"2026-07-05T11:15:18Z"},{"alias_kind":"pith_short_8","alias_value":"Z3ZEWN7K","created_at":"2026-07-05T11:15:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Z3ZEWN7K3MHQDSEEPKJL5PS26L","target":"record","payload":{"canonical_record":{"source":{"id":"2412.07169","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-10T04:03:46Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"73b7477064df1abdf759f9cab2871967177a571d5df556aaa4b732cda01925f0","abstract_canon_sha256":"0d2a522bed09b73b5d746c69613bb3c01c0278e67127f77236c7dac9ab3e3b46"},"schema_version":"1.0"},"canonical_sha256":"cef24b37eadb0f01c8847a92bebe5af2c3a0f5767c83aec2d26a11e592988050","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:18.663328Z","signature_b64":"+SkTj6+OW9MgpmB10KZ5shzO0XZyVW6ySBmkPq/GxDP3v8m1dFzIOe1bGtmOE32XWJ3lyYwcccSQQ6vDRWJABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cef24b37eadb0f01c8847a92bebe5af2c3a0f5767c83aec2d26a11e592988050","last_reissued_at":"2026-07-05T11:15:18.662804Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:18.662804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.07169","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":"2026-07-05T11:15:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g/1gyP2I1FRjMFWaDml/m3D275AclBuSiNBEUC0qm/oPnZ8elHfP3I2eXgu9A8SZcVFRBJiy0eOAwkOLsjb2CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:04:16.009941Z"},"content_sha256":"196832ca2d6fb4e70d836112a530562326009c43cf587ab071d1b0b46166be9a","schema_version":"1.0","event_id":"sha256:196832ca2d6fb4e70d836112a530562326009c43cf587ab071d1b0b46166be9a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Z3ZEWN7K3MHQDSEEPKJL5PS26L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"John A. Onofrey, Lawrence H. Staib, Ravid Shwartz-Ziv, Tal Zeevi, Yann LeCun","submitted_at":"2024-12-10T04:03:46Z","abstract_excerpt":"Accurate uncertainty estimation is crucial for deploying neural networks in risk-sensitive applications such as medical diagnosis. Monte Carlo Dropout is a widely used technique for approximating predictive uncertainty by performing stochastic forward passes with dropout during inference. However, using static dropout rates across all layers and inputs can lead to suboptimal uncertainty estimates, as it fails to adapt to the varying characteristics of individual inputs and network layers. Existing approaches optimize dropout rates during training using labeled data, resulting in fixed inferenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07169","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/2412.07169/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":"2026-07-05T11:15:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"USw/c7TQpHJVTHl9n80q8FTV79pMtDpDTp5XlOf+RAVM1QQj5CjXxwyv8QxeLwKahgn+5A78fOOKolxlDTsYDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:04:16.011172Z"},"content_sha256":"4e241be2f24910d249bca0a6e278e9bed28f370a498176d93a925fe3fc51cb15","schema_version":"1.0","event_id":"sha256:4e241be2f24910d249bca0a6e278e9bed28f370a498176d93a925fe3fc51cb15"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z3ZEWN7K3MHQDSEEPKJL5PS26L/bundle.json","state_url":"https://pith.science/pith/Z3ZEWN7K3MHQDSEEPKJL5PS26L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z3ZEWN7K3MHQDSEEPKJL5PS26L/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":"2026-08-14T09:04:16Z","links":{"resolver":"https://pith.science/pith/Z3ZEWN7K3MHQDSEEPKJL5PS26L","bundle":"https://pith.science/pith/Z3ZEWN7K3MHQDSEEPKJL5PS26L/bundle.json","state":"https://pith.science/pith/Z3ZEWN7K3MHQDSEEPKJL5PS26L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z3ZEWN7K3MHQDSEEPKJL5PS26L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Z3ZEWN7K3MHQDSEEPKJL5PS26L","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":"0d2a522bed09b73b5d746c69613bb3c01c0278e67127f77236c7dac9ab3e3b46","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-10T04:03:46Z","title_canon_sha256":"73b7477064df1abdf759f9cab2871967177a571d5df556aaa4b732cda01925f0"},"schema_version":"1.0","source":{"id":"2412.07169","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.07169","created_at":"2026-07-05T11:15:18Z"},{"alias_kind":"arxiv_version","alias_value":"2412.07169v4","created_at":"2026-07-05T11:15:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07169","created_at":"2026-07-05T11:15:18Z"},{"alias_kind":"pith_short_12","alias_value":"Z3ZEWN7K3MHQ","created_at":"2026-07-05T11:15:18Z"},{"alias_kind":"pith_short_16","alias_value":"Z3ZEWN7K3MHQDSEE","created_at":"2026-07-05T11:15:18Z"},{"alias_kind":"pith_short_8","alias_value":"Z3ZEWN7K","created_at":"2026-07-05T11:15:18Z"}],"graph_snapshots":[{"event_id":"sha256:4e241be2f24910d249bca0a6e278e9bed28f370a498176d93a925fe3fc51cb15","target":"graph","created_at":"2026-07-05T11:15:18Z","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/2412.07169/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Accurate uncertainty estimation is crucial for deploying neural networks in risk-sensitive applications such as medical diagnosis. Monte Carlo Dropout is a widely used technique for approximating predictive uncertainty by performing stochastic forward passes with dropout during inference. However, using static dropout rates across all layers and inputs can lead to suboptimal uncertainty estimates, as it fails to adapt to the varying characteristics of individual inputs and network layers. Existing approaches optimize dropout rates during training using labeled data, resulting in fixed inferenc","authors_text":"John A. Onofrey, Lawrence H. Staib, Ravid Shwartz-Ziv, Tal Zeevi, Yann LeCun","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07169","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":"sha256:196832ca2d6fb4e70d836112a530562326009c43cf587ab071d1b0b46166be9a","target":"record","created_at":"2026-07-05T11:15:18Z","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":"0d2a522bed09b73b5d746c69613bb3c01c0278e67127f77236c7dac9ab3e3b46","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-10T04:03:46Z","title_canon_sha256":"73b7477064df1abdf759f9cab2871967177a571d5df556aaa4b732cda01925f0"},"schema_version":"1.0","source":{"id":"2412.07169","kind":"arxiv","version":4}},"canonical_sha256":"cef24b37eadb0f01c8847a92bebe5af2c3a0f5767c83aec2d26a11e592988050","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cef24b37eadb0f01c8847a92bebe5af2c3a0f5767c83aec2d26a11e592988050","first_computed_at":"2026-07-05T11:15:18.662804Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:18.662804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+SkTj6+OW9MgpmB10KZ5shzO0XZyVW6ySBmkPq/GxDP3v8m1dFzIOe1bGtmOE32XWJ3lyYwcccSQQ6vDRWJABQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:18.663328Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.07169","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:196832ca2d6fb4e70d836112a530562326009c43cf587ab071d1b0b46166be9a","sha256:4e241be2f24910d249bca0a6e278e9bed28f370a498176d93a925fe3fc51cb15"],"state_sha256":"dd0edd674d263ba5315bae077bd6fee1c247fc3a7365741f6d5869be38677286"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aLiySqBzMhGHXk+wtv76ToVhwCATO0C0trVjOfMQMcyyhD2+o717jj+LpVIK8WTQNS2tAoPnebkTZDV64oxVCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T09:04:16.018009Z","bundle_sha256":"99c6d065887e1f77e63a96d3314b5f400139ef08486c9b5867f0399ef965d64b"}}