{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:RABWPPG25HIHVKRICQ2R7NRBIN","short_pith_number":"pith:RABWPPG2","canonical_record":{"source":{"id":"2210.12928","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-24T03:00:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b7e0101f271a1f1b496070878d4ac3a0b812fc0433ce42328be2ca1aea85a5ac","abstract_canon_sha256":"31630d44584adda7d1c067b833ab8fdd4633a60e7ad2334d78946996e1337be4"},"schema_version":"1.0"},"canonical_sha256":"880367bcdae9d07aaa2814351fb621435473b2c43f3ebc93ddde5cdf7f6a8bc1","source":{"kind":"arxiv","id":"2210.12928","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.12928","created_at":"2026-07-05T06:24:10Z"},{"alias_kind":"arxiv_version","alias_value":"2210.12928v3","created_at":"2026-07-05T06:24:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12928","created_at":"2026-07-05T06:24:10Z"},{"alias_kind":"pith_short_12","alias_value":"RABWPPG25HIH","created_at":"2026-07-05T06:24:10Z"},{"alias_kind":"pith_short_16","alias_value":"RABWPPG25HIHVKRI","created_at":"2026-07-05T06:24:10Z"},{"alias_kind":"pith_short_8","alias_value":"RABWPPG2","created_at":"2026-07-05T06:24:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:RABWPPG25HIHVKRICQ2R7NRBIN","target":"record","payload":{"canonical_record":{"source":{"id":"2210.12928","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-24T03:00:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b7e0101f271a1f1b496070878d4ac3a0b812fc0433ce42328be2ca1aea85a5ac","abstract_canon_sha256":"31630d44584adda7d1c067b833ab8fdd4633a60e7ad2334d78946996e1337be4"},"schema_version":"1.0"},"canonical_sha256":"880367bcdae9d07aaa2814351fb621435473b2c43f3ebc93ddde5cdf7f6a8bc1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:10.375017Z","signature_b64":"ASStzwAU24vJgQOfsm68dbeHaIre0ENIpzPiEMCQqEiUIn6o7/K6oW4bceyNUbqrWu1UYjedWlGnylvS6U94Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"880367bcdae9d07aaa2814351fb621435473b2c43f3ebc93ddde5cdf7f6a8bc1","last_reissued_at":"2026-07-05T06:24:10.374604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:10.374604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.12928","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:24:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pjhgc66KwlLLKZHWmyNRwAz2vVS8/huPfFMH2Y1d3qq7paApHfAvvvxUYN0ucNRxrHZU1RNjTqIF/9VJ/cBuBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T01:49:22.876822Z"},"content_sha256":"72724d3d6e2d674833f3b6c1f7916bb5982ac0b1773940d346c4853f4ded4a23","schema_version":"1.0","event_id":"sha256:72724d3d6e2d674833f3b6c1f7916bb5982ac0b1773940d346c4853f4ded4a23"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:RABWPPG25HIHVKRICQ2R7NRBIN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GFlowOut: Dropout with Generative Flow Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anirudh Goyal, Bonaventure Dossou, Chris Emezue, Dianbo Liu, Dinghuai Zhang, Kenji Kawaguchi, Moksh Jain, Nadhir Hassen, Nikolay Malkin, Qianli Shen, Salem Lahlou, Xu ji, Yoshua Bengio","submitted_at":"2022-10-24T03:00:01Z","abstract_excerpt":"Bayesian Inference offers principled tools to tackle many critical problems with modern neural networks such as poor calibration and generalization, and data inefficiency. However, scaling Bayesian inference to large architectures is challenging and requires restrictive approximations. Monte Carlo Dropout has been widely used as a relatively cheap way for approximate Inference and to estimate uncertainty with deep neural networks. Traditionally, the dropout mask is sampled independently from a fixed distribution. Recent works show that the dropout mask can be viewed as a latent variable, which"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12928","kind":"arxiv","version":3},"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/2210.12928/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":"2026-07-05T06:24:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7yOB0HeL5C5FYy+AhomTMUm6CGkTnzqbR2EeqdFsfGNSavAaxSDto8vM5HUA3bHKjJvuxavfhFid/e0X86OgDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T01:49:22.877344Z"},"content_sha256":"8df154395956d9db24593422ec475d09b3f5e645c1dcac63553accf495fcb424","schema_version":"1.0","event_id":"sha256:8df154395956d9db24593422ec475d09b3f5e645c1dcac63553accf495fcb424"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RABWPPG25HIHVKRICQ2R7NRBIN/bundle.json","state_url":"https://pith.science/pith/RABWPPG25HIHVKRICQ2R7NRBIN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RABWPPG25HIHVKRICQ2R7NRBIN/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":"2026-08-20T01:49:22Z","links":{"resolver":"https://pith.science/pith/RABWPPG25HIHVKRICQ2R7NRBIN","bundle":"https://pith.science/pith/RABWPPG25HIHVKRICQ2R7NRBIN/bundle.json","state":"https://pith.science/pith/RABWPPG25HIHVKRICQ2R7NRBIN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RABWPPG25HIHVKRICQ2R7NRBIN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RABWPPG25HIHVKRICQ2R7NRBIN","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":"31630d44584adda7d1c067b833ab8fdd4633a60e7ad2334d78946996e1337be4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-24T03:00:01Z","title_canon_sha256":"b7e0101f271a1f1b496070878d4ac3a0b812fc0433ce42328be2ca1aea85a5ac"},"schema_version":"1.0","source":{"id":"2210.12928","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.12928","created_at":"2026-07-05T06:24:10Z"},{"alias_kind":"arxiv_version","alias_value":"2210.12928v3","created_at":"2026-07-05T06:24:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12928","created_at":"2026-07-05T06:24:10Z"},{"alias_kind":"pith_short_12","alias_value":"RABWPPG25HIH","created_at":"2026-07-05T06:24:10Z"},{"alias_kind":"pith_short_16","alias_value":"RABWPPG25HIHVKRI","created_at":"2026-07-05T06:24:10Z"},{"alias_kind":"pith_short_8","alias_value":"RABWPPG2","created_at":"2026-07-05T06:24:10Z"}],"graph_snapshots":[{"event_id":"sha256:8df154395956d9db24593422ec475d09b3f5e645c1dcac63553accf495fcb424","target":"graph","created_at":"2026-07-05T06:24:10Z","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/2210.12928/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Bayesian Inference offers principled tools to tackle many critical problems with modern neural networks such as poor calibration and generalization, and data inefficiency. However, scaling Bayesian inference to large architectures is challenging and requires restrictive approximations. Monte Carlo Dropout has been widely used as a relatively cheap way for approximate Inference and to estimate uncertainty with deep neural networks. Traditionally, the dropout mask is sampled independently from a fixed distribution. Recent works show that the dropout mask can be viewed as a latent variable, which","authors_text":"Anirudh Goyal, Bonaventure Dossou, Chris Emezue, Dianbo Liu, Dinghuai Zhang, Kenji Kawaguchi, Moksh Jain, Nadhir Hassen, Nikolay Malkin, Qianli Shen, Salem Lahlou, Xu ji, Yoshua Bengio","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-24T03:00:01Z","title":"GFlowOut: Dropout with Generative Flow Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12928","kind":"arxiv","version":3},"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":"sha256:72724d3d6e2d674833f3b6c1f7916bb5982ac0b1773940d346c4853f4ded4a23","target":"record","created_at":"2026-07-05T06:24:10Z","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":"31630d44584adda7d1c067b833ab8fdd4633a60e7ad2334d78946996e1337be4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-24T03:00:01Z","title_canon_sha256":"b7e0101f271a1f1b496070878d4ac3a0b812fc0433ce42328be2ca1aea85a5ac"},"schema_version":"1.0","source":{"id":"2210.12928","kind":"arxiv","version":3}},"canonical_sha256":"880367bcdae9d07aaa2814351fb621435473b2c43f3ebc93ddde5cdf7f6a8bc1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"880367bcdae9d07aaa2814351fb621435473b2c43f3ebc93ddde5cdf7f6a8bc1","first_computed_at":"2026-07-05T06:24:10.374604Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:24:10.374604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ASStzwAU24vJgQOfsm68dbeHaIre0ENIpzPiEMCQqEiUIn6o7/K6oW4bceyNUbqrWu1UYjedWlGnylvS6U94Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:24:10.375017Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.12928","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72724d3d6e2d674833f3b6c1f7916bb5982ac0b1773940d346c4853f4ded4a23","sha256:8df154395956d9db24593422ec475d09b3f5e645c1dcac63553accf495fcb424"],"state_sha256":"3321d0d3d169c3770cc197343f62b99c4a1236d54d856c5b7a87966e882828ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iAB8VjTcWxqtD0C57TyJDzf1feltbbJq/HWQtTj+OsjtS5E7VVuFovonmwNDgULazetR05SVdpno6tSfFpWEDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T01:49:22.881680Z","bundle_sha256":"77212221c915e20958736e9794767d7a66e345691dca1445522676bb6f619a8f"}}