{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:7QM3RQKE7QXU5APF4KCLDODFLU","short_pith_number":"pith:7QM3RQKE","canonical_record":{"source":{"id":"2110.00276","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-10-01T09:04:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"439869b7ac6121ca1c8e09741f857486a7bac79f1801062803c183ab7947fd8e","abstract_canon_sha256":"aecce467e627f851778d980e9ac830b8ddf925713857301dcce7cacc37d53852"},"schema_version":"1.0"},"canonical_sha256":"fc19b8c144fc2f4e81e5e284b1b8655d2ef8eee2924517a5945efa386bebb21a","source":{"kind":"arxiv","id":"2110.00276","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.00276","created_at":"2026-07-05T03:19:28Z"},{"alias_kind":"arxiv_version","alias_value":"2110.00276v1","created_at":"2026-07-05T03:19:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.00276","created_at":"2026-07-05T03:19:28Z"},{"alias_kind":"pith_short_12","alias_value":"7QM3RQKE7QXU","created_at":"2026-07-05T03:19:28Z"},{"alias_kind":"pith_short_16","alias_value":"7QM3RQKE7QXU5APF","created_at":"2026-07-05T03:19:28Z"},{"alias_kind":"pith_short_8","alias_value":"7QM3RQKE","created_at":"2026-07-05T03:19:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:7QM3RQKE7QXU5APF4KCLDODFLU","target":"record","payload":{"canonical_record":{"source":{"id":"2110.00276","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-10-01T09:04:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"439869b7ac6121ca1c8e09741f857486a7bac79f1801062803c183ab7947fd8e","abstract_canon_sha256":"aecce467e627f851778d980e9ac830b8ddf925713857301dcce7cacc37d53852"},"schema_version":"1.0"},"canonical_sha256":"fc19b8c144fc2f4e81e5e284b1b8655d2ef8eee2924517a5945efa386bebb21a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:19:28.001529Z","signature_b64":"G9Y7WNomkQc6hZYqSPeG9eEnllizoG2arNrVy1AaT0qb0r3FnS0Ip0E5ljQ3BVQcNVxDOZW4OWkM/sRqz8MmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc19b8c144fc2f4e81e5e284b1b8655d2ef8eee2924517a5945efa386bebb21a","last_reissued_at":"2026-07-05T03:19:28.001121Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:19:28.001121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.00276","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:19:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"feZZCD7JRq8Te21BHdqOps4EnVyPtrwFfOeBJOg1wjz8iDzdzdX7dqcVTYMhl+pa5mGB7p3Oom0ITQMnYOxyAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:35:01.509202Z"},"content_sha256":"032e31399dda0d1441196923fe2f77a9f3a6f406770116b26226ee1628a52ff6","schema_version":"1.0","event_id":"sha256:032e31399dda0d1441196923fe2f77a9f3a6f406770116b26226ee1628a52ff6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:7QM3RQKE7QXU5APF4KCLDODFLU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TyXe: Pyro-based Bayesian neural nets for Pytorch","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hippolyt Ritter, Theofanis Karaletsos","submitted_at":"2021-10-01T09:04:26Z","abstract_excerpt":"We introduce TyXe, a Bayesian neural network library built on top of Pytorch and Pyro. Our leading design principle is to cleanly separate architecture, prior, inference and likelihood specification, allowing for a flexible workflow where users can quickly iterate over combinations of these components. In contrast to existing packages TyXe does not implement any layer classes, and instead relies on architectures defined in generic Pytorch code. TyXe then provides modular choices for canonical priors, variational guides, inference techniques, and layer selections for a Bayesian treatment of the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.00276","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/2110.00276/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":"2026-07-05T03:19:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xC7vdu0KyiH17awadOoUyNTL2yOGN5BEX7lmlhLd7v8gDg24ouu+hiXMAa40UsWV6Jxvr6dtJst6I7jZgRdUAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:35:01.510271Z"},"content_sha256":"02ca1d2a90db59121f8b1732553417eba26f0a82a0a487943d36bba1025ac6c6","schema_version":"1.0","event_id":"sha256:02ca1d2a90db59121f8b1732553417eba26f0a82a0a487943d36bba1025ac6c6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7QM3RQKE7QXU5APF4KCLDODFLU/bundle.json","state_url":"https://pith.science/pith/7QM3RQKE7QXU5APF4KCLDODFLU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7QM3RQKE7QXU5APF4KCLDODFLU/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":"2026-08-06T00:35:01Z","links":{"resolver":"https://pith.science/pith/7QM3RQKE7QXU5APF4KCLDODFLU","bundle":"https://pith.science/pith/7QM3RQKE7QXU5APF4KCLDODFLU/bundle.json","state":"https://pith.science/pith/7QM3RQKE7QXU5APF4KCLDODFLU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7QM3RQKE7QXU5APF4KCLDODFLU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:7QM3RQKE7QXU5APF4KCLDODFLU","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":"aecce467e627f851778d980e9ac830b8ddf925713857301dcce7cacc37d53852","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-10-01T09:04:26Z","title_canon_sha256":"439869b7ac6121ca1c8e09741f857486a7bac79f1801062803c183ab7947fd8e"},"schema_version":"1.0","source":{"id":"2110.00276","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.00276","created_at":"2026-07-05T03:19:28Z"},{"alias_kind":"arxiv_version","alias_value":"2110.00276v1","created_at":"2026-07-05T03:19:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.00276","created_at":"2026-07-05T03:19:28Z"},{"alias_kind":"pith_short_12","alias_value":"7QM3RQKE7QXU","created_at":"2026-07-05T03:19:28Z"},{"alias_kind":"pith_short_16","alias_value":"7QM3RQKE7QXU5APF","created_at":"2026-07-05T03:19:28Z"},{"alias_kind":"pith_short_8","alias_value":"7QM3RQKE","created_at":"2026-07-05T03:19:28Z"}],"graph_snapshots":[{"event_id":"sha256:02ca1d2a90db59121f8b1732553417eba26f0a82a0a487943d36bba1025ac6c6","target":"graph","created_at":"2026-07-05T03:19:28Z","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/2110.00276/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce TyXe, a Bayesian neural network library built on top of Pytorch and Pyro. Our leading design principle is to cleanly separate architecture, prior, inference and likelihood specification, allowing for a flexible workflow where users can quickly iterate over combinations of these components. In contrast to existing packages TyXe does not implement any layer classes, and instead relies on architectures defined in generic Pytorch code. TyXe then provides modular choices for canonical priors, variational guides, inference techniques, and layer selections for a Bayesian treatment of the","authors_text":"Hippolyt Ritter, Theofanis Karaletsos","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-10-01T09:04:26Z","title":"TyXe: Pyro-based Bayesian neural nets for Pytorch"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.00276","kind":"arxiv","version":1},"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":"sha256:032e31399dda0d1441196923fe2f77a9f3a6f406770116b26226ee1628a52ff6","target":"record","created_at":"2026-07-05T03:19:28Z","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":"aecce467e627f851778d980e9ac830b8ddf925713857301dcce7cacc37d53852","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-10-01T09:04:26Z","title_canon_sha256":"439869b7ac6121ca1c8e09741f857486a7bac79f1801062803c183ab7947fd8e"},"schema_version":"1.0","source":{"id":"2110.00276","kind":"arxiv","version":1}},"canonical_sha256":"fc19b8c144fc2f4e81e5e284b1b8655d2ef8eee2924517a5945efa386bebb21a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc19b8c144fc2f4e81e5e284b1b8655d2ef8eee2924517a5945efa386bebb21a","first_computed_at":"2026-07-05T03:19:28.001121Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:19:28.001121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G9Y7WNomkQc6hZYqSPeG9eEnllizoG2arNrVy1AaT0qb0r3FnS0Ip0E5ljQ3BVQcNVxDOZW4OWkM/sRqz8MmCw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:19:28.001529Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.00276","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:032e31399dda0d1441196923fe2f77a9f3a6f406770116b26226ee1628a52ff6","sha256:02ca1d2a90db59121f8b1732553417eba26f0a82a0a487943d36bba1025ac6c6"],"state_sha256":"3c6a4ae199e36c1c4205d97cf0171151b598d940bd8d372aa81d20afa45f339e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tlBo+sUAItxI/8i2skw2HvGFEg01tjYfPkIzWumQAwcR//Vo4avwDdwQx5FQkdy12TZQ7di9zvBi51aG/yhUDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T00:35:01.517270Z","bundle_sha256":"1ddc093f67f3c6621b96d667bfd9947232567112bf03aa7a398b45213d3749e2"}}