{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:K24MLFHKUHHSS642KBB2U6QPCR","short_pith_number":"pith:K24MLFHK","canonical_record":{"source":{"id":"2501.18665","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T15:44:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fec87e5d2bf346d5bf4025662135e674abb3312c6dcc52deac5a1e4fc4489c50","abstract_canon_sha256":"d7d51a853c58893bd1fc360fc9e081728476c9b94ef5bd5eb082f55e5d2627e6"},"schema_version":"1.0"},"canonical_sha256":"56b8c594eaa1cf297b9a5043aa7a0f147cf0fb300e6b3aff7c3a67379e5c9817","source":{"kind":"arxiv","id":"2501.18665","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18665","created_at":"2026-07-05T11:39:47Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18665v2","created_at":"2026-07-05T11:39:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18665","created_at":"2026-07-05T11:39:47Z"},{"alias_kind":"pith_short_12","alias_value":"K24MLFHKUHHS","created_at":"2026-07-05T11:39:47Z"},{"alias_kind":"pith_short_16","alias_value":"K24MLFHKUHHSS642","created_at":"2026-07-05T11:39:47Z"},{"alias_kind":"pith_short_8","alias_value":"K24MLFHK","created_at":"2026-07-05T11:39:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:K24MLFHKUHHSS642KBB2U6QPCR","target":"record","payload":{"canonical_record":{"source":{"id":"2501.18665","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T15:44:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fec87e5d2bf346d5bf4025662135e674abb3312c6dcc52deac5a1e4fc4489c50","abstract_canon_sha256":"d7d51a853c58893bd1fc360fc9e081728476c9b94ef5bd5eb082f55e5d2627e6"},"schema_version":"1.0"},"canonical_sha256":"56b8c594eaa1cf297b9a5043aa7a0f147cf0fb300e6b3aff7c3a67379e5c9817","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:47.767381Z","signature_b64":"THLFaYt0XIbp5BmMrI3O5Z4WBeoSUdLeMRCh/O3Pgp0rkYzTX+0PJLAboNZS5Ch6Hn71K0q4WncnlGE3DeQSAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56b8c594eaa1cf297b9a5043aa7a0f147cf0fb300e6b3aff7c3a67379e5c9817","last_reissued_at":"2026-07-05T11:39:47.766849Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:47.766849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.18665","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":"2026-07-05T11:39:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kUdktIWKHIrNpxXsBAqfFL4swzqTkflpm5MSvoyXaW5hu4YgcsAhJ6EcV2V44NrOfGub03j5X/9mEVpjczVEAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T19:23:57.217825Z"},"content_sha256":"aa7a13cab549862ac9aad994e81cad6d87cfad3c1ab6a0bfdc410037586f06b8","schema_version":"1.0","event_id":"sha256:aa7a13cab549862ac9aad994e81cad6d87cfad3c1ab6a0bfdc410037586f06b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:K24MLFHKUHHSS642KBB2U6QPCR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BARNN: A Bayesian Autoregressive and Recurrent Neural Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dario Coscia, Gianluigi Rozza, Max Welling, Nicola Demo","submitted_at":"2025-01-30T15:44:04Z","abstract_excerpt":"Autoregressive and recurrent networks have achieved remarkable progress across various fields, from weather forecasting to molecular generation and Large Language Models. Despite their strong predictive capabilities, these models lack a rigorous framework for addressing uncertainty, which is key in scientific applications such as PDE solving, molecular generation and Machine Learning Force Fields. To address this shortcoming we present BARNN: a variational Bayesian Autoregressive and Recurrent Neural Network. BARNNs aim to provide a principled way to turn any autoregressive or recurrent model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18665","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/2501.18665/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":"2026-07-05T11:39:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uyp+ugOeduq8ijiqIrQ8UlWU+3nb4GjHmWaSd1VdMC6NvTsVG/d0EYUu4ZUsMUa+uTdRMCII3mc9GjGyQu1qAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T19:23:57.218678Z"},"content_sha256":"fe136f9f33a0ddace462834da1646cbe9a7f361838daf08804d2a83f2736ba4a","schema_version":"1.0","event_id":"sha256:fe136f9f33a0ddace462834da1646cbe9a7f361838daf08804d2a83f2736ba4a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K24MLFHKUHHSS642KBB2U6QPCR/bundle.json","state_url":"https://pith.science/pith/K24MLFHKUHHSS642KBB2U6QPCR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K24MLFHKUHHSS642KBB2U6QPCR/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":"2026-08-10T19:23:57Z","links":{"resolver":"https://pith.science/pith/K24MLFHKUHHSS642KBB2U6QPCR","bundle":"https://pith.science/pith/K24MLFHKUHHSS642KBB2U6QPCR/bundle.json","state":"https://pith.science/pith/K24MLFHKUHHSS642KBB2U6QPCR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K24MLFHKUHHSS642KBB2U6QPCR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K24MLFHKUHHSS642KBB2U6QPCR","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":"d7d51a853c58893bd1fc360fc9e081728476c9b94ef5bd5eb082f55e5d2627e6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T15:44:04Z","title_canon_sha256":"fec87e5d2bf346d5bf4025662135e674abb3312c6dcc52deac5a1e4fc4489c50"},"schema_version":"1.0","source":{"id":"2501.18665","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18665","created_at":"2026-07-05T11:39:47Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18665v2","created_at":"2026-07-05T11:39:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18665","created_at":"2026-07-05T11:39:47Z"},{"alias_kind":"pith_short_12","alias_value":"K24MLFHKUHHS","created_at":"2026-07-05T11:39:47Z"},{"alias_kind":"pith_short_16","alias_value":"K24MLFHKUHHSS642","created_at":"2026-07-05T11:39:47Z"},{"alias_kind":"pith_short_8","alias_value":"K24MLFHK","created_at":"2026-07-05T11:39:47Z"}],"graph_snapshots":[{"event_id":"sha256:fe136f9f33a0ddace462834da1646cbe9a7f361838daf08804d2a83f2736ba4a","target":"graph","created_at":"2026-07-05T11:39:47Z","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/2501.18665/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autoregressive and recurrent networks have achieved remarkable progress across various fields, from weather forecasting to molecular generation and Large Language Models. Despite their strong predictive capabilities, these models lack a rigorous framework for addressing uncertainty, which is key in scientific applications such as PDE solving, molecular generation and Machine Learning Force Fields. To address this shortcoming we present BARNN: a variational Bayesian Autoregressive and Recurrent Neural Network. BARNNs aim to provide a principled way to turn any autoregressive or recurrent model ","authors_text":"Dario Coscia, Gianluigi Rozza, Max Welling, Nicola Demo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T15:44:04Z","title":"BARNN: A Bayesian Autoregressive and Recurrent Neural Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18665","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:aa7a13cab549862ac9aad994e81cad6d87cfad3c1ab6a0bfdc410037586f06b8","target":"record","created_at":"2026-07-05T11:39:47Z","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":"d7d51a853c58893bd1fc360fc9e081728476c9b94ef5bd5eb082f55e5d2627e6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T15:44:04Z","title_canon_sha256":"fec87e5d2bf346d5bf4025662135e674abb3312c6dcc52deac5a1e4fc4489c50"},"schema_version":"1.0","source":{"id":"2501.18665","kind":"arxiv","version":2}},"canonical_sha256":"56b8c594eaa1cf297b9a5043aa7a0f147cf0fb300e6b3aff7c3a67379e5c9817","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56b8c594eaa1cf297b9a5043aa7a0f147cf0fb300e6b3aff7c3a67379e5c9817","first_computed_at":"2026-07-05T11:39:47.766849Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:47.766849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"THLFaYt0XIbp5BmMrI3O5Z4WBeoSUdLeMRCh/O3Pgp0rkYzTX+0PJLAboNZS5Ch6Hn71K0q4WncnlGE3DeQSAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:47.767381Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.18665","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa7a13cab549862ac9aad994e81cad6d87cfad3c1ab6a0bfdc410037586f06b8","sha256:fe136f9f33a0ddace462834da1646cbe9a7f361838daf08804d2a83f2736ba4a"],"state_sha256":"558373eef0513470d15f9f7fae69eca0152dd1b333a76dabccfad21347e1d996"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IZ+emIUmOVgpX1fpOlUXS8lWBB9DreRyueUOey47PZHvpUrMkl+lN7/cqnWX/CWTBCxkrD5wGeDYcXVongm0DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T19:23:57.223314Z","bundle_sha256":"e2a3a84aff80ad9407d8ee843b439c6ad0e3ecba408660436d955dd2a39d9218"}}