{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:XJWOWFPUVXICA7V2UVQIUXW7ZV","short_pith_number":"pith:XJWOWFPU","canonical_record":{"source":{"id":"1201.4339","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.NC","submitted_at":"2012-01-20T17:04:18Z","cross_cats_sorted":[],"title_canon_sha256":"7ae3938c29de886b240c9241c85d4742593b28512cc957fadf28ba48e35311bb","abstract_canon_sha256":"65ed30af268f1866ac999fb704914ab2db78b6bed642756fc7a2a2ecac95c047"},"schema_version":"1.0"},"canonical_sha256":"ba6ceb15f4add0207ebaa5608a5edfcd41c38380f6a357a88ada70415f3a42b7","source":{"kind":"arxiv","id":"1201.4339","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1201.4339","created_at":"2026-05-18T03:51:35Z"},{"alias_kind":"arxiv_version","alias_value":"1201.4339v1","created_at":"2026-05-18T03:51:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1201.4339","created_at":"2026-05-18T03:51:35Z"},{"alias_kind":"pith_short_12","alias_value":"XJWOWFPUVXIC","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_16","alias_value":"XJWOWFPUVXICA7V2","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_8","alias_value":"XJWOWFPU","created_at":"2026-05-18T12:27:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:XJWOWFPUVXICA7V2UVQIUXW7ZV","target":"record","payload":{"canonical_record":{"source":{"id":"1201.4339","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.NC","submitted_at":"2012-01-20T17:04:18Z","cross_cats_sorted":[],"title_canon_sha256":"7ae3938c29de886b240c9241c85d4742593b28512cc957fadf28ba48e35311bb","abstract_canon_sha256":"65ed30af268f1866ac999fb704914ab2db78b6bed642756fc7a2a2ecac95c047"},"schema_version":"1.0"},"canonical_sha256":"ba6ceb15f4add0207ebaa5608a5edfcd41c38380f6a357a88ada70415f3a42b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:51:35.549940Z","signature_b64":"5/Q+nV0Eg81VhJK9JehIjUfnG64sweBO3LSH+dAQtPIi+2ecdGcNx53aIS6+Ejudcc0e9o4kK7EhlERI4b1CAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba6ceb15f4add0207ebaa5608a5edfcd41c38380f6a357a88ada70415f3a42b7","last_reissued_at":"2026-05-18T03:51:35.549278Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:51:35.549278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1201.4339","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":"2026-05-18T03:51:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qjGvOMrhtZdJ71Ttcf2eY8Vrx9/YqBCOAmdQ4GiiFwaOcslnOA5XBMd5Nqf2TXjTUE93P4LlNN1riw1kgHGaAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T05:47:54.695256Z"},"content_sha256":"578c6238b12cd1303a9a7bb6c39ed6bd8f8faec11e4734a70a4c7ea4863f4fde","schema_version":"1.0","event_id":"sha256:578c6238b12cd1303a9a7bb6c39ed6bd8f8faec11e4734a70a4c7ea4863f4fde"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:XJWOWFPUVXICA7V2UVQIUXW7ZV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recognizing recurrent neural networks (rRNN): Bayesian inference for recurrent neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.NC","authors_text":"Sebastian Bitzer, Stefan J. Kiebel","submitted_at":"2012-01-20T17:04:18Z","abstract_excerpt":"Recurrent neural networks (RNNs) are widely used in computational neuroscience and machine learning applications. In an RNN, each neuron computes its output as a nonlinear function of its integrated input. While the importance of RNNs, especially as models of brain processing, is undisputed, it is also widely acknowledged that the computations in standard RNN models may be an over-simplification of what real neuronal networks compute. Here, we suggest that the RNN approach may be made both neurobiologically more plausible and computationally more powerful by its fusion with Bayesian inference "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1201.4339","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":""},"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":"2026-05-18T03:51:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tEKDw+X/A+rn8bqO6yISO6GatVQlPaS/UtXzmmDaIcHXu/D0NPbfiQQ7YF4deSCY9IWtEYsKAKi6+LdzBsCcCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T05:47:54.695624Z"},"content_sha256":"d3c8fe1dc397aadc68a552dea5fe0538af33dac2b8879210af254b91c6acd64d","schema_version":"1.0","event_id":"sha256:d3c8fe1dc397aadc68a552dea5fe0538af33dac2b8879210af254b91c6acd64d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XJWOWFPUVXICA7V2UVQIUXW7ZV/bundle.json","state_url":"https://pith.science/pith/XJWOWFPUVXICA7V2UVQIUXW7ZV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XJWOWFPUVXICA7V2UVQIUXW7ZV/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":"2026-06-25T05:47:54Z","links":{"resolver":"https://pith.science/pith/XJWOWFPUVXICA7V2UVQIUXW7ZV","bundle":"https://pith.science/pith/XJWOWFPUVXICA7V2UVQIUXW7ZV/bundle.json","state":"https://pith.science/pith/XJWOWFPUVXICA7V2UVQIUXW7ZV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XJWOWFPUVXICA7V2UVQIUXW7ZV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:XJWOWFPUVXICA7V2UVQIUXW7ZV","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":"65ed30af268f1866ac999fb704914ab2db78b6bed642756fc7a2a2ecac95c047","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.NC","submitted_at":"2012-01-20T17:04:18Z","title_canon_sha256":"7ae3938c29de886b240c9241c85d4742593b28512cc957fadf28ba48e35311bb"},"schema_version":"1.0","source":{"id":"1201.4339","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1201.4339","created_at":"2026-05-18T03:51:35Z"},{"alias_kind":"arxiv_version","alias_value":"1201.4339v1","created_at":"2026-05-18T03:51:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1201.4339","created_at":"2026-05-18T03:51:35Z"},{"alias_kind":"pith_short_12","alias_value":"XJWOWFPUVXIC","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_16","alias_value":"XJWOWFPUVXICA7V2","created_at":"2026-05-18T12:27:27Z"},{"alias_kind":"pith_short_8","alias_value":"XJWOWFPU","created_at":"2026-05-18T12:27:27Z"}],"graph_snapshots":[{"event_id":"sha256:d3c8fe1dc397aadc68a552dea5fe0538af33dac2b8879210af254b91c6acd64d","target":"graph","created_at":"2026-05-18T03:51:35Z","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"},"paper":{"abstract_excerpt":"Recurrent neural networks (RNNs) are widely used in computational neuroscience and machine learning applications. In an RNN, each neuron computes its output as a nonlinear function of its integrated input. While the importance of RNNs, especially as models of brain processing, is undisputed, it is also widely acknowledged that the computations in standard RNN models may be an over-simplification of what real neuronal networks compute. Here, we suggest that the RNN approach may be made both neurobiologically more plausible and computationally more powerful by its fusion with Bayesian inference ","authors_text":"Sebastian Bitzer, Stefan J. Kiebel","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.NC","submitted_at":"2012-01-20T17:04:18Z","title":"Recognizing recurrent neural networks (rRNN): Bayesian inference for recurrent neural networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1201.4339","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":"sha256:578c6238b12cd1303a9a7bb6c39ed6bd8f8faec11e4734a70a4c7ea4863f4fde","target":"record","created_at":"2026-05-18T03:51:35Z","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":"65ed30af268f1866ac999fb704914ab2db78b6bed642756fc7a2a2ecac95c047","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.NC","submitted_at":"2012-01-20T17:04:18Z","title_canon_sha256":"7ae3938c29de886b240c9241c85d4742593b28512cc957fadf28ba48e35311bb"},"schema_version":"1.0","source":{"id":"1201.4339","kind":"arxiv","version":1}},"canonical_sha256":"ba6ceb15f4add0207ebaa5608a5edfcd41c38380f6a357a88ada70415f3a42b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba6ceb15f4add0207ebaa5608a5edfcd41c38380f6a357a88ada70415f3a42b7","first_computed_at":"2026-05-18T03:51:35.549278Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:51:35.549278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5/Q+nV0Eg81VhJK9JehIjUfnG64sweBO3LSH+dAQtPIi+2ecdGcNx53aIS6+Ejudcc0e9o4kK7EhlERI4b1CAg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:51:35.549940Z","signed_message":"canonical_sha256_bytes"},"source_id":"1201.4339","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:578c6238b12cd1303a9a7bb6c39ed6bd8f8faec11e4734a70a4c7ea4863f4fde","sha256:d3c8fe1dc397aadc68a552dea5fe0538af33dac2b8879210af254b91c6acd64d"],"state_sha256":"89cff404eba55d97087c32a5a475b4c8e20c0017a6680a507d221ec7eebf495e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pYSMzXq+ucd+1X+3KoVZxgX5giUhK1mYo7LK8tcBiO1Okh2oWsP7dV6DEPCl0QASgbujz0wEPKLZNX9bAsE6CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-25T05:47:54.697601Z","bundle_sha256":"a595098bc4459e2c2c5feeb807de8462ccd6b1ff03734d9ccd97399a968ecaf2"}}