{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:BYLPEBF3IFQCHPUTUVHCWBLBUV","short_pith_number":"pith:BYLPEBF3","canonical_record":{"source":{"id":"1901.08817","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-25T10:28:44Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1987a4c74c92353477484b08cb38b7e6c19c0cafc116ab4e7964e98a899baceb","abstract_canon_sha256":"a08deebb59940a1e9d907259b95ffb88aae7c3a9962a25d5f58e484b24ebfcc6"},"schema_version":"1.0"},"canonical_sha256":"0e16f204bb416023be93a54e2b0561a571b4ee8f42cc750face2e2550f821e46","source":{"kind":"arxiv","id":"1901.08817","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08817","created_at":"2026-05-17T23:46:52Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08817v2","created_at":"2026-05-17T23:46:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08817","created_at":"2026-05-17T23:46:52Z"},{"alias_kind":"pith_short_12","alias_value":"BYLPEBF3IFQC","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"BYLPEBF3IFQCHPUT","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"BYLPEBF3","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:BYLPEBF3IFQCHPUTUVHCWBLBUV","target":"record","payload":{"canonical_record":{"source":{"id":"1901.08817","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-25T10:28:44Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1987a4c74c92353477484b08cb38b7e6c19c0cafc116ab4e7964e98a899baceb","abstract_canon_sha256":"a08deebb59940a1e9d907259b95ffb88aae7c3a9962a25d5f58e484b24ebfcc6"},"schema_version":"1.0"},"canonical_sha256":"0e16f204bb416023be93a54e2b0561a571b4ee8f42cc750face2e2550f821e46","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:52.994032Z","signature_b64":"ZYfacA1u0utGWbzkzzgK6r0td4QQg0Xr0hnJhqG1GC0AxTPsBVC26+KT5bgoDY+RPN5BGW9rF9qRC5tXWE/uBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e16f204bb416023be93a54e2b0561a571b4ee8f42cc750face2e2550f821e46","last_reissued_at":"2026-05-17T23:46:52.993556Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:52.993556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.08817","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":"2026-05-17T23:46:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pKC/aQ1eqhs9aX6al9/fE3N4s8H6WHUIhr69/jbdj/VlJzcljnPr3BtregQujmKG5la1SqOp2ydNLYIF+rTdBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T16:25:37.557484Z"},"content_sha256":"54e6c5b41a45111a2ef1e746502f9bffcf018fd9f0b146ead92ba1c11b17ddc1","schema_version":"1.0","event_id":"sha256:54e6c5b41a45111a2ef1e746502f9bffcf018fd9f0b146ead92ba1c11b17ddc1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:BYLPEBF3IFQCHPUTUVHCWBLBUV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"State-Regularized Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cheng Wang, Mathias Niepert","submitted_at":"2019-01-25T10:28:44Z","abstract_excerpt":"Recurrent neural networks are a widely used class of neural architectures. They have, however, two shortcomings. First, it is difficult to understand what exactly they learn. Second, they tend to work poorly on sequences requiring long-term memorization, despite having this capacity in principle. We aim to address both shortcomings with a class of recurrent networks that use a stochastic state transition mechanism between cell applications. This mechanism, which we term state-regularization, makes RNNs transition between a finite set of learnable states. We evaluate state-regularized RNNs on ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08817","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":""},"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":"2026-05-17T23:46:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ygdDnbIdzZKAxZsM63FnVXq7OuiTWZP1zxB8ZKhVUmEfs0Xq6DaNTEMGtW0Ef1xVPENwF3L3HU/0lcdIEgIDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T16:25:37.558379Z"},"content_sha256":"b958d03fc85b0e4a0850aaca596841f6d5a1c8db698aee59f7ac80d0d47ed956","schema_version":"1.0","event_id":"sha256:b958d03fc85b0e4a0850aaca596841f6d5a1c8db698aee59f7ac80d0d47ed956"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BYLPEBF3IFQCHPUTUVHCWBLBUV/bundle.json","state_url":"https://pith.science/pith/BYLPEBF3IFQCHPUTUVHCWBLBUV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BYLPEBF3IFQCHPUTUVHCWBLBUV/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":"2026-05-31T16:25:37Z","links":{"resolver":"https://pith.science/pith/BYLPEBF3IFQCHPUTUVHCWBLBUV","bundle":"https://pith.science/pith/BYLPEBF3IFQCHPUTUVHCWBLBUV/bundle.json","state":"https://pith.science/pith/BYLPEBF3IFQCHPUTUVHCWBLBUV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BYLPEBF3IFQCHPUTUVHCWBLBUV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:BYLPEBF3IFQCHPUTUVHCWBLBUV","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":"a08deebb59940a1e9d907259b95ffb88aae7c3a9962a25d5f58e484b24ebfcc6","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-25T10:28:44Z","title_canon_sha256":"1987a4c74c92353477484b08cb38b7e6c19c0cafc116ab4e7964e98a899baceb"},"schema_version":"1.0","source":{"id":"1901.08817","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08817","created_at":"2026-05-17T23:46:52Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08817v2","created_at":"2026-05-17T23:46:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08817","created_at":"2026-05-17T23:46:52Z"},{"alias_kind":"pith_short_12","alias_value":"BYLPEBF3IFQC","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"BYLPEBF3IFQCHPUT","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"BYLPEBF3","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:b958d03fc85b0e4a0850aaca596841f6d5a1c8db698aee59f7ac80d0d47ed956","target":"graph","created_at":"2026-05-17T23:46:52Z","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 are a widely used class of neural architectures. They have, however, two shortcomings. First, it is difficult to understand what exactly they learn. Second, they tend to work poorly on sequences requiring long-term memorization, despite having this capacity in principle. We aim to address both shortcomings with a class of recurrent networks that use a stochastic state transition mechanism between cell applications. This mechanism, which we term state-regularization, makes RNNs transition between a finite set of learnable states. We evaluate state-regularized RNNs on (","authors_text":"Cheng Wang, Mathias Niepert","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-25T10:28:44Z","title":"State-Regularized Recurrent Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08817","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":"sha256:54e6c5b41a45111a2ef1e746502f9bffcf018fd9f0b146ead92ba1c11b17ddc1","target":"record","created_at":"2026-05-17T23:46:52Z","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":"a08deebb59940a1e9d907259b95ffb88aae7c3a9962a25d5f58e484b24ebfcc6","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-25T10:28:44Z","title_canon_sha256":"1987a4c74c92353477484b08cb38b7e6c19c0cafc116ab4e7964e98a899baceb"},"schema_version":"1.0","source":{"id":"1901.08817","kind":"arxiv","version":2}},"canonical_sha256":"0e16f204bb416023be93a54e2b0561a571b4ee8f42cc750face2e2550f821e46","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e16f204bb416023be93a54e2b0561a571b4ee8f42cc750face2e2550f821e46","first_computed_at":"2026-05-17T23:46:52.993556Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:52.993556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZYfacA1u0utGWbzkzzgK6r0td4QQg0Xr0hnJhqG1GC0AxTPsBVC26+KT5bgoDY+RPN5BGW9rF9qRC5tXWE/uBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:52.994032Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.08817","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54e6c5b41a45111a2ef1e746502f9bffcf018fd9f0b146ead92ba1c11b17ddc1","sha256:b958d03fc85b0e4a0850aaca596841f6d5a1c8db698aee59f7ac80d0d47ed956"],"state_sha256":"4b67864c489e7b17db5f2bc0fa47a9f51d5b754f89aa678e515d479958259753"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LPgEz0cTPQZr8acBd6uwYcJ6hqskMMU/wyyWZYSOTYOfIPmS7N+Nl6dkCfaEAwtgQMjiqIdHFu0KkeiQlNezAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T16:25:37.562138Z","bundle_sha256":"2ee99750b7e304aca787974d59d4cc8e42c17348ab97bcb638b7420e2b9a49bc"}}