{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:4LI2YATE2O3BEZU5WSYLQTXT7M","short_pith_number":"pith:4LI2YATE","canonical_record":{"source":{"id":"1810.07411","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-10-17T07:36:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cb606a499f6dfe3e97c429cf4e26b5ebdd1e30a47e27569d4abbf46434ff6d96","abstract_canon_sha256":"7eda12a9c30125c793854b444594c9c922ca1f536ea82ff9dba82ca26b6622fb"},"schema_version":"1.0"},"canonical_sha256":"e2d1ac0264d3b612669db4b0b84ef3fb07ff82b385c772cb6446b22edc36112e","source":{"kind":"arxiv","id":"1810.07411","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.07411","created_at":"2026-07-04T23:53:10Z"},{"alias_kind":"arxiv_version","alias_value":"1810.07411v4","created_at":"2026-07-04T23:53:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.07411","created_at":"2026-07-04T23:53:10Z"},{"alias_kind":"pith_short_12","alias_value":"4LI2YATE2O3B","created_at":"2026-07-04T23:53:10Z"},{"alias_kind":"pith_short_16","alias_value":"4LI2YATE2O3BEZU5","created_at":"2026-07-04T23:53:10Z"},{"alias_kind":"pith_short_8","alias_value":"4LI2YATE","created_at":"2026-07-04T23:53:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:4LI2YATE2O3BEZU5WSYLQTXT7M","target":"record","payload":{"canonical_record":{"source":{"id":"1810.07411","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-10-17T07:36:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cb606a499f6dfe3e97c429cf4e26b5ebdd1e30a47e27569d4abbf46434ff6d96","abstract_canon_sha256":"7eda12a9c30125c793854b444594c9c922ca1f536ea82ff9dba82ca26b6622fb"},"schema_version":"1.0"},"canonical_sha256":"e2d1ac0264d3b612669db4b0b84ef3fb07ff82b385c772cb6446b22edc36112e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:53:10.488126Z","signature_b64":"e2oXxrbZiNOdR+6aEmUibKnr6KSjopMsZsfoW//JsrmKhIeTHrCkruSbKXBEwCyVqaemmNI0VrWntHfjgOFdBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2d1ac0264d3b612669db4b0b84ef3fb07ff82b385c772cb6446b22edc36112e","last_reissued_at":"2026-07-04T23:53:10.487592Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:53:10.487592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.07411","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:53:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Et5A1HXjIjbqNySQ41lLhA0bnsSVPOhUSoTARoUutZ6ewQuuoQUAHmq73chbbSoTFYg2hbhBmHx/D64jZJAVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T21:11:40.603422Z"},"content_sha256":"bea9d7fac03b0d9d40147b2694729a7b138350b127ca60a987f1a727befcfb4b","schema_version":"1.0","event_id":"sha256:bea9d7fac03b0d9d40147b2694729a7b138350b127ca60a987f1a727befcfb4b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:4LI2YATE2O3BEZU5WSYLQTXT7M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Continual Learning of Recurrent Neural Networks by Locally Aligning Distributed Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Alexander Ororbia, Ankur Mali, C. Lee Giles, Daniel Kifer","submitted_at":"2018-10-17T07:36:47Z","abstract_excerpt":"Temporal models based on recurrent neural networks have proven to be quite powerful in a wide variety of applications. However, training these models often relies on back-propagation through time, which entails unfolding the network over many time steps, making the process of conducting credit assignment considerably more challenging. Furthermore, the nature of back-propagation itself does not permit the use of non-differentiable activation functions and is inherently sequential, making parallelization of the underlying training process difficult. Here, we propose the Parallel Temporal Neural "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.07411","kind":"arxiv","version":4},"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/1810.07411/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":"2026-07-04T23:53:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ugVPkke8jZArbhs98W2rDwvy4WDA/cmLifsR4Uj9edW3K3H8qZ3ffsEsGgSeFDWcqreVkYborMqvKIq/xGKgAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T21:11:40.603808Z"},"content_sha256":"df1741305312fc6bb5f562a15c33c8519217c6e53141c336751b3ad41f998ede","schema_version":"1.0","event_id":"sha256:df1741305312fc6bb5f562a15c33c8519217c6e53141c336751b3ad41f998ede"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4LI2YATE2O3BEZU5WSYLQTXT7M/bundle.json","state_url":"https://pith.science/pith/4LI2YATE2O3BEZU5WSYLQTXT7M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4LI2YATE2O3BEZU5WSYLQTXT7M/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":"2026-08-05T21:11:40Z","links":{"resolver":"https://pith.science/pith/4LI2YATE2O3BEZU5WSYLQTXT7M","bundle":"https://pith.science/pith/4LI2YATE2O3BEZU5WSYLQTXT7M/bundle.json","state":"https://pith.science/pith/4LI2YATE2O3BEZU5WSYLQTXT7M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4LI2YATE2O3BEZU5WSYLQTXT7M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:4LI2YATE2O3BEZU5WSYLQTXT7M","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":"7eda12a9c30125c793854b444594c9c922ca1f536ea82ff9dba82ca26b6622fb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-10-17T07:36:47Z","title_canon_sha256":"cb606a499f6dfe3e97c429cf4e26b5ebdd1e30a47e27569d4abbf46434ff6d96"},"schema_version":"1.0","source":{"id":"1810.07411","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.07411","created_at":"2026-07-04T23:53:10Z"},{"alias_kind":"arxiv_version","alias_value":"1810.07411v4","created_at":"2026-07-04T23:53:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.07411","created_at":"2026-07-04T23:53:10Z"},{"alias_kind":"pith_short_12","alias_value":"4LI2YATE2O3B","created_at":"2026-07-04T23:53:10Z"},{"alias_kind":"pith_short_16","alias_value":"4LI2YATE2O3BEZU5","created_at":"2026-07-04T23:53:10Z"},{"alias_kind":"pith_short_8","alias_value":"4LI2YATE","created_at":"2026-07-04T23:53:10Z"}],"graph_snapshots":[{"event_id":"sha256:df1741305312fc6bb5f562a15c33c8519217c6e53141c336751b3ad41f998ede","target":"graph","created_at":"2026-07-04T23:53:10Z","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/1810.07411/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Temporal models based on recurrent neural networks have proven to be quite powerful in a wide variety of applications. However, training these models often relies on back-propagation through time, which entails unfolding the network over many time steps, making the process of conducting credit assignment considerably more challenging. Furthermore, the nature of back-propagation itself does not permit the use of non-differentiable activation functions and is inherently sequential, making parallelization of the underlying training process difficult. Here, we propose the Parallel Temporal Neural ","authors_text":"Alexander Ororbia, Ankur Mali, C. Lee Giles, Daniel Kifer","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-10-17T07:36:47Z","title":"Continual Learning of Recurrent Neural Networks by Locally Aligning Distributed Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.07411","kind":"arxiv","version":4},"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:bea9d7fac03b0d9d40147b2694729a7b138350b127ca60a987f1a727befcfb4b","target":"record","created_at":"2026-07-04T23:53:10Z","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":"7eda12a9c30125c793854b444594c9c922ca1f536ea82ff9dba82ca26b6622fb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-10-17T07:36:47Z","title_canon_sha256":"cb606a499f6dfe3e97c429cf4e26b5ebdd1e30a47e27569d4abbf46434ff6d96"},"schema_version":"1.0","source":{"id":"1810.07411","kind":"arxiv","version":4}},"canonical_sha256":"e2d1ac0264d3b612669db4b0b84ef3fb07ff82b385c772cb6446b22edc36112e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2d1ac0264d3b612669db4b0b84ef3fb07ff82b385c772cb6446b22edc36112e","first_computed_at":"2026-07-04T23:53:10.487592Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:53:10.487592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e2oXxrbZiNOdR+6aEmUibKnr6KSjopMsZsfoW//JsrmKhIeTHrCkruSbKXBEwCyVqaemmNI0VrWntHfjgOFdBA==","signature_status":"signed_v1","signed_at":"2026-07-04T23:53:10.488126Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.07411","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bea9d7fac03b0d9d40147b2694729a7b138350b127ca60a987f1a727befcfb4b","sha256:df1741305312fc6bb5f562a15c33c8519217c6e53141c336751b3ad41f998ede"],"state_sha256":"d60ba84a2f6d0c1c92acb4ee91ba3f8b067b72c9eb33f7cdb44947fe92d1c1ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NSvEJSvb9+Q1oV4H1L7Wu6UIBZPqWHUbGdd2Q/0lG3RPnJJp2koZe8Q0IJwHYZYiCnFVAfkL1ug5bFl05+LFDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T21:11:40.606350Z","bundle_sha256":"5a16a4d611c7d9c7350b1ffd189912be491d27068362f32194362ec3ac5c90f4"}}