{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WWWD5VZ6LGZV5PRPM64U655U56","short_pith_number":"pith:WWWD5VZ6","canonical_record":{"source":{"id":"2103.05487","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-09T15:19:59Z","cross_cats_sorted":["math.DS","stat.ML"],"title_canon_sha256":"9bcc876c61ce36b47c2acab3b41231f85e3191348fc7cfa4a3b75f0020122ab8","abstract_canon_sha256":"7a628fc62f65be94d2a816113c707c557e8ed563622837c4fbf72e82e872aa9a"},"schema_version":"1.0"},"canonical_sha256":"b5ac3ed73e59b35ebe2f67b94f77b4ef80fe5caefa32c6e1a54f05f8558327b9","source":{"kind":"arxiv","id":"2103.05487","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.05487","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"arxiv_version","alias_value":"2103.05487v2","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.05487","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"pith_short_12","alias_value":"WWWD5VZ6LGZV","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"pith_short_16","alias_value":"WWWD5VZ6LGZV5PRP","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"pith_short_8","alias_value":"WWWD5VZ6","created_at":"2026-07-05T03:06:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WWWD5VZ6LGZV5PRPM64U655U56","target":"record","payload":{"canonical_record":{"source":{"id":"2103.05487","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-09T15:19:59Z","cross_cats_sorted":["math.DS","stat.ML"],"title_canon_sha256":"9bcc876c61ce36b47c2acab3b41231f85e3191348fc7cfa4a3b75f0020122ab8","abstract_canon_sha256":"7a628fc62f65be94d2a816113c707c557e8ed563622837c4fbf72e82e872aa9a"},"schema_version":"1.0"},"canonical_sha256":"b5ac3ed73e59b35ebe2f67b94f77b4ef80fe5caefa32c6e1a54f05f8558327b9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:46.054120Z","signature_b64":"pzplRUjQQ+luq+dtY0UlNHEm3xnyvqclzm6OGjy81JuafAexKKXFCj8uJ75oSgY6q+DU/d2E0moKMfddZtafBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5ac3ed73e59b35ebe2f67b94f77b4ef80fe5caefa32c6e1a54f05f8558327b9","last_reissued_at":"2026-07-05T03:06:46.053736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:46.053736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.05487","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":"2026-07-05T03:06:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LmaH4z5PC5cLY4DCOnDAOuEbyejMM+FMXHWo2EcYpSBm+8EpuRpOYSMpjtKdVA92egVcgjEb4giiRI+bKr7ZBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:12:52.954174Z"},"content_sha256":"20edf873544626ee4558d5f057a25d937a31da7092763103056621359a643e81","schema_version":"1.0","event_id":"sha256:20edf873544626ee4558d5f057a25d937a31da7092763103056621359a643e81"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WWWD5VZ6LGZV5PRPM64U655U56","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UnICORNN: A recurrent model for learning very long time dependencies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Siddhartha Mishra, T. Konstantin Rusch","submitted_at":"2021-03-09T15:19:59Z","abstract_excerpt":"The design of recurrent neural networks (RNNs) to accurately process sequential inputs with long-time dependencies is very challenging on account of the exploding and vanishing gradient problem. To overcome this, we propose a novel RNN architecture which is based on a structure preserving discretization of a Hamiltonian system of second-order ordinary differential equations that models networks of oscillators. The resulting RNN is fast, invertible (in time), memory efficient and we derive rigorous bounds on the hidden state gradients to prove the mitigation of the exploding and vanishing gradi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.05487","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/2103.05487/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":"2026-07-05T03:06:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k6CQyGN3hQ5uY/aNNSIHGg/5Us9dKETBUL02Tq8JbfutA162A9fcFEzcl8Imm+fSmRRXmko/CfKesLrMKGQbAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:12:52.954698Z"},"content_sha256":"5c074da1b2e0b0a51c72d0bde87c0ae590c9d122466b3038ee4b1c67c48670c0","schema_version":"1.0","event_id":"sha256:5c074da1b2e0b0a51c72d0bde87c0ae590c9d122466b3038ee4b1c67c48670c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WWWD5VZ6LGZV5PRPM64U655U56/bundle.json","state_url":"https://pith.science/pith/WWWD5VZ6LGZV5PRPM64U655U56/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WWWD5VZ6LGZV5PRPM64U655U56/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":"2026-08-05T07:12:52Z","links":{"resolver":"https://pith.science/pith/WWWD5VZ6LGZV5PRPM64U655U56","bundle":"https://pith.science/pith/WWWD5VZ6LGZV5PRPM64U655U56/bundle.json","state":"https://pith.science/pith/WWWD5VZ6LGZV5PRPM64U655U56/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WWWD5VZ6LGZV5PRPM64U655U56/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WWWD5VZ6LGZV5PRPM64U655U56","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":"7a628fc62f65be94d2a816113c707c557e8ed563622837c4fbf72e82e872aa9a","cross_cats_sorted":["math.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-09T15:19:59Z","title_canon_sha256":"9bcc876c61ce36b47c2acab3b41231f85e3191348fc7cfa4a3b75f0020122ab8"},"schema_version":"1.0","source":{"id":"2103.05487","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.05487","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"arxiv_version","alias_value":"2103.05487v2","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.05487","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"pith_short_12","alias_value":"WWWD5VZ6LGZV","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"pith_short_16","alias_value":"WWWD5VZ6LGZV5PRP","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"pith_short_8","alias_value":"WWWD5VZ6","created_at":"2026-07-05T03:06:46Z"}],"graph_snapshots":[{"event_id":"sha256:5c074da1b2e0b0a51c72d0bde87c0ae590c9d122466b3038ee4b1c67c48670c0","target":"graph","created_at":"2026-07-05T03:06:46Z","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/2103.05487/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The design of recurrent neural networks (RNNs) to accurately process sequential inputs with long-time dependencies is very challenging on account of the exploding and vanishing gradient problem. To overcome this, we propose a novel RNN architecture which is based on a structure preserving discretization of a Hamiltonian system of second-order ordinary differential equations that models networks of oscillators. The resulting RNN is fast, invertible (in time), memory efficient and we derive rigorous bounds on the hidden state gradients to prove the mitigation of the exploding and vanishing gradi","authors_text":"Siddhartha Mishra, T. Konstantin Rusch","cross_cats":["math.DS","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-09T15:19:59Z","title":"UnICORNN: A recurrent model for learning very long time dependencies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.05487","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":"sha256:20edf873544626ee4558d5f057a25d937a31da7092763103056621359a643e81","target":"record","created_at":"2026-07-05T03:06:46Z","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":"7a628fc62f65be94d2a816113c707c557e8ed563622837c4fbf72e82e872aa9a","cross_cats_sorted":["math.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-09T15:19:59Z","title_canon_sha256":"9bcc876c61ce36b47c2acab3b41231f85e3191348fc7cfa4a3b75f0020122ab8"},"schema_version":"1.0","source":{"id":"2103.05487","kind":"arxiv","version":2}},"canonical_sha256":"b5ac3ed73e59b35ebe2f67b94f77b4ef80fe5caefa32c6e1a54f05f8558327b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5ac3ed73e59b35ebe2f67b94f77b4ef80fe5caefa32c6e1a54f05f8558327b9","first_computed_at":"2026-07-05T03:06:46.053736Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:06:46.053736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pzplRUjQQ+luq+dtY0UlNHEm3xnyvqclzm6OGjy81JuafAexKKXFCj8uJ75oSgY6q+DU/d2E0moKMfddZtafBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:06:46.054120Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.05487","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20edf873544626ee4558d5f057a25d937a31da7092763103056621359a643e81","sha256:5c074da1b2e0b0a51c72d0bde87c0ae590c9d122466b3038ee4b1c67c48670c0"],"state_sha256":"1131224d93cbb492de887d0bd308c426a501fb0fad5e38a439e9b0874149bc8f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/wY6mY558Q313bs6i8OH+aOw3WUympARBXH46maOqgRF79iZ8jQtOeN80dvKK7RIqo8PYv4JFbKcsG9bqqZLAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T07:12:52.957950Z","bundle_sha256":"5e82b1b67fb86f1f98e6c13f235d78814c2e3a6fa4fcb228910281b77ab3c97f"}}