{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:FK6JQG4LG2GUYBMAXFTCWK6YHJ","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":"2b0fb30f9887a49199a78dcd0b1c138b89fff6966f8352a932e17c4eacfc7415","cross_cats_sorted":["cs.IT","cs.LG","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-08-29T16:18:44Z","title_canon_sha256":"31351208afc3e47aba94753592d9be24c171df0763ca6537fde766eae8dcc9fe"},"schema_version":"1.0","source":{"id":"1708.08863","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.08863","created_at":"2026-05-18T00:15:10Z"},{"alias_kind":"arxiv_version","alias_value":"1708.08863v2","created_at":"2026-05-18T00:15:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.08863","created_at":"2026-05-18T00:15:10Z"},{"alias_kind":"pith_short_12","alias_value":"FK6JQG4LG2GU","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FK6JQG4LG2GUYBMA","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FK6JQG4L","created_at":"2026-05-18T12:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:f4af9b82e761f3a35bb6320845096462953201a9d2553fae99c72650114e3efc","target":"graph","created_at":"2026-05-18T00:15:10Z","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"},"paper":{"abstract_excerpt":"Recurrent Neural Networks (RNNs) achieve state-of-the-art results in many sequence-to-sequence modeling tasks. However, RNNs are difficult to train and tend to suffer from overfitting. Motivated by the Data Processing Inequality (DPI), we formulate the multi-layered network as a Markov chain, introducing a training method that comprises training the network gradually and using layer-wise gradient clipping. We found that applying our methods, combined with previously introduced regularization and optimization methods, resulted in improvements in state-of-the-art architectures operating in langu","authors_text":"Gal Rattner, Haim Permuter, Ziv Aharoni","cross_cats":["cs.IT","cs.LG","math.IT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-08-29T16:18:44Z","title":"Gradual Learning of Recurrent Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.08863","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":"sha256:5ddb0e6958e37f7d7568a06022c0ac4a7801408da1c4d3107cb4fa1aee44e2e7","target":"record","created_at":"2026-05-18T00:15:10Z","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":"2b0fb30f9887a49199a78dcd0b1c138b89fff6966f8352a932e17c4eacfc7415","cross_cats_sorted":["cs.IT","cs.LG","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-08-29T16:18:44Z","title_canon_sha256":"31351208afc3e47aba94753592d9be24c171df0763ca6537fde766eae8dcc9fe"},"schema_version":"1.0","source":{"id":"1708.08863","kind":"arxiv","version":2}},"canonical_sha256":"2abc981b8b368d4c0580b9662b2bd83a6297e9d3cdaff6646ea61c0aa7db944b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2abc981b8b368d4c0580b9662b2bd83a6297e9d3cdaff6646ea61c0aa7db944b","first_computed_at":"2026-05-18T00:15:10.260602Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:10.260602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ajRxWNqrKD2En4/ka1btLgYNXh7q3EffYemSLaif9SqAjY798J1ivb3R2ku0f+Umf4G37LFJwsH9NIktkFVpCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:10.261357Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.08863","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ddb0e6958e37f7d7568a06022c0ac4a7801408da1c4d3107cb4fa1aee44e2e7","sha256:f4af9b82e761f3a35bb6320845096462953201a9d2553fae99c72650114e3efc"],"state_sha256":"3c05197f4120e1e77c2cf9bad1902311c0884bff391126e0e3d08c855868ec08"}