{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:RXUR6GVM22QCMV6NMK3IW7O4PD","short_pith_number":"pith:RXUR6GVM","canonical_record":{"source":{"id":"1902.05696","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-15T06:01:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"938801fc41ab657aa24de37ca95673c0a42bac83fcadbf54ea2c84b8702dfbbf","abstract_canon_sha256":"dcd3dff53afd0eb881aa73743014c87f489852e4e19c23a0aa9e370b04241ce2"},"schema_version":"1.0"},"canonical_sha256":"8de91f1aacd6a02657cd62b68b7ddc78e25e9b713edf759bbb1f2131407bb5b4","source":{"kind":"arxiv","id":"1902.05696","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.05696","created_at":"2026-05-17T23:53:56Z"},{"alias_kind":"arxiv_version","alias_value":"1902.05696v1","created_at":"2026-05-17T23:53:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.05696","created_at":"2026-05-17T23:53:56Z"},{"alias_kind":"pith_short_12","alias_value":"RXUR6GVM22QC","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"RXUR6GVM22QCMV6N","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"RXUR6GVM","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:RXUR6GVM22QCMV6NMK3IW7O4PD","target":"record","payload":{"canonical_record":{"source":{"id":"1902.05696","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-15T06:01:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"938801fc41ab657aa24de37ca95673c0a42bac83fcadbf54ea2c84b8702dfbbf","abstract_canon_sha256":"dcd3dff53afd0eb881aa73743014c87f489852e4e19c23a0aa9e370b04241ce2"},"schema_version":"1.0"},"canonical_sha256":"8de91f1aacd6a02657cd62b68b7ddc78e25e9b713edf759bbb1f2131407bb5b4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:56.480645Z","signature_b64":"TNpBs0S8u2pDQE8oeuSwHnnon8V43AwDHzFyJO/tRwzr/qCZwjn/duQzbXpEweEJe8CIorpT+paowXxtdnjrAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8de91f1aacd6a02657cd62b68b7ddc78e25e9b713edf759bbb1f2131407bb5b4","last_reissued_at":"2026-05-17T23:53:56.480066Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:56.480066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.05696","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":"2026-05-17T23:53:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X1KPkL5rqk45Ur2T4RAEi195v1b3CQWhykPpZOS54naIaoBJ59bxkcmk3taixL/APbLXVQClmMq+sCbZnfaHBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T04:52:46.530354Z"},"content_sha256":"5b04f1cd2c11ed760f454002c47491c47e41fed927c0825b82df8800433b039e","schema_version":"1.0","event_id":"sha256:5b04f1cd2c11ed760f454002c47491c47e41fed927c0825b82df8800433b039e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:RXUR6GVM22QCMV6NMK3IW7O4PD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Adaptively Scale Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guo-jun Qi, Hao Hu, Liqiang Wang","submitted_at":"2019-02-15T06:01:24Z","abstract_excerpt":"Recent advancements in recurrent neural network (RNN) research have demonstrated the superiority of utilizing multiscale structures in learning temporal representations of time series. Currently, most of multiscale RNNs use fixed scales, which do not comply with the nature of dynamical temporal patterns among sequences. In this paper, we propose Adaptively Scaled Recurrent Neural Networks (ASRNN), a simple but efficient way to handle this problem. Instead of using predefined scales, ASRNNs are able to learn and adjust scales based on different temporal contexts, making them more flexible in mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.05696","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":"2026-05-17T23:53:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sds1NiUu3iX9uizcHAsrl+fhQ06l1tIT6oSiiY9xl1HTgB5pGp8sPuHu+FHuyAst22VxMsrWltM/NaOtMZKoDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T04:52:46.531073Z"},"content_sha256":"875aa3aadd7573078466cbe4bc376c30b36764333ed8a5682b068ea146b6eba5","schema_version":"1.0","event_id":"sha256:875aa3aadd7573078466cbe4bc376c30b36764333ed8a5682b068ea146b6eba5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RXUR6GVM22QCMV6NMK3IW7O4PD/bundle.json","state_url":"https://pith.science/pith/RXUR6GVM22QCMV6NMK3IW7O4PD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RXUR6GVM22QCMV6NMK3IW7O4PD/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":"2026-06-01T04:52:46Z","links":{"resolver":"https://pith.science/pith/RXUR6GVM22QCMV6NMK3IW7O4PD","bundle":"https://pith.science/pith/RXUR6GVM22QCMV6NMK3IW7O4PD/bundle.json","state":"https://pith.science/pith/RXUR6GVM22QCMV6NMK3IW7O4PD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RXUR6GVM22QCMV6NMK3IW7O4PD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:RXUR6GVM22QCMV6NMK3IW7O4PD","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":"dcd3dff53afd0eb881aa73743014c87f489852e4e19c23a0aa9e370b04241ce2","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-15T06:01:24Z","title_canon_sha256":"938801fc41ab657aa24de37ca95673c0a42bac83fcadbf54ea2c84b8702dfbbf"},"schema_version":"1.0","source":{"id":"1902.05696","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.05696","created_at":"2026-05-17T23:53:56Z"},{"alias_kind":"arxiv_version","alias_value":"1902.05696v1","created_at":"2026-05-17T23:53:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.05696","created_at":"2026-05-17T23:53:56Z"},{"alias_kind":"pith_short_12","alias_value":"RXUR6GVM22QC","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"RXUR6GVM22QCMV6N","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"RXUR6GVM","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:875aa3aadd7573078466cbe4bc376c30b36764333ed8a5682b068ea146b6eba5","target":"graph","created_at":"2026-05-17T23:53:56Z","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":"Recent advancements in recurrent neural network (RNN) research have demonstrated the superiority of utilizing multiscale structures in learning temporal representations of time series. Currently, most of multiscale RNNs use fixed scales, which do not comply with the nature of dynamical temporal patterns among sequences. In this paper, we propose Adaptively Scaled Recurrent Neural Networks (ASRNN), a simple but efficient way to handle this problem. Instead of using predefined scales, ASRNNs are able to learn and adjust scales based on different temporal contexts, making them more flexible in mo","authors_text":"Guo-jun Qi, Hao Hu, Liqiang Wang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-15T06:01:24Z","title":"Learning to Adaptively Scale Recurrent Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.05696","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":"sha256:5b04f1cd2c11ed760f454002c47491c47e41fed927c0825b82df8800433b039e","target":"record","created_at":"2026-05-17T23:53:56Z","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":"dcd3dff53afd0eb881aa73743014c87f489852e4e19c23a0aa9e370b04241ce2","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-15T06:01:24Z","title_canon_sha256":"938801fc41ab657aa24de37ca95673c0a42bac83fcadbf54ea2c84b8702dfbbf"},"schema_version":"1.0","source":{"id":"1902.05696","kind":"arxiv","version":1}},"canonical_sha256":"8de91f1aacd6a02657cd62b68b7ddc78e25e9b713edf759bbb1f2131407bb5b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8de91f1aacd6a02657cd62b68b7ddc78e25e9b713edf759bbb1f2131407bb5b4","first_computed_at":"2026-05-17T23:53:56.480066Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:53:56.480066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TNpBs0S8u2pDQE8oeuSwHnnon8V43AwDHzFyJO/tRwzr/qCZwjn/duQzbXpEweEJe8CIorpT+paowXxtdnjrAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:53:56.480645Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.05696","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b04f1cd2c11ed760f454002c47491c47e41fed927c0825b82df8800433b039e","sha256:875aa3aadd7573078466cbe4bc376c30b36764333ed8a5682b068ea146b6eba5"],"state_sha256":"d8f3c53f67419b26205c55cc737bd4a55583b3ebcab89f0b45d721134aab815f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5xDF7+GE6ljQu4F0K95CbY20SJMqh9ov4MlXYHqZ51kRboWi71Q252isA8T+wzKAzUG6gDH+XrlGXitNCUsLCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T04:52:46.534246Z","bundle_sha256":"8ab9fcdab063153b6b8d5735a7fa95101847bdb8fe262553c386c68f41a6e82d"}}