{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:KJFJE5JNDQS7D5UPWVVKICENZ5","short_pith_number":"pith:KJFJE5JN","canonical_record":{"source":{"id":"1905.12034","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T19:03:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c59ef23af35b232fff27ba0a07a7bce146f3e9d05d68e484e562071a8ee74b5a","abstract_canon_sha256":"958aaea51a6ae85146ffabc0833a195d96f147d83318836308105f12f711c191"},"schema_version":"1.0"},"canonical_sha256":"524a92752d1c25f1f68fb56aa4088dcf5e5003540b58b4fa5d9e8154e6e84b2e","source":{"kind":"arxiv","id":"1905.12034","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.12034","created_at":"2026-05-17T23:44:49Z"},{"alias_kind":"arxiv_version","alias_value":"1905.12034v1","created_at":"2026-05-17T23:44:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12034","created_at":"2026-05-17T23:44:49Z"},{"alias_kind":"pith_short_12","alias_value":"KJFJE5JNDQS7","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KJFJE5JNDQS7D5UP","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KJFJE5JN","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:KJFJE5JNDQS7D5UPWVVKICENZ5","target":"record","payload":{"canonical_record":{"source":{"id":"1905.12034","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T19:03:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c59ef23af35b232fff27ba0a07a7bce146f3e9d05d68e484e562071a8ee74b5a","abstract_canon_sha256":"958aaea51a6ae85146ffabc0833a195d96f147d83318836308105f12f711c191"},"schema_version":"1.0"},"canonical_sha256":"524a92752d1c25f1f68fb56aa4088dcf5e5003540b58b4fa5d9e8154e6e84b2e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:49.170151Z","signature_b64":"NGMsuU238wh1OEw1KQ0XxbZylbQyV98Tsc6BTEbAC1sAoOJlPcLCpAbiJuAF3GzeWsjBU/XeAAIPj/KLU82ZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"524a92752d1c25f1f68fb56aa4088dcf5e5003540b58b4fa5d9e8154e6e84b2e","last_reissued_at":"2026-05-17T23:44:49.169586Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:49.169586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.12034","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":"2026-05-17T23:44:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ug2g2CMLLDk2sGUyflQM+bAiGpKm1TuG/tG151eAqmjRCDaDdqvr5V8XAzyFsEfxlAW+PzU47jrVgt1ZuvaSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T06:05:08.009977Z"},"content_sha256":"d9a0b3cea5678d68a36a167d9402061bcd6fa102ef48d17ae88611cb08b1a746","schema_version":"1.0","event_id":"sha256:d9a0b3cea5678d68a36a167d9402061bcd6fa102ef48d17ae88611cb08b1a746"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:KJFJE5JNDQS7D5UPWVVKICENZ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring Interpretable LSTM Neural Networks over Multi-Variable Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Nino Antulov-Fantulin, Tao Lin, Tian Guo","submitted_at":"2019-05-28T19:03:12Z","abstract_excerpt":"For recurrent neural networks trained on time series with target and exogenous variables, in addition to accurate prediction, it is also desired to provide interpretable insights into the data. In this paper, we explore the structure of LSTM recurrent neural networks to learn variable-wise hidden states, with the aim to capture different dynamics in multi-variable time series and distinguish the contribution of variables to the prediction. With these variable-wise hidden states, a mixture attention mechanism is proposed to model the generative process of the target. Then we develop associated "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12034","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":"2026-05-17T23:44:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3RVxMGuSF2cS2lZQiALXvDTMB4kseUgVcvDW3DZrNNw8y597u9GCu9886TStwRD54NxR2Pi0y6cwKjSTtD1oBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T06:05:08.010689Z"},"content_sha256":"78fe3a0cca368fc4041fb86a46d32cec292c8d55e961e30bccbd2ce06aaa8d9b","schema_version":"1.0","event_id":"sha256:78fe3a0cca368fc4041fb86a46d32cec292c8d55e961e30bccbd2ce06aaa8d9b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KJFJE5JNDQS7D5UPWVVKICENZ5/bundle.json","state_url":"https://pith.science/pith/KJFJE5JNDQS7D5UPWVVKICENZ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KJFJE5JNDQS7D5UPWVVKICENZ5/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":"2026-06-06T06:05:08Z","links":{"resolver":"https://pith.science/pith/KJFJE5JNDQS7D5UPWVVKICENZ5","bundle":"https://pith.science/pith/KJFJE5JNDQS7D5UPWVVKICENZ5/bundle.json","state":"https://pith.science/pith/KJFJE5JNDQS7D5UPWVVKICENZ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KJFJE5JNDQS7D5UPWVVKICENZ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:KJFJE5JNDQS7D5UPWVVKICENZ5","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":"958aaea51a6ae85146ffabc0833a195d96f147d83318836308105f12f711c191","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T19:03:12Z","title_canon_sha256":"c59ef23af35b232fff27ba0a07a7bce146f3e9d05d68e484e562071a8ee74b5a"},"schema_version":"1.0","source":{"id":"1905.12034","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.12034","created_at":"2026-05-17T23:44:49Z"},{"alias_kind":"arxiv_version","alias_value":"1905.12034v1","created_at":"2026-05-17T23:44:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12034","created_at":"2026-05-17T23:44:49Z"},{"alias_kind":"pith_short_12","alias_value":"KJFJE5JNDQS7","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KJFJE5JNDQS7D5UP","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KJFJE5JN","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:78fe3a0cca368fc4041fb86a46d32cec292c8d55e961e30bccbd2ce06aaa8d9b","target":"graph","created_at":"2026-05-17T23:44:49Z","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":"For recurrent neural networks trained on time series with target and exogenous variables, in addition to accurate prediction, it is also desired to provide interpretable insights into the data. In this paper, we explore the structure of LSTM recurrent neural networks to learn variable-wise hidden states, with the aim to capture different dynamics in multi-variable time series and distinguish the contribution of variables to the prediction. With these variable-wise hidden states, a mixture attention mechanism is proposed to model the generative process of the target. Then we develop associated ","authors_text":"Nino Antulov-Fantulin, Tao Lin, Tian Guo","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T19:03:12Z","title":"Exploring Interpretable LSTM Neural Networks over Multi-Variable Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12034","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:d9a0b3cea5678d68a36a167d9402061bcd6fa102ef48d17ae88611cb08b1a746","target":"record","created_at":"2026-05-17T23:44:49Z","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":"958aaea51a6ae85146ffabc0833a195d96f147d83318836308105f12f711c191","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T19:03:12Z","title_canon_sha256":"c59ef23af35b232fff27ba0a07a7bce146f3e9d05d68e484e562071a8ee74b5a"},"schema_version":"1.0","source":{"id":"1905.12034","kind":"arxiv","version":1}},"canonical_sha256":"524a92752d1c25f1f68fb56aa4088dcf5e5003540b58b4fa5d9e8154e6e84b2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"524a92752d1c25f1f68fb56aa4088dcf5e5003540b58b4fa5d9e8154e6e84b2e","first_computed_at":"2026-05-17T23:44:49.169586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:49.169586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NGMsuU238wh1OEw1KQ0XxbZylbQyV98Tsc6BTEbAC1sAoOJlPcLCpAbiJuAF3GzeWsjBU/XeAAIPj/KLU82ZBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:49.170151Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.12034","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9a0b3cea5678d68a36a167d9402061bcd6fa102ef48d17ae88611cb08b1a746","sha256:78fe3a0cca368fc4041fb86a46d32cec292c8d55e961e30bccbd2ce06aaa8d9b"],"state_sha256":"af91dc4f788a0af2436970a4ca9ba4254c0509ef9876c05a3fc93d7792d4802e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AYyirUiKPf2Jr+9nPZ1jVGNgVNlPCRnFO+gqpsXMMuvTawje+5XJz3P6i+FUJoJ31XqfXBNXD/wHOfsT6wvIBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T06:05:08.014613Z","bundle_sha256":"260c780171b39f28f4e5865c965b75f2921dc131bcbfcdac3da749ce92e8a310"}}