{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:GII4J6QTUEL7OF42OWOEFVGPTU","short_pith_number":"pith:GII4J6QT","canonical_record":{"source":{"id":"1712.06530","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-18T17:16:07Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"d794d1ae4b51e589e70792ab3ebf1caa7b89dc6185e11962a8de8ba2e869f052","abstract_canon_sha256":"75194fa5013091558f44b1ff61832906c46f162cd5ed2a9630d8050e302aceab"},"schema_version":"1.0"},"canonical_sha256":"3211c4fa13a117f7179a759c42d4cf9d078c7ed3a8a5fb10f32356fb92992826","source":{"kind":"arxiv","id":"1712.06530","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.06530","created_at":"2026-05-17T23:54:36Z"},{"alias_kind":"arxiv_version","alias_value":"1712.06530v6","created_at":"2026-05-17T23:54:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.06530","created_at":"2026-05-17T23:54:36Z"},{"alias_kind":"pith_short_12","alias_value":"GII4J6QTUEL7","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"GII4J6QTUEL7OF42","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"GII4J6QT","created_at":"2026-05-18T12:31:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:GII4J6QTUEL7OF42OWOEFVGPTU","target":"record","payload":{"canonical_record":{"source":{"id":"1712.06530","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-18T17:16:07Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"d794d1ae4b51e589e70792ab3ebf1caa7b89dc6185e11962a8de8ba2e869f052","abstract_canon_sha256":"75194fa5013091558f44b1ff61832906c46f162cd5ed2a9630d8050e302aceab"},"schema_version":"1.0"},"canonical_sha256":"3211c4fa13a117f7179a759c42d4cf9d078c7ed3a8a5fb10f32356fb92992826","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:36.677404Z","signature_b64":"vN0B7dgdO2wYWDqy/nR+QoUbcS9h+ckT9Lje6F15UfMDl1rfNZ7BK4J1BKiZmkMBF4rRj/K69oVegphJ/YoGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3211c4fa13a117f7179a759c42d4cf9d078c7ed3a8a5fb10f32356fb92992826","last_reissued_at":"2026-05-17T23:54:36.676736Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:36.676736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.06530","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:54:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y2qIXn9G2RKabBWs9sDWmDpWFOVj3doWXTfC9o6D3H45/EzwDYo1sQ3NWdLw4WIQxL+e0QQd0Mpd1zIFYPcbCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T21:09:50.426783Z"},"content_sha256":"29bfc11a3bb0901a2df0d7e026683587de36023ee7e0ff5ba378fda4299a328a","schema_version":"1.0","event_id":"sha256:29bfc11a3bb0901a2df0d7e026683587de36023ee7e0ff5ba378fda4299a328a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:GII4J6QTUEL7OF42OWOEFVGPTU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic Weight Alignment for Temporal Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Brian Kenji Iwana, Seiichi Uchida","submitted_at":"2017-12-18T17:16:07Z","abstract_excerpt":"In this paper, we propose a method of improving temporal Convolutional Neural Networks (CNN) by determining the optimal alignment of weights and inputs using dynamic programming. Conventional CNN convolutions linearly match the shared weights to a window of the input. However, it is possible that there exists a more optimal alignment of weights. Thus, we propose the use of Dynamic Time Warping (DTW) to dynamically align the weights to the input of the convolutional layer. Specifically, the dynamic alignment overcomes issues such as temporal distortion by finding the minimal distance matching o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.06530","kind":"arxiv","version":6},"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":"2026-05-17T23:54:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lx93J6nMHZsUjhtu70Bo1ZCf3gHkqwu2IpEieyGbadE8RRjLW5BtZT8cCJwqtCta8IJG26mIO9fM/h9aQil7AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T21:09:50.427131Z"},"content_sha256":"084968dff741cc76ef74822291d4e0253b8f377d2e0c0c41eaa9cc6f0b8e9fa2","schema_version":"1.0","event_id":"sha256:084968dff741cc76ef74822291d4e0253b8f377d2e0c0c41eaa9cc6f0b8e9fa2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GII4J6QTUEL7OF42OWOEFVGPTU/bundle.json","state_url":"https://pith.science/pith/GII4J6QTUEL7OF42OWOEFVGPTU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GII4J6QTUEL7OF42OWOEFVGPTU/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":"2026-06-01T21:09:50Z","links":{"resolver":"https://pith.science/pith/GII4J6QTUEL7OF42OWOEFVGPTU","bundle":"https://pith.science/pith/GII4J6QTUEL7OF42OWOEFVGPTU/bundle.json","state":"https://pith.science/pith/GII4J6QTUEL7OF42OWOEFVGPTU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GII4J6QTUEL7OF42OWOEFVGPTU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:GII4J6QTUEL7OF42OWOEFVGPTU","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":"75194fa5013091558f44b1ff61832906c46f162cd5ed2a9630d8050e302aceab","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-18T17:16:07Z","title_canon_sha256":"d794d1ae4b51e589e70792ab3ebf1caa7b89dc6185e11962a8de8ba2e869f052"},"schema_version":"1.0","source":{"id":"1712.06530","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.06530","created_at":"2026-05-17T23:54:36Z"},{"alias_kind":"arxiv_version","alias_value":"1712.06530v6","created_at":"2026-05-17T23:54:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.06530","created_at":"2026-05-17T23:54:36Z"},{"alias_kind":"pith_short_12","alias_value":"GII4J6QTUEL7","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"GII4J6QTUEL7OF42","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"GII4J6QT","created_at":"2026-05-18T12:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:084968dff741cc76ef74822291d4e0253b8f377d2e0c0c41eaa9cc6f0b8e9fa2","target":"graph","created_at":"2026-05-17T23:54:36Z","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":"In this paper, we propose a method of improving temporal Convolutional Neural Networks (CNN) by determining the optimal alignment of weights and inputs using dynamic programming. Conventional CNN convolutions linearly match the shared weights to a window of the input. However, it is possible that there exists a more optimal alignment of weights. Thus, we propose the use of Dynamic Time Warping (DTW) to dynamically align the weights to the input of the convolutional layer. Specifically, the dynamic alignment overcomes issues such as temporal distortion by finding the minimal distance matching o","authors_text":"Brian Kenji Iwana, Seiichi Uchida","cross_cats":["cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-18T17:16:07Z","title":"Dynamic Weight Alignment for Temporal Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.06530","kind":"arxiv","version":6},"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":"sha256:29bfc11a3bb0901a2df0d7e026683587de36023ee7e0ff5ba378fda4299a328a","target":"record","created_at":"2026-05-17T23:54:36Z","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":"75194fa5013091558f44b1ff61832906c46f162cd5ed2a9630d8050e302aceab","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-18T17:16:07Z","title_canon_sha256":"d794d1ae4b51e589e70792ab3ebf1caa7b89dc6185e11962a8de8ba2e869f052"},"schema_version":"1.0","source":{"id":"1712.06530","kind":"arxiv","version":6}},"canonical_sha256":"3211c4fa13a117f7179a759c42d4cf9d078c7ed3a8a5fb10f32356fb92992826","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3211c4fa13a117f7179a759c42d4cf9d078c7ed3a8a5fb10f32356fb92992826","first_computed_at":"2026-05-17T23:54:36.676736Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:36.676736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vN0B7dgdO2wYWDqy/nR+QoUbcS9h+ckT9Lje6F15UfMDl1rfNZ7BK4J1BKiZmkMBF4rRj/K69oVegphJ/YoGBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:36.677404Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.06530","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29bfc11a3bb0901a2df0d7e026683587de36023ee7e0ff5ba378fda4299a328a","sha256:084968dff741cc76ef74822291d4e0253b8f377d2e0c0c41eaa9cc6f0b8e9fa2"],"state_sha256":"5c0e2f1240be933e3e401aa2034534322fa55a32b100191a68d3d33950d88966"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u3etbRspItsPbiKPazeZdvNr5C8wkfTPaaXFbyCBC73qxrK56UvPPW4afGcC15sIDlG3wtsONZeMgZTAgSKZDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T21:09:50.429044Z","bundle_sha256":"aee06190ddfd4b4c516ab0ea9d77dec66915e5cd3864e330b154b1e0b03e030d"}}