{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VBEDG2RKPQJKXWBILTWQXUMGN6","short_pith_number":"pith:VBEDG2RK","schema_version":"1.0","canonical_sha256":"a848336a2a7c12abd8285ced0bd1866f80769800911b51718143121098eec5c6","source":{"kind":"arxiv","id":"2106.11911","version":1},"attestation_state":"computed","paper":{"title":"Residual Networks as Flows of Velocity Fields for Diffeomorphic Time Series Alignment","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boulbaba Ben Amor, Fan Zhu, Hao Huang, Xichan Lin, Yi Fang","submitted_at":"2021-06-22T16:38:48Z","abstract_excerpt":"Non-linear (large) time warping is a challenging source of nuisance in time-series analysis. In this paper, we propose a novel diffeomorphic temporal transformer network for both pairwise and joint time-series alignment. Our ResNet-TW (Deep Residual Network for Time Warping) tackles the alignment problem by compositing a flow of incremental diffeomorphic mappings. Governed by the flow equation, our Residual Network (ResNet) builds smooth, fluid and regular flows of velocity fields and consequently generates smooth and invertible transformations (i.e. diffeomorphic warping functions). Inspired "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2106.11911","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-22T16:38:48Z","cross_cats_sorted":[],"title_canon_sha256":"94c8706e46f4c20ea1518949668d1d8b66d2e89cf0b6d05c17206127267f69a7","abstract_canon_sha256":"8d5cfb02be5d0233a96263a8124d76d19453b7ce6c8d32852bc4108420ed7150"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:51:34.148372Z","signature_b64":"ypSPr/sKDcPH6v/7Ta/+Nczs84Wb7vAoWQ8gTq526LWP0JHDNqB4I3e6s9rps/thufTm/RZq/bsnm1feIObhCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a848336a2a7c12abd8285ced0bd1866f80769800911b51718143121098eec5c6","last_reissued_at":"2026-07-05T02:51:34.147852Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:51:34.147852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Residual Networks as Flows of Velocity Fields for Diffeomorphic Time Series Alignment","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boulbaba Ben Amor, Fan Zhu, Hao Huang, Xichan Lin, Yi Fang","submitted_at":"2021-06-22T16:38:48Z","abstract_excerpt":"Non-linear (large) time warping is a challenging source of nuisance in time-series analysis. In this paper, we propose a novel diffeomorphic temporal transformer network for both pairwise and joint time-series alignment. Our ResNet-TW (Deep Residual Network for Time Warping) tackles the alignment problem by compositing a flow of incremental diffeomorphic mappings. Governed by the flow equation, our Residual Network (ResNet) builds smooth, fluid and regular flows of velocity fields and consequently generates smooth and invertible transformations (i.e. diffeomorphic warping functions). Inspired "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.11911","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.11911/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2106.11911","created_at":"2026-07-05T02:51:34.147923+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.11911v1","created_at":"2026-07-05T02:51:34.147923+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.11911","created_at":"2026-07-05T02:51:34.147923+00:00"},{"alias_kind":"pith_short_12","alias_value":"VBEDG2RKPQJK","created_at":"2026-07-05T02:51:34.147923+00:00"},{"alias_kind":"pith_short_16","alias_value":"VBEDG2RKPQJKXWBI","created_at":"2026-07-05T02:51:34.147923+00:00"},{"alias_kind":"pith_short_8","alias_value":"VBEDG2RK","created_at":"2026-07-05T02:51:34.147923+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06591","citing_title":"Diffeomorphic Temporal Alignment Nets for Time-series Joint Alignment and Averaging","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VBEDG2RKPQJKXWBILTWQXUMGN6","json":"https://pith.science/pith/VBEDG2RKPQJKXWBILTWQXUMGN6.json","graph_json":"https://pith.science/api/pith-number/VBEDG2RKPQJKXWBILTWQXUMGN6/graph.json","events_json":"https://pith.science/api/pith-number/VBEDG2RKPQJKXWBILTWQXUMGN6/events.json","paper":"https://pith.science/paper/VBEDG2RK"},"agent_actions":{"view_html":"https://pith.science/pith/VBEDG2RKPQJKXWBILTWQXUMGN6","download_json":"https://pith.science/pith/VBEDG2RKPQJKXWBILTWQXUMGN6.json","view_paper":"https://pith.science/paper/VBEDG2RK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.11911&json=true","fetch_graph":"https://pith.science/api/pith-number/VBEDG2RKPQJKXWBILTWQXUMGN6/graph.json","fetch_events":"https://pith.science/api/pith-number/VBEDG2RKPQJKXWBILTWQXUMGN6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VBEDG2RKPQJKXWBILTWQXUMGN6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VBEDG2RKPQJKXWBILTWQXUMGN6/action/storage_attestation","attest_author":"https://pith.science/pith/VBEDG2RKPQJKXWBILTWQXUMGN6/action/author_attestation","sign_citation":"https://pith.science/pith/VBEDG2RKPQJKXWBILTWQXUMGN6/action/citation_signature","submit_replication":"https://pith.science/pith/VBEDG2RKPQJKXWBILTWQXUMGN6/action/replication_record"}},"created_at":"2026-07-05T02:51:34.147923+00:00","updated_at":"2026-07-05T02:51:34.147923+00:00"}