{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IBZTYAPBY3WAJDTROEYHGBNQXK","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":"4114ea871389d171beed7a7484a4eeec9ef800567199d4acc73fcf11b44af70a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-06T15:45:28Z","title_canon_sha256":"fb0fd739932b116ec7d54ac488673f2c32152ac72a79a494284795b6eeec0a68"},"schema_version":"1.0","source":{"id":"2310.04486","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.04486","created_at":"2026-07-05T08:17:11Z"},{"alias_kind":"arxiv_version","alias_value":"2310.04486v3","created_at":"2026-07-05T08:17:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04486","created_at":"2026-07-05T08:17:11Z"},{"alias_kind":"pith_short_12","alias_value":"IBZTYAPBY3WA","created_at":"2026-07-05T08:17:11Z"},{"alias_kind":"pith_short_16","alias_value":"IBZTYAPBY3WAJDTR","created_at":"2026-07-05T08:17:11Z"},{"alias_kind":"pith_short_8","alias_value":"IBZTYAPB","created_at":"2026-07-05T08:17:11Z"}],"graph_snapshots":[{"event_id":"sha256:3a994499d832ff64fdb5169b9482d7948cba9dde899be89291bf9aacf59a874e","target":"graph","created_at":"2026-07-05T08:17:11Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.04486/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multivariate time series present challenges to standard machine learning techniques, as they are often unlabeled, high dimensional, noisy, and contain missing data. To address this, we propose T-Rep, a self-supervised method to learn time series representations at a timestep granularity. T-Rep learns vector embeddings of time alongside its feature extractor, to extract temporal features such as trend, periodicity, or distribution shifts from the signal. These time-embeddings are leveraged in pretext tasks, to incorporate smooth and fine-grained temporal dependencies in the representations, as ","authors_text":"Adrien Bennetot, Archibald Fraikin, St\\'ephanie Allassonni\\`ere","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-06T15:45:28Z","title":"T-Rep: Representation Learning for Time Series using Time-Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04486","kind":"arxiv","version":3},"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:bbf1c942ae7c4725ccdfd358c1ef089301a2f70e92311ea6579991f636f619df","target":"record","created_at":"2026-07-05T08:17:11Z","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":"4114ea871389d171beed7a7484a4eeec9ef800567199d4acc73fcf11b44af70a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-06T15:45:28Z","title_canon_sha256":"fb0fd739932b116ec7d54ac488673f2c32152ac72a79a494284795b6eeec0a68"},"schema_version":"1.0","source":{"id":"2310.04486","kind":"arxiv","version":3}},"canonical_sha256":"40733c01e1c6ec048e7171307305b0bab0840eb543d8b795c7a78fd6164dcfff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40733c01e1c6ec048e7171307305b0bab0840eb543d8b795c7a78fd6164dcfff","first_computed_at":"2026-07-05T08:17:11.110211Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:17:11.110211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6pIThS+O84tCbB/xrBz9/Y/PSml4S6OxCg9wCklUsDfYDdB63Zuq6z1sXaST+jhSU+wCpKXusAdjkY3ILHgHBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:17:11.110643Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.04486","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbf1c942ae7c4725ccdfd358c1ef089301a2f70e92311ea6579991f636f619df","sha256:3a994499d832ff64fdb5169b9482d7948cba9dde899be89291bf9aacf59a874e"],"state_sha256":"b3feba3c6974e95d0efbdf1810ec44dda80ae3af3c3cf4384fd3121c59f57efc"}