{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OVUJRDZ6KY62OKJS4TYWM7KTYH","short_pith_number":"pith:OVUJRDZ6","schema_version":"1.0","canonical_sha256":"7568988f3e563da72932e4f1667d53c1d6567082f1bdf2c7d1123e21e6b255ef","source":{"kind":"arxiv","id":"2106.00614","version":1},"attestation_state":"computed","paper":{"title":"Pattern Discovery in Time Series with Byte Pair Encoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.SP","authors_text":"Kristina Lerman, Nazgol Tavabi","submitted_at":"2021-05-30T00:47:19Z","abstract_excerpt":"The growing popularity of wearable sensors has generated large quantities of temporal physiological and activity data. Ability to analyze this data offers new opportunities for real-time health monitoring and forecasting. However, temporal physiological data presents many analytic challenges: the data is noisy, contains many missing values, and each series has a different length. Most methods proposed for time series analysis and classification do not handle datasets with these characteristics nor do they offer interpretability and explainability, a critical requirement in the health domain. W"},"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":"2106.00614","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SP","submitted_at":"2021-05-30T00:47:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3999ebe41f1883a2541c6e06c82e9d66aeea1fadcfb44a052ef673ef72961644","abstract_canon_sha256":"71cd6291ee3ccf94f387d9b2aed315439fc858fceff6291ae955f91bdc314e9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:45:08.923212Z","signature_b64":"sxeDu6sfyq+qBJL73dHYrmfKb03p4gcjE+PLgzAilRqnHrjO3TU6y03dNvAAOFVm02vQXp1cPacukw3opTdzCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7568988f3e563da72932e4f1667d53c1d6567082f1bdf2c7d1123e21e6b255ef","last_reissued_at":"2026-07-05T02:45:08.922845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:45:08.922845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pattern Discovery in Time Series with Byte Pair Encoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.SP","authors_text":"Kristina Lerman, Nazgol Tavabi","submitted_at":"2021-05-30T00:47:19Z","abstract_excerpt":"The growing popularity of wearable sensors has generated large quantities of temporal physiological and activity data. Ability to analyze this data offers new opportunities for real-time health monitoring and forecasting. However, temporal physiological data presents many analytic challenges: the data is noisy, contains many missing values, and each series has a different length. Most methods proposed for time series analysis and classification do not handle datasets with these characteristics nor do they offer interpretability and explainability, a critical requirement in the health domain. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00614","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/2106.00614/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":"2106.00614","created_at":"2026-07-05T02:45:08.922909+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.00614v1","created_at":"2026-07-05T02:45:08.922909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00614","created_at":"2026-07-05T02:45:08.922909+00:00"},{"alias_kind":"pith_short_12","alias_value":"OVUJRDZ6KY62","created_at":"2026-07-05T02:45:08.922909+00:00"},{"alias_kind":"pith_short_16","alias_value":"OVUJRDZ6KY62OKJS","created_at":"2026-07-05T02:45:08.922909+00:00"},{"alias_kind":"pith_short_8","alias_value":"OVUJRDZ6","created_at":"2026-07-05T02:45:08.922909+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.14373","citing_title":"ECG-Byte: A Tokenizer for End-to-End Generative Electrocardiogram Language Modeling","ref_index":67,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OVUJRDZ6KY62OKJS4TYWM7KTYH","json":"https://pith.science/pith/OVUJRDZ6KY62OKJS4TYWM7KTYH.json","graph_json":"https://pith.science/api/pith-number/OVUJRDZ6KY62OKJS4TYWM7KTYH/graph.json","events_json":"https://pith.science/api/pith-number/OVUJRDZ6KY62OKJS4TYWM7KTYH/events.json","paper":"https://pith.science/paper/OVUJRDZ6"},"agent_actions":{"view_html":"https://pith.science/pith/OVUJRDZ6KY62OKJS4TYWM7KTYH","download_json":"https://pith.science/pith/OVUJRDZ6KY62OKJS4TYWM7KTYH.json","view_paper":"https://pith.science/paper/OVUJRDZ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.00614&json=true","fetch_graph":"https://pith.science/api/pith-number/OVUJRDZ6KY62OKJS4TYWM7KTYH/graph.json","fetch_events":"https://pith.science/api/pith-number/OVUJRDZ6KY62OKJS4TYWM7KTYH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OVUJRDZ6KY62OKJS4TYWM7KTYH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OVUJRDZ6KY62OKJS4TYWM7KTYH/action/storage_attestation","attest_author":"https://pith.science/pith/OVUJRDZ6KY62OKJS4TYWM7KTYH/action/author_attestation","sign_citation":"https://pith.science/pith/OVUJRDZ6KY62OKJS4TYWM7KTYH/action/citation_signature","submit_replication":"https://pith.science/pith/OVUJRDZ6KY62OKJS4TYWM7KTYH/action/replication_record"}},"created_at":"2026-07-05T02:45:08.922909+00:00","updated_at":"2026-07-05T02:45:08.922909+00:00"}