{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QEQS2VDY7AESW2ZWYQ3MTOK4CD","short_pith_number":"pith:QEQS2VDY","schema_version":"1.0","canonical_sha256":"81212d5478f8092b6b36c436c9b95c10c9507b0f2fe96a73111b8d180267e029","source":{"kind":"arxiv","id":"2303.12799","version":2},"attestation_state":"computed","paper":{"title":"Time Series as Images: Vision Transformer for Irregularly Sampled Time Series","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Shiyang Li, Xifeng Yan, Zekun Li","submitted_at":"2023-03-01T22:42:44Z","abstract_excerpt":"Irregularly sampled time series are increasingly prevalent, particularly in medical domains. While various specialized methods have been developed to handle these irregularities, effectively modeling their complex dynamics and pronounced sparsity remains a challenge. This paper introduces a novel perspective by converting irregularly sampled time series into line graph images, then utilizing powerful pre-trained vision transformers for time series classification in the same way as image classification. This method not only largely simplifies specialized algorithm designs but also presents the "},"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":"2303.12799","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-01T22:42:44Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"15cd909bab67d821a35dcb87d472ebd92dd0eed386ea49aa5cc61b9d356064b4","abstract_canon_sha256":"7f03a7cf4076265b9342c405123a0ed943a0e8f1e48cbcfd8abbfac169f9eebf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:07.944770Z","signature_b64":"ELBBZAFN1A6yb4WniwxNcppaYFMdL1lk2LHan+q46GN3abPKzgy6UIw1rf2QV79pRQdteCoqPm8gN3yYxB2kCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81212d5478f8092b6b36c436c9b95c10c9507b0f2fe96a73111b8d180267e029","last_reissued_at":"2026-07-05T07:07:07.944275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:07.944275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Time Series as Images: Vision Transformer for Irregularly Sampled Time Series","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Shiyang Li, Xifeng Yan, Zekun Li","submitted_at":"2023-03-01T22:42:44Z","abstract_excerpt":"Irregularly sampled time series are increasingly prevalent, particularly in medical domains. While various specialized methods have been developed to handle these irregularities, effectively modeling their complex dynamics and pronounced sparsity remains a challenge. This paper introduces a novel perspective by converting irregularly sampled time series into line graph images, then utilizing powerful pre-trained vision transformers for time series classification in the same way as image classification. This method not only largely simplifies specialized algorithm designs but also presents the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.12799","kind":"arxiv","version":2},"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/2303.12799/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":"2303.12799","created_at":"2026-07-05T07:07:07.944338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.12799v2","created_at":"2026-07-05T07:07:07.944338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.12799","created_at":"2026-07-05T07:07:07.944338+00:00"},{"alias_kind":"pith_short_12","alias_value":"QEQS2VDY7AES","created_at":"2026-07-05T07:07:07.944338+00:00"},{"alias_kind":"pith_short_16","alias_value":"QEQS2VDY7AESW2ZW","created_at":"2026-07-05T07:07:07.944338+00:00"},{"alias_kind":"pith_short_8","alias_value":"QEQS2VDY","created_at":"2026-07-05T07:07:07.944338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18847","citing_title":"Signal, Image, or Symbolic: Exploring the Best Input Representation for Electrocardiogram-Language Models Through a Unified Framework","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QEQS2VDY7AESW2ZWYQ3MTOK4CD","json":"https://pith.science/pith/QEQS2VDY7AESW2ZWYQ3MTOK4CD.json","graph_json":"https://pith.science/api/pith-number/QEQS2VDY7AESW2ZWYQ3MTOK4CD/graph.json","events_json":"https://pith.science/api/pith-number/QEQS2VDY7AESW2ZWYQ3MTOK4CD/events.json","paper":"https://pith.science/paper/QEQS2VDY"},"agent_actions":{"view_html":"https://pith.science/pith/QEQS2VDY7AESW2ZWYQ3MTOK4CD","download_json":"https://pith.science/pith/QEQS2VDY7AESW2ZWYQ3MTOK4CD.json","view_paper":"https://pith.science/paper/QEQS2VDY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.12799&json=true","fetch_graph":"https://pith.science/api/pith-number/QEQS2VDY7AESW2ZWYQ3MTOK4CD/graph.json","fetch_events":"https://pith.science/api/pith-number/QEQS2VDY7AESW2ZWYQ3MTOK4CD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QEQS2VDY7AESW2ZWYQ3MTOK4CD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QEQS2VDY7AESW2ZWYQ3MTOK4CD/action/storage_attestation","attest_author":"https://pith.science/pith/QEQS2VDY7AESW2ZWYQ3MTOK4CD/action/author_attestation","sign_citation":"https://pith.science/pith/QEQS2VDY7AESW2ZWYQ3MTOK4CD/action/citation_signature","submit_replication":"https://pith.science/pith/QEQS2VDY7AESW2ZWYQ3MTOK4CD/action/replication_record"}},"created_at":"2026-07-05T07:07:07.944338+00:00","updated_at":"2026-07-05T07:07:07.944338+00:00"}