{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TII4SEAQDCRBV6PFYZLGD6G35S","short_pith_number":"pith:TII4SEAQ","schema_version":"1.0","canonical_sha256":"9a11c9101018a21af9e5c65661f8dbecaf2800817bf16e2ad3cb524d06b90f0b","source":{"kind":"arxiv","id":"2305.16642","version":1},"attestation_state":"computed","paper":{"title":"Improving Position Encoding of Transformers for Multivariate Time Series Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chang Wei Tan, Geoffrey I. Webb, Mahsa Salehi, Navid Mohammadi Foumani","submitted_at":"2023-05-26T05:30:04Z","abstract_excerpt":"Transformers have demonstrated outstanding performance in many applications of deep learning. When applied to time series data, transformers require effective position encoding to capture the ordering of the time series data. The efficacy of position encoding in time series analysis is not well-studied and remains controversial, e.g., whether it is better to inject absolute position encoding or relative position encoding, or a combination of them. In order to clarify this, we first review existing absolute and relative position encoding methods when applied in time series classification. We th"},"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":"2305.16642","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-26T05:30:04Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"52a35f80b41c2075cfe58a921dbabad2379056abb0f35fcbcaa41c52bb459200","abstract_canon_sha256":"4d4086275896b0613e7478112711f22cda1dee1ef6e4040bddd79abe730f8dd3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:02.655120Z","signature_b64":"Fn75TUMImb7nvOYIMvJxw3BqQNollf6c9gnjgY+nrxZJjiRJ6W4ZFBvfuJ0SR9ismp3Yg/96IDZPfMGfnxD7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a11c9101018a21af9e5c65661f8dbecaf2800817bf16e2ad3cb524d06b90f0b","last_reissued_at":"2026-07-05T07:47:02.654659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:02.654659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Position Encoding of Transformers for Multivariate Time Series Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chang Wei Tan, Geoffrey I. Webb, Mahsa Salehi, Navid Mohammadi Foumani","submitted_at":"2023-05-26T05:30:04Z","abstract_excerpt":"Transformers have demonstrated outstanding performance in many applications of deep learning. When applied to time series data, transformers require effective position encoding to capture the ordering of the time series data. The efficacy of position encoding in time series analysis is not well-studied and remains controversial, e.g., whether it is better to inject absolute position encoding or relative position encoding, or a combination of them. In order to clarify this, we first review existing absolute and relative position encoding methods when applied in time series classification. We th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16642","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/2305.16642/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":"2305.16642","created_at":"2026-07-05T07:47:02.654715+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.16642v1","created_at":"2026-07-05T07:47:02.654715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16642","created_at":"2026-07-05T07:47:02.654715+00:00"},{"alias_kind":"pith_short_12","alias_value":"TII4SEAQDCRB","created_at":"2026-07-05T07:47:02.654715+00:00"},{"alias_kind":"pith_short_16","alias_value":"TII4SEAQDCRBV6PF","created_at":"2026-07-05T07:47:02.654715+00:00"},{"alias_kind":"pith_short_8","alias_value":"TII4SEAQ","created_at":"2026-07-05T07:47:02.654715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06796","citing_title":"Enhancing deep learning models for time series classification via knowledge distillation","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07437","citing_title":"ASTRAFier: A Novel and Scalable Transformer-based Stellar Variability Classifier","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TII4SEAQDCRBV6PFYZLGD6G35S","json":"https://pith.science/pith/TII4SEAQDCRBV6PFYZLGD6G35S.json","graph_json":"https://pith.science/api/pith-number/TII4SEAQDCRBV6PFYZLGD6G35S/graph.json","events_json":"https://pith.science/api/pith-number/TII4SEAQDCRBV6PFYZLGD6G35S/events.json","paper":"https://pith.science/paper/TII4SEAQ"},"agent_actions":{"view_html":"https://pith.science/pith/TII4SEAQDCRBV6PFYZLGD6G35S","download_json":"https://pith.science/pith/TII4SEAQDCRBV6PFYZLGD6G35S.json","view_paper":"https://pith.science/paper/TII4SEAQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.16642&json=true","fetch_graph":"https://pith.science/api/pith-number/TII4SEAQDCRBV6PFYZLGD6G35S/graph.json","fetch_events":"https://pith.science/api/pith-number/TII4SEAQDCRBV6PFYZLGD6G35S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TII4SEAQDCRBV6PFYZLGD6G35S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TII4SEAQDCRBV6PFYZLGD6G35S/action/storage_attestation","attest_author":"https://pith.science/pith/TII4SEAQDCRBV6PFYZLGD6G35S/action/author_attestation","sign_citation":"https://pith.science/pith/TII4SEAQDCRBV6PFYZLGD6G35S/action/citation_signature","submit_replication":"https://pith.science/pith/TII4SEAQDCRBV6PFYZLGD6G35S/action/replication_record"}},"created_at":"2026-07-05T07:47:02.654715+00:00","updated_at":"2026-07-05T07:47:02.654715+00:00"}