{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EJLJ5NLHC4UGYMBXDXMG2AIVVW","short_pith_number":"pith:EJLJ5NLH","schema_version":"1.0","canonical_sha256":"22569eb56717286c30371dd86d0115adac9f897e7903f31f9ad61758fbc631cc","source":{"kind":"arxiv","id":"2410.23222","version":4},"attestation_state":"computed","paper":{"title":"Dataset-Driven Channel Masks in Transformers for Multivariate Time Series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Channel masks from similarity matrices and learnable domain parameters enable partial channel dependence in Transformer attention for multivariate time series.","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kibok Lee, Seunghan Lee, Taeyoung Park","submitted_at":"2024-10-30T17:12:03Z","abstract_excerpt":"Recent advancements in foundation models have been successfully extended to the time series (TS) domain, facilitated by the emergence of large-scale TS datasets. However, previous efforts have primarily Capturing channel dependency (CD) is essential for modeling multivariate time series (TS), and attention-based methods have been widely employed for this purpose. Nonetheless, these methods primarily focus on modifying the architecture, often neglecting the importance of dataset-specific characteristics. In this work, we introduce the concept of partial channel dependence (PCD) to enhance CD mo"},"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":"2410.23222","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-30T17:12:03Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"fa73b375f2ee064d83f7213ab416f9a2637cc63b5448a101de214c6baf22b5fe","abstract_canon_sha256":"2dfe6cfb818b3cea396fd99e984693b67ef043ba895eeb899258e64122e60068"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:04:51.338785Z","signature_b64":"Tur5MbNwPfE67KMbf9/KUsFNDOLZKQG2AR6DeURfByZEEfLYBjFqxT9oCMjlmUS3a2lGgqYLGpSx4zeoYMHZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22569eb56717286c30371dd86d0115adac9f897e7903f31f9ad61758fbc631cc","last_reissued_at":"2026-05-29T01:04:51.338236Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:04:51.338236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dataset-Driven Channel Masks in Transformers for Multivariate Time Series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Channel masks from similarity matrices and learnable domain parameters enable partial channel dependence in Transformer attention for multivariate time series.","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kibok Lee, Seunghan Lee, Taeyoung Park","submitted_at":"2024-10-30T17:12:03Z","abstract_excerpt":"Recent advancements in foundation models have been successfully extended to the time series (TS) domain, facilitated by the emergence of large-scale TS datasets. However, previous efforts have primarily Capturing channel dependency (CD) is essential for modeling multivariate time series (TS), and attention-based methods have been widely employed for this purpose. Nonetheless, these methods primarily focus on modifying the architecture, often neglecting the importance of dataset-specific characteristics. In this work, we introduce the concept of partial channel dependence (PCD) to enhance CD mo"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Channel masks consisting of a similarity matrix and dataset-specific learnable domain parameters, integrated via element-wise multiplication into attention matrices, achieve partial channel dependence and thereby enhance channel dependency modeling in Transformer-based multivariate time series models.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a similarity matrix derived from the data plus a modest number of learnable domain parameters will reliably isolate the relevant partial dependencies without introducing harmful bias or requiring per-dataset hyper-parameter search that negates the claimed benefit.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Introduces channel masks built from similarity matrices plus learnable domain parameters to realize partial channel dependence inside Transformer attention for multivariate time series.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Channel masks from similarity matrices and learnable domain parameters enable partial channel dependence in Transformer attention for multivariate time series.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"6e8778362d05f2fb69bec99abb75fa5ae6eb7552f46ea310301d054547c224b4"},"source":{"id":"2410.23222","kind":"arxiv","version":4},"verdict":{"id":"7e77a271-f676-4fd9-8770-914fd23927b4","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-23T18:36:12.791850Z","strongest_claim":"Channel masks consisting of a similarity matrix and dataset-specific learnable domain parameters, integrated via element-wise multiplication into attention matrices, achieve partial channel dependence and thereby enhance channel dependency modeling in Transformer-based multivariate time series models.","one_line_summary":"Introduces channel masks built from similarity matrices plus learnable domain parameters to realize partial channel dependence inside Transformer attention for multivariate time series.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a similarity matrix derived from the data plus a modest number of learnable domain parameters will reliably isolate the relevant partial dependencies without introducing harmful bias or requiring per-dataset hyper-parameter search that negates the claimed benefit.","pith_extraction_headline":"Channel masks from similarity matrices and learnable domain parameters enable partial channel dependence in Transformer attention for multivariate time series."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.23222/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":"2410.23222","created_at":"2026-05-29T01:04:51.338344+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.23222v4","created_at":"2026-05-29T01:04:51.338344+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23222","created_at":"2026-05-29T01:04:51.338344+00:00"},{"alias_kind":"pith_short_12","alias_value":"EJLJ5NLHC4UG","created_at":"2026-05-29T01:04:51.338344+00:00"},{"alias_kind":"pith_short_16","alias_value":"EJLJ5NLHC4UGYMBX","created_at":"2026-05-29T01:04:51.338344+00:00"},{"alias_kind":"pith_short_8","alias_value":"EJLJ5NLH","created_at":"2026-05-29T01:04:51.338344+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EJLJ5NLHC4UGYMBXDXMG2AIVVW","json":"https://pith.science/pith/EJLJ5NLHC4UGYMBXDXMG2AIVVW.json","graph_json":"https://pith.science/api/pith-number/EJLJ5NLHC4UGYMBXDXMG2AIVVW/graph.json","events_json":"https://pith.science/api/pith-number/EJLJ5NLHC4UGYMBXDXMG2AIVVW/events.json","paper":"https://pith.science/paper/EJLJ5NLH"},"agent_actions":{"view_html":"https://pith.science/pith/EJLJ5NLHC4UGYMBXDXMG2AIVVW","download_json":"https://pith.science/pith/EJLJ5NLHC4UGYMBXDXMG2AIVVW.json","view_paper":"https://pith.science/paper/EJLJ5NLH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.23222&json=true","fetch_graph":"https://pith.science/api/pith-number/EJLJ5NLHC4UGYMBXDXMG2AIVVW/graph.json","fetch_events":"https://pith.science/api/pith-number/EJLJ5NLHC4UGYMBXDXMG2AIVVW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EJLJ5NLHC4UGYMBXDXMG2AIVVW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EJLJ5NLHC4UGYMBXDXMG2AIVVW/action/storage_attestation","attest_author":"https://pith.science/pith/EJLJ5NLHC4UGYMBXDXMG2AIVVW/action/author_attestation","sign_citation":"https://pith.science/pith/EJLJ5NLHC4UGYMBXDXMG2AIVVW/action/citation_signature","submit_replication":"https://pith.science/pith/EJLJ5NLHC4UGYMBXDXMG2AIVVW/action/replication_record"}},"created_at":"2026-05-29T01:04:51.338344+00:00","updated_at":"2026-05-29T01:04:51.338344+00:00"}