{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EJLJ5NLHC4UGYMBXDXMG2AIVVW","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":"2dfe6cfb818b3cea396fd99e984693b67ef043ba895eeb899258e64122e60068","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-30T17:12:03Z","title_canon_sha256":"fa73b375f2ee064d83f7213ab416f9a2637cc63b5448a101de214c6baf22b5fe"},"schema_version":"1.0","source":{"id":"2410.23222","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.23222","created_at":"2026-05-29T01:04:51Z"},{"alias_kind":"arxiv_version","alias_value":"2410.23222v4","created_at":"2026-05-29T01:04:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23222","created_at":"2026-05-29T01:04:51Z"},{"alias_kind":"pith_short_12","alias_value":"EJLJ5NLHC4UG","created_at":"2026-05-29T01:04:51Z"},{"alias_kind":"pith_short_16","alias_value":"EJLJ5NLHC4UGYMBX","created_at":"2026-05-29T01:04:51Z"},{"alias_kind":"pith_short_8","alias_value":"EJLJ5NLH","created_at":"2026-05-29T01:04:51Z"}],"graph_snapshots":[{"event_id":"sha256:3ac36a9f60d39e5888f47f790247a7cef72b393fa05b8d14d0f716e15c116dc6","target":"graph","created_at":"2026-05-29T01:04:51Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Introduces channel masks built from similarity matrices plus learnable domain parameters to realize partial channel dependence inside Transformer attention for multivariate time series."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Channel masks from similarity matrices and learnable domain parameters enable partial channel dependence in Transformer attention for multivariate time series."}],"snapshot_sha256":"6e8778362d05f2fb69bec99abb75fa5ae6eb7552f46ea310301d054547c224b4"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.23222/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Kibok Lee, Seunghan Lee, Taeyoung Park","cross_cats":["cs.AI","stat.ML"],"headline":"Channel masks from similarity matrices and learnable domain parameters enable partial channel dependence in Transformer attention for multivariate time series.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-30T17:12:03Z","title":"Dataset-Driven Channel Masks in Transformers for Multivariate Time Series"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23222","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-23T18:36:12.791850Z","id":"7e77a271-f676-4fd9-8770-914fd23927b4","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Channel masks from similarity matrices and learnable domain parameters enable partial channel dependence in Transformer attention for multivariate time series.","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.","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."}},"verdict_id":"7e77a271-f676-4fd9-8770-914fd23927b4"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:82018724c5d48f1235a0f8162f821b1d78221ae94addc7f66d516454041647fe","target":"record","created_at":"2026-05-29T01:04:51Z","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":"2dfe6cfb818b3cea396fd99e984693b67ef043ba895eeb899258e64122e60068","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-30T17:12:03Z","title_canon_sha256":"fa73b375f2ee064d83f7213ab416f9a2637cc63b5448a101de214c6baf22b5fe"},"schema_version":"1.0","source":{"id":"2410.23222","kind":"arxiv","version":4}},"canonical_sha256":"22569eb56717286c30371dd86d0115adac9f897e7903f31f9ad61758fbc631cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22569eb56717286c30371dd86d0115adac9f897e7903f31f9ad61758fbc631cc","first_computed_at":"2026-05-29T01:04:51.338236Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:04:51.338236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tur5MbNwPfE67KMbf9/KUsFNDOLZKQG2AR6DeURfByZEEfLYBjFqxT9oCMjlmUS3a2lGgqYLGpSx4zeoYMHZCQ==","signature_status":"signed_v1","signed_at":"2026-05-29T01:04:51.338785Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.23222","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82018724c5d48f1235a0f8162f821b1d78221ae94addc7f66d516454041647fe","sha256:3ac36a9f60d39e5888f47f790247a7cef72b393fa05b8d14d0f716e15c116dc6"],"state_sha256":"95bb2ce04b7518bc65691eb607fcf7634ba0cd58f56416f9514b1ee7319ae6bc"}