{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HAIMMSN6WNLOGA5HGOHSFNDDN6","short_pith_number":"pith:HAIMMSN6","schema_version":"1.0","canonical_sha256":"3810c649beb356e303a7338f22b4636fa2ca2cb98330e0e8162829abb308a279","source":{"kind":"arxiv","id":"2506.05597","version":1},"attestation_state":"computed","paper":{"title":"FaCTR: Factorized Channel-Temporal Representation Transformers for Efficient Time Series Forecasting","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Harini Subramanyan, Yash Vijay","submitted_at":"2025-06-05T21:17:53Z","abstract_excerpt":"While Transformers excel in language and vision-where inputs are semantically rich and exhibit univariate dependency structures-their architectural complexity leads to diminishing returns in time series forecasting. Time series data is characterized by low per-timestep information density and complex dependencies across channels and covariates, requiring conditioning on structured variable interactions. To address this mismatch and overparameterization, we propose FaCTR, a lightweight spatiotemporal Transformer with an explicitly structural design. FaCTR injects dynamic, symmetric cross-channe"},"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":"2506.05597","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T21:17:53Z","cross_cats_sorted":[],"title_canon_sha256":"a53867e150be561d734f5aff72e34bc79362d8c6f6f8713055165d3b4a82fe6b","abstract_canon_sha256":"84cfc86e535b70b100c70de95eb3a15e57feaa10927572452e709cd5d059bef6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:06.537685Z","signature_b64":"EH3RtNUjm7OS/1DIoXcK2avxUvwex+Ua7nZBHdUixTUZx6oyltIs7mi0X5zsi32NxzA6Tl5kgbKXIDS/2pNBCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3810c649beb356e303a7338f22b4636fa2ca2cb98330e0e8162829abb308a279","last_reissued_at":"2026-07-05T11:17:06.537034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:06.537034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FaCTR: Factorized Channel-Temporal Representation Transformers for Efficient Time Series Forecasting","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Harini Subramanyan, Yash Vijay","submitted_at":"2025-06-05T21:17:53Z","abstract_excerpt":"While Transformers excel in language and vision-where inputs are semantically rich and exhibit univariate dependency structures-their architectural complexity leads to diminishing returns in time series forecasting. Time series data is characterized by low per-timestep information density and complex dependencies across channels and covariates, requiring conditioning on structured variable interactions. To address this mismatch and overparameterization, we propose FaCTR, a lightweight spatiotemporal Transformer with an explicitly structural design. FaCTR injects dynamic, symmetric cross-channe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05597","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/2506.05597/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":"2506.05597","created_at":"2026-07-05T11:17:06.537127+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05597v1","created_at":"2026-07-05T11:17:06.537127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05597","created_at":"2026-07-05T11:17:06.537127+00:00"},{"alias_kind":"pith_short_12","alias_value":"HAIMMSN6WNLO","created_at":"2026-07-05T11:17:06.537127+00:00"},{"alias_kind":"pith_short_16","alias_value":"HAIMMSN6WNLOGA5H","created_at":"2026-07-05T11:17:06.537127+00:00"},{"alias_kind":"pith_short_8","alias_value":"HAIMMSN6","created_at":"2026-07-05T11:17:06.537127+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/HAIMMSN6WNLOGA5HGOHSFNDDN6","json":"https://pith.science/pith/HAIMMSN6WNLOGA5HGOHSFNDDN6.json","graph_json":"https://pith.science/api/pith-number/HAIMMSN6WNLOGA5HGOHSFNDDN6/graph.json","events_json":"https://pith.science/api/pith-number/HAIMMSN6WNLOGA5HGOHSFNDDN6/events.json","paper":"https://pith.science/paper/HAIMMSN6"},"agent_actions":{"view_html":"https://pith.science/pith/HAIMMSN6WNLOGA5HGOHSFNDDN6","download_json":"https://pith.science/pith/HAIMMSN6WNLOGA5HGOHSFNDDN6.json","view_paper":"https://pith.science/paper/HAIMMSN6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05597&json=true","fetch_graph":"https://pith.science/api/pith-number/HAIMMSN6WNLOGA5HGOHSFNDDN6/graph.json","fetch_events":"https://pith.science/api/pith-number/HAIMMSN6WNLOGA5HGOHSFNDDN6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HAIMMSN6WNLOGA5HGOHSFNDDN6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HAIMMSN6WNLOGA5HGOHSFNDDN6/action/storage_attestation","attest_author":"https://pith.science/pith/HAIMMSN6WNLOGA5HGOHSFNDDN6/action/author_attestation","sign_citation":"https://pith.science/pith/HAIMMSN6WNLOGA5HGOHSFNDDN6/action/citation_signature","submit_replication":"https://pith.science/pith/HAIMMSN6WNLOGA5HGOHSFNDDN6/action/replication_record"}},"created_at":"2026-07-05T11:17:06.537127+00:00","updated_at":"2026-07-05T11:17:06.537127+00:00"}