{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ALZM2WUE7F26VT5EGCHD22MQEF","short_pith_number":"pith:ALZM2WUE","schema_version":"1.0","canonical_sha256":"02f2cd5a84f975eacfa4308e3d69902169ea6067599aac1689776fba447bdbd7","source":{"kind":"arxiv","id":"2502.05701","version":1},"attestation_state":"computed","paper":{"title":"TOKON: TOKenization-Optimized Normalization for time series analysis with a large language model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Janghoon Yang","submitted_at":"2025-02-08T21:42:14Z","abstract_excerpt":"While large language models have rapidly evolved towards general artificial intelligence, their versatility in analyzing time series data remains limited. To address this limitation, we propose a novel normalization technique that considers the inherent nature of tokenization. The proposed Tokenization-Optimized Normalization (TOKON) simplifies time series data by representing each element with a single token, effectively reducing the number of tokens by 2 to 3 times. Additionally, we introduce a novel prompt for time series forecasting, termed Time Series Forecasting with Care (TFSC), to furt"},"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":"2502.05701","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-08T21:42:14Z","cross_cats_sorted":[],"title_canon_sha256":"1b9fce24fa7b9bfee8e6b0d8b0800db5ec6f394e4e592b3d47d7816cc63168c3","abstract_canon_sha256":"054053ae0b4ae196f341770ee4d3645f436b8d3fcfc438923b3e790b728ef6ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:42.206604Z","signature_b64":"nQ7LMMX3WSyR5u//XNn1d9N7fMlG/3TB3VYU3O3Y+wmltecDY8dW0YMcMCZBf1RZ5eCJjeFyDQrmSdgjNePJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02f2cd5a84f975eacfa4308e3d69902169ea6067599aac1689776fba447bdbd7","last_reissued_at":"2026-07-05T10:11:42.206200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:42.206200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TOKON: TOKenization-Optimized Normalization for time series analysis with a large language model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Janghoon Yang","submitted_at":"2025-02-08T21:42:14Z","abstract_excerpt":"While large language models have rapidly evolved towards general artificial intelligence, their versatility in analyzing time series data remains limited. To address this limitation, we propose a novel normalization technique that considers the inherent nature of tokenization. The proposed Tokenization-Optimized Normalization (TOKON) simplifies time series data by representing each element with a single token, effectively reducing the number of tokens by 2 to 3 times. Additionally, we introduce a novel prompt for time series forecasting, termed Time Series Forecasting with Care (TFSC), to furt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05701","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/2502.05701/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":"2502.05701","created_at":"2026-07-05T10:11:42.206251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.05701v1","created_at":"2026-07-05T10:11:42.206251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05701","created_at":"2026-07-05T10:11:42.206251+00:00"},{"alias_kind":"pith_short_12","alias_value":"ALZM2WUE7F26","created_at":"2026-07-05T10:11:42.206251+00:00"},{"alias_kind":"pith_short_16","alias_value":"ALZM2WUE7F26VT5E","created_at":"2026-07-05T10:11:42.206251+00:00"},{"alias_kind":"pith_short_8","alias_value":"ALZM2WUE","created_at":"2026-07-05T10:11:42.206251+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02912","citing_title":"Data-Driven Forecasting of three-Component Seismograms Using Transformer Architectures","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ALZM2WUE7F26VT5EGCHD22MQEF","json":"https://pith.science/pith/ALZM2WUE7F26VT5EGCHD22MQEF.json","graph_json":"https://pith.science/api/pith-number/ALZM2WUE7F26VT5EGCHD22MQEF/graph.json","events_json":"https://pith.science/api/pith-number/ALZM2WUE7F26VT5EGCHD22MQEF/events.json","paper":"https://pith.science/paper/ALZM2WUE"},"agent_actions":{"view_html":"https://pith.science/pith/ALZM2WUE7F26VT5EGCHD22MQEF","download_json":"https://pith.science/pith/ALZM2WUE7F26VT5EGCHD22MQEF.json","view_paper":"https://pith.science/paper/ALZM2WUE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.05701&json=true","fetch_graph":"https://pith.science/api/pith-number/ALZM2WUE7F26VT5EGCHD22MQEF/graph.json","fetch_events":"https://pith.science/api/pith-number/ALZM2WUE7F26VT5EGCHD22MQEF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ALZM2WUE7F26VT5EGCHD22MQEF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ALZM2WUE7F26VT5EGCHD22MQEF/action/storage_attestation","attest_author":"https://pith.science/pith/ALZM2WUE7F26VT5EGCHD22MQEF/action/author_attestation","sign_citation":"https://pith.science/pith/ALZM2WUE7F26VT5EGCHD22MQEF/action/citation_signature","submit_replication":"https://pith.science/pith/ALZM2WUE7F26VT5EGCHD22MQEF/action/replication_record"}},"created_at":"2026-07-05T10:11:42.206251+00:00","updated_at":"2026-07-05T10:11:42.206251+00:00"}