{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2L6E424HWZVMMMNR7EFWBSXEB7","short_pith_number":"pith:2L6E424H","schema_version":"1.0","canonical_sha256":"d2fc4e6b87b66ac631b1f90b60cae40ffb66841c4012d629a20ab77ec65dd682","source":{"kind":"arxiv","id":"2308.08241","version":2},"attestation_state":"computed","paper":{"title":"TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chenxi Sun, Hongyan Li, Shenda Hong, Yaliang Li","submitted_at":"2023-08-16T09:16:02Z","abstract_excerpt":"This work summarizes two ways to accomplish Time-Series (TS) tasks in today's Large Language Model (LLM) context: LLM-for-TS (model-centric) designs and trains a fundamental large model, or fine-tunes a pre-trained LLM for TS data; TS-for-LLM (data-centric) converts TS into a model-friendly representation to enable the pre-trained LLM to handle TS data. Given the lack of data, limited resources, semantic context requirements, and so on, this work focuses on TS-for-LLM, where we aim to activate LLM's ability for TS data by designing a TS embedding method suitable for LLM. The proposed method is"},"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":"2308.08241","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-16T09:16:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2e34a7da5d8761772848404395258c9c26c05ebd6c6d743d1a6db201f138e2be","abstract_canon_sha256":"eab6f0e88b18f966a13c6248a1793dafac26925ca11ffea9a5d8adfacdd94e63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:58.416902Z","signature_b64":"HKosULcKUE/7Bimw4KfH/AJVuIXGCTLbnR34iHRkZqUCeWi7epXjwtpanuKcGdPB5eMmwBJcIemVPkuuH+POCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2fc4e6b87b66ac631b1f90b60cae40ffb66841c4012d629a20ab77ec65dd682","last_reissued_at":"2026-07-05T07:47:58.416352Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:58.416352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chenxi Sun, Hongyan Li, Shenda Hong, Yaliang Li","submitted_at":"2023-08-16T09:16:02Z","abstract_excerpt":"This work summarizes two ways to accomplish Time-Series (TS) tasks in today's Large Language Model (LLM) context: LLM-for-TS (model-centric) designs and trains a fundamental large model, or fine-tunes a pre-trained LLM for TS data; TS-for-LLM (data-centric) converts TS into a model-friendly representation to enable the pre-trained LLM to handle TS data. Given the lack of data, limited resources, semantic context requirements, and so on, this work focuses on TS-for-LLM, where we aim to activate LLM's ability for TS data by designing a TS embedding method suitable for LLM. The proposed method is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.08241","kind":"arxiv","version":2},"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/2308.08241/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":"2308.08241","created_at":"2026-07-05T07:47:58.416421+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.08241v2","created_at":"2026-07-05T07:47:58.416421+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.08241","created_at":"2026-07-05T07:47:58.416421+00:00"},{"alias_kind":"pith_short_12","alias_value":"2L6E424HWZVM","created_at":"2026-07-05T07:47:58.416421+00:00"},{"alias_kind":"pith_short_16","alias_value":"2L6E424HWZVMMMNR","created_at":"2026-07-05T07:47:58.416421+00:00"},{"alias_kind":"pith_short_8","alias_value":"2L6E424H","created_at":"2026-07-05T07:47:58.416421+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.06623","citing_title":"LLM-Guided Task-Semantic Field Factorization for Industrial Process Forecasting","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2607.06111","citing_title":"LLM-Guided Measurement Credibility Correction for Trustworthy Industrial Process Inference","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2607.01918","citing_title":"Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2401.03717","citing_title":"Universal Time-Series Representation Learning: A Survey","ref_index":188,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22055","citing_title":"Prototype-Guided Classification Sub-Task Decoupling Framework: Enhancing Generalization and Interpretability for Multivariate Time Series","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13711","citing_title":"MILM: Large Language Models for Multimodal Irregular Time Series with Informative Sampling","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2L6E424HWZVMMMNR7EFWBSXEB7","json":"https://pith.science/pith/2L6E424HWZVMMMNR7EFWBSXEB7.json","graph_json":"https://pith.science/api/pith-number/2L6E424HWZVMMMNR7EFWBSXEB7/graph.json","events_json":"https://pith.science/api/pith-number/2L6E424HWZVMMMNR7EFWBSXEB7/events.json","paper":"https://pith.science/paper/2L6E424H"},"agent_actions":{"view_html":"https://pith.science/pith/2L6E424HWZVMMMNR7EFWBSXEB7","download_json":"https://pith.science/pith/2L6E424HWZVMMMNR7EFWBSXEB7.json","view_paper":"https://pith.science/paper/2L6E424H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.08241&json=true","fetch_graph":"https://pith.science/api/pith-number/2L6E424HWZVMMMNR7EFWBSXEB7/graph.json","fetch_events":"https://pith.science/api/pith-number/2L6E424HWZVMMMNR7EFWBSXEB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2L6E424HWZVMMMNR7EFWBSXEB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2L6E424HWZVMMMNR7EFWBSXEB7/action/storage_attestation","attest_author":"https://pith.science/pith/2L6E424HWZVMMMNR7EFWBSXEB7/action/author_attestation","sign_citation":"https://pith.science/pith/2L6E424HWZVMMMNR7EFWBSXEB7/action/citation_signature","submit_replication":"https://pith.science/pith/2L6E424HWZVMMMNR7EFWBSXEB7/action/replication_record"}},"created_at":"2026-07-05T07:47:58.416421+00:00","updated_at":"2026-07-05T07:47:58.416421+00:00"}