{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C7JZVH426QMCF7MKHEI5ICNBZG","short_pith_number":"pith:C7JZVH42","schema_version":"1.0","canonical_sha256":"17d39a9f9af41822fd8a3911d409a1c997efe1d3fcb724fd43449402ea55d7c9","source":{"kind":"arxiv","id":"2606.12481","version":1},"attestation_state":"computed","paper":{"title":"Representing Time Series as Structured Programs for LLM Reasoning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changhee Lee, Changhun Oh, Irina Rish, Jaeho Kim, Seokhyun Lee","submitted_at":"2026-06-10T07:42:35Z","abstract_excerpt":"Large language models (LLMs) have demonstrated strong reasoning and instruction-following capabilities, making them potentially powerful tools for time-series analysis. However, time series lie outside their native textual modality, raising a fundamental question: how should time series be represented so that LLMs can reason about them effectively? Existing work typically serializes raw numerical sequences or fine-tunes pre-trained LLMs on time-series data. These approaches place the burden of extracting temporal structure directly on the LLM, creating a modality mismatch that often degrades p"},"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":"2606.12481","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T07:42:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"70f4d85562bd57bd48aafc3830299b2558e365079011a9ee9f2c2d93b4cb5581","abstract_canon_sha256":"4a8df642e3395318999b47aa1bc79416d6dc45103087638750827cc59e37616e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T00:07:51.781834Z","signature_b64":"jSqhKI1Rxlh45Z9ObZHOyz4hZR8Labm6eN2wdqkGajOPRkQxj7UJ4LvFPzx8iGyfXyiP0Kf1n7PxDvSXfA15CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17d39a9f9af41822fd8a3911d409a1c997efe1d3fcb724fd43449402ea55d7c9","last_reissued_at":"2026-06-12T00:07:51.781394Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T00:07:51.781394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Representing Time Series as Structured Programs for LLM Reasoning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changhee Lee, Changhun Oh, Irina Rish, Jaeho Kim, Seokhyun Lee","submitted_at":"2026-06-10T07:42:35Z","abstract_excerpt":"Large language models (LLMs) have demonstrated strong reasoning and instruction-following capabilities, making them potentially powerful tools for time-series analysis. However, time series lie outside their native textual modality, raising a fundamental question: how should time series be represented so that LLMs can reason about them effectively? Existing work typically serializes raw numerical sequences or fine-tunes pre-trained LLMs on time-series data. These approaches place the burden of extracting temporal structure directly on the LLM, creating a modality mismatch that often degrades p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12481","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/2606.12481/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":"2606.12481","created_at":"2026-06-12T00:07:51.781466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.12481v1","created_at":"2026-06-12T00:07:51.781466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12481","created_at":"2026-06-12T00:07:51.781466+00:00"},{"alias_kind":"pith_short_12","alias_value":"C7JZVH426QMC","created_at":"2026-06-12T00:07:51.781466+00:00"},{"alias_kind":"pith_short_16","alias_value":"C7JZVH426QMCF7MK","created_at":"2026-06-12T00:07:51.781466+00:00"},{"alias_kind":"pith_short_8","alias_value":"C7JZVH42","created_at":"2026-06-12T00:07:51.781466+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/C7JZVH426QMCF7MKHEI5ICNBZG","json":"https://pith.science/pith/C7JZVH426QMCF7MKHEI5ICNBZG.json","graph_json":"https://pith.science/api/pith-number/C7JZVH426QMCF7MKHEI5ICNBZG/graph.json","events_json":"https://pith.science/api/pith-number/C7JZVH426QMCF7MKHEI5ICNBZG/events.json","paper":"https://pith.science/paper/C7JZVH42"},"agent_actions":{"view_html":"https://pith.science/pith/C7JZVH426QMCF7MKHEI5ICNBZG","download_json":"https://pith.science/pith/C7JZVH426QMCF7MKHEI5ICNBZG.json","view_paper":"https://pith.science/paper/C7JZVH42","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.12481&json=true","fetch_graph":"https://pith.science/api/pith-number/C7JZVH426QMCF7MKHEI5ICNBZG/graph.json","fetch_events":"https://pith.science/api/pith-number/C7JZVH426QMCF7MKHEI5ICNBZG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C7JZVH426QMCF7MKHEI5ICNBZG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C7JZVH426QMCF7MKHEI5ICNBZG/action/storage_attestation","attest_author":"https://pith.science/pith/C7JZVH426QMCF7MKHEI5ICNBZG/action/author_attestation","sign_citation":"https://pith.science/pith/C7JZVH426QMCF7MKHEI5ICNBZG/action/citation_signature","submit_replication":"https://pith.science/pith/C7JZVH426QMCF7MKHEI5ICNBZG/action/replication_record"}},"created_at":"2026-06-12T00:07:51.781466+00:00","updated_at":"2026-06-12T00:07:51.781466+00:00"}