{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:V6H673OK4V67EV6ANDD45EEQXK","short_pith_number":"pith:V6H673OK","schema_version":"1.0","canonical_sha256":"af8fefedcae57df257c068c7ce9090baa75e57df09aa90bd9754fd1150e0dd0a","source":{"kind":"arxiv","id":"2602.03164","version":2},"attestation_state":"computed","paper":{"title":"MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mingyue Cheng, Qi Liu, Shijin Wang, Shuo Yu, Xiaoyu Tao, Yaguo Liu, Ze Guo","submitted_at":"2026-02-03T06:31:40Z","abstract_excerpt":"Time series forecasting (TSF) plays a critical role in decision-making for many real-world applications. Recently, large language model (LLM)- based forecasters have made promising advancements. Despite their effectiveness, existing methods often lack explicit experience accumulation and continual evolution. In this work, we propose MemCast, a learning-to-memory framework that reformulates TSF as an experience-conditioned reasoning task. Specifically, we learn experience from the training set and organize it into a hierarchical memory. This is achieved by summarizing prediction results into hi"},"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":"2602.03164","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-03T06:31:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"64f06de4efb4e8cbb9c8ab27c70b3af039938847e64232e99b9759af88353ad9","abstract_canon_sha256":"51f8505cb86958c7973e7cb7a256b7c78ecf5c86671872f13085f8baf38a1aca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:09:54.721855Z","signature_b64":"d3DjI4JQ/fRzacY7mjgimqlpM+ErYV7gjvi0ScATWfnofKOO4hD3S0O6u8zlW0AAUM4VlZF9e/6hw8CkmvfGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af8fefedcae57df257c068c7ce9090baa75e57df09aa90bd9754fd1150e0dd0a","last_reissued_at":"2026-06-10T01:09:54.720729Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:09:54.720729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mingyue Cheng, Qi Liu, Shijin Wang, Shuo Yu, Xiaoyu Tao, Yaguo Liu, Ze Guo","submitted_at":"2026-02-03T06:31:40Z","abstract_excerpt":"Time series forecasting (TSF) plays a critical role in decision-making for many real-world applications. Recently, large language model (LLM)- based forecasters have made promising advancements. Despite their effectiveness, existing methods often lack explicit experience accumulation and continual evolution. In this work, we propose MemCast, a learning-to-memory framework that reformulates TSF as an experience-conditioned reasoning task. Specifically, we learn experience from the training set and organize it into a hierarchical memory. This is achieved by summarizing prediction results into hi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.03164","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/2602.03164/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":"2602.03164","created_at":"2026-06-10T01:09:54.720897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.03164v2","created_at":"2026-06-10T01:09:54.720897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.03164","created_at":"2026-06-10T01:09:54.720897+00:00"},{"alias_kind":"pith_short_12","alias_value":"V6H673OK4V67","created_at":"2026-06-10T01:09:54.720897+00:00"},{"alias_kind":"pith_short_16","alias_value":"V6H673OK4V67EV6A","created_at":"2026-06-10T01:09:54.720897+00:00"},{"alias_kind":"pith_short_8","alias_value":"V6H673OK","created_at":"2026-06-10T01:09:54.720897+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.03383","citing_title":"GeoDecider: A Coarse-to-Fine Agentic Workflow for Explainable Lithology Classification","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21501","citing_title":"GeoMind: An Agentic Workflow for Lithology Classification with Reasoned Tool Invocation","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00015","citing_title":"TimeRFT: Stimulating Generalizable Time Series Forecasting for TSFMs via Reinforcement Finetuning","ref_index":63,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V6H673OK4V67EV6ANDD45EEQXK","json":"https://pith.science/pith/V6H673OK4V67EV6ANDD45EEQXK.json","graph_json":"https://pith.science/api/pith-number/V6H673OK4V67EV6ANDD45EEQXK/graph.json","events_json":"https://pith.science/api/pith-number/V6H673OK4V67EV6ANDD45EEQXK/events.json","paper":"https://pith.science/paper/V6H673OK"},"agent_actions":{"view_html":"https://pith.science/pith/V6H673OK4V67EV6ANDD45EEQXK","download_json":"https://pith.science/pith/V6H673OK4V67EV6ANDD45EEQXK.json","view_paper":"https://pith.science/paper/V6H673OK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.03164&json=true","fetch_graph":"https://pith.science/api/pith-number/V6H673OK4V67EV6ANDD45EEQXK/graph.json","fetch_events":"https://pith.science/api/pith-number/V6H673OK4V67EV6ANDD45EEQXK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V6H673OK4V67EV6ANDD45EEQXK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V6H673OK4V67EV6ANDD45EEQXK/action/storage_attestation","attest_author":"https://pith.science/pith/V6H673OK4V67EV6ANDD45EEQXK/action/author_attestation","sign_citation":"https://pith.science/pith/V6H673OK4V67EV6ANDD45EEQXK/action/citation_signature","submit_replication":"https://pith.science/pith/V6H673OK4V67EV6ANDD45EEQXK/action/replication_record"}},"created_at":"2026-06-10T01:09:54.720897+00:00","updated_at":"2026-06-10T01:09:54.720897+00:00"}