{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:O2H6E4ZZDBWWMYBF6JK3JKBYWX","short_pith_number":"pith:O2H6E4ZZ","schema_version":"1.0","canonical_sha256":"768fe27339186d666025f255b4a838b5c094cffba5c6a2358b444a418555493a","source":{"kind":"arxiv","id":"2606.03097","version":1},"attestation_state":"computed","paper":{"title":"From Long News to Accurate Forecast: Importance-Aware Fusion and PRM-Guided Reflection for Time Series Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hui-Ling Zhen, Kaichao Liang, Linqi Song, Mingxuan Yuan, Mingyang Liu, Qingcan Kang, Shixiong Kai, Tao Zhong, Yuke Wang","submitted_at":"2026-06-02T03:36:30Z","abstract_excerpt":"Incorporating news into time series forecasting is appealing because news can reveal abrupt exogenous events that historical values alone cannot recover. However, existing LLM-based news-forecasting pipelines face two practical limitations: relevant news articles often exceed the model's context window, and iterative retrieval of supplementary news is typically unguided, leading to redundant updates and slow convergence. We address these issues with a novel framework that combines importance-aware news compression and process-level retrieval supervision. First, we train an importance reward mo"},"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":"2606.03097","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T03:36:30Z","cross_cats_sorted":[],"title_canon_sha256":"71218b3afeee8b6f8aaecc5d28d18a64deb2ee199c5cd11e32d3f245f5abe906","abstract_canon_sha256":"2aec99c11e6ff16c727820feb8cdfd38a2ad23b465b3fb89e81baa42b1d6dd56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:31.582356Z","signature_b64":"MEggi0KCIE05tCbGyzCr7DAL/NxtuTVQwd8N7UAqmOhIuOADg0qAgZu/ofBSxub9djoGa9TItCjSqffp5hq4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"768fe27339186d666025f255b4a838b5c094cffba5c6a2358b444a418555493a","last_reissued_at":"2026-06-03T01:05:31.581957Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:31.581957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Long News to Accurate Forecast: Importance-Aware Fusion and PRM-Guided Reflection for Time Series Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hui-Ling Zhen, Kaichao Liang, Linqi Song, Mingxuan Yuan, Mingyang Liu, Qingcan Kang, Shixiong Kai, Tao Zhong, Yuke Wang","submitted_at":"2026-06-02T03:36:30Z","abstract_excerpt":"Incorporating news into time series forecasting is appealing because news can reveal abrupt exogenous events that historical values alone cannot recover. However, existing LLM-based news-forecasting pipelines face two practical limitations: relevant news articles often exceed the model's context window, and iterative retrieval of supplementary news is typically unguided, leading to redundant updates and slow convergence. We address these issues with a novel framework that combines importance-aware news compression and process-level retrieval supervision. First, we train an importance reward mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03097","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/2606.03097/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":"2606.03097","created_at":"2026-06-03T01:05:31.582011+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03097v1","created_at":"2026-06-03T01:05:31.582011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03097","created_at":"2026-06-03T01:05:31.582011+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2H6E4ZZDBWW","created_at":"2026-06-03T01:05:31.582011+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2H6E4ZZDBWWMYBF","created_at":"2026-06-03T01:05:31.582011+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2H6E4ZZ","created_at":"2026-06-03T01:05:31.582011+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/O2H6E4ZZDBWWMYBF6JK3JKBYWX","json":"https://pith.science/pith/O2H6E4ZZDBWWMYBF6JK3JKBYWX.json","graph_json":"https://pith.science/api/pith-number/O2H6E4ZZDBWWMYBF6JK3JKBYWX/graph.json","events_json":"https://pith.science/api/pith-number/O2H6E4ZZDBWWMYBF6JK3JKBYWX/events.json","paper":"https://pith.science/paper/O2H6E4ZZ"},"agent_actions":{"view_html":"https://pith.science/pith/O2H6E4ZZDBWWMYBF6JK3JKBYWX","download_json":"https://pith.science/pith/O2H6E4ZZDBWWMYBF6JK3JKBYWX.json","view_paper":"https://pith.science/paper/O2H6E4ZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03097&json=true","fetch_graph":"https://pith.science/api/pith-number/O2H6E4ZZDBWWMYBF6JK3JKBYWX/graph.json","fetch_events":"https://pith.science/api/pith-number/O2H6E4ZZDBWWMYBF6JK3JKBYWX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2H6E4ZZDBWWMYBF6JK3JKBYWX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2H6E4ZZDBWWMYBF6JK3JKBYWX/action/storage_attestation","attest_author":"https://pith.science/pith/O2H6E4ZZDBWWMYBF6JK3JKBYWX/action/author_attestation","sign_citation":"https://pith.science/pith/O2H6E4ZZDBWWMYBF6JK3JKBYWX/action/citation_signature","submit_replication":"https://pith.science/pith/O2H6E4ZZDBWWMYBF6JK3JKBYWX/action/replication_record"}},"created_at":"2026-06-03T01:05:31.582011+00:00","updated_at":"2026-06-03T01:05:31.582011+00:00"}