{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C7NFY5N2AEDMBA3W73VPICDIY6","short_pith_number":"pith:C7NFY5N2","schema_version":"1.0","canonical_sha256":"17da5c75ba0106c08376feeaf40868c7a924686cb9cc771fec31ba3b5c7dade6","source":{"kind":"arxiv","id":"2602.23161","version":4},"attestation_state":"computed","paper":{"title":"PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"PATRA improves time series question answering by aligning extracted trends and seasonalities with language models while balancing rewards across task difficulties to support deeper reasoning.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bin Yang, Chenjuan Guo, Christian S. Jensen, Junkai Lu, Peng Chen, Xingjian Wu, Yang Shu","submitted_at":"2026-02-26T16:20:03Z","abstract_excerpt":"Time series reasoning demands both the perception of complex dynamics and logical depth. However, existing LLM-based approaches exhibit two limitations: they often treat time series merely as text or images, failing to capture the patterns like trends and seasonalities needed to answer specific questions; and when trained on a mix of simple and complex tasks, simpler objectives often dominate the learning process, hindering the development of deep reasoning capabilities. To address these limitations, we propose the Pattern-Aware Alignment and Balanced Reasoning model (PATRA), introducing a pat"},"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":true},"canonical_record":{"source":{"id":"2602.23161","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-26T16:20:03Z","cross_cats_sorted":[],"title_canon_sha256":"5f999ace13ce50e2028b8082f252480183a7b66ae1493e95c39cb95f64561f99","abstract_canon_sha256":"5e91d22033801cf9c5ee7d8699b8b525a540e1bce14e41081203484e768b3bb4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:51.833781Z","signature_b64":"3NRmyFUmm8AltYD5N0VWXSR2Nw6SoItvhUlDtWL4t0Vv59Q+IZW2guwWb7fT8ULh01q5ftTHjbf2Nim5OS5pBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17da5c75ba0106c08376feeaf40868c7a924686cb9cc771fec31ba3b5c7dade6","last_reissued_at":"2026-06-02T02:04:51.833265Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:51.833265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"PATRA improves time series question answering by aligning extracted trends and seasonalities with language models while balancing rewards across task difficulties to support deeper reasoning.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bin Yang, Chenjuan Guo, Christian S. Jensen, Junkai Lu, Peng Chen, Xingjian Wu, Yang Shu","submitted_at":"2026-02-26T16:20:03Z","abstract_excerpt":"Time series reasoning demands both the perception of complex dynamics and logical depth. However, existing LLM-based approaches exhibit two limitations: they often treat time series merely as text or images, failing to capture the patterns like trends and seasonalities needed to answer specific questions; and when trained on a mix of simple and complex tasks, simpler objectives often dominate the learning process, hindering the development of deep reasoning capabilities. To address these limitations, we propose the Pattern-Aware Alignment and Balanced Reasoning model (PATRA), introducing a pat"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"PATRA outperforms strong baselines across diverse Time Series Question Answering (TSQA) tasks, demonstrating superior cross-modal understanding and reasoning capability.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the pattern-aware mechanism successfully captures relevant dynamics without introducing noise and that the balanced reward truly enables deeper reasoning rather than just averaging performance across tasks.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PATRA improves time series question answering by extracting patterns like trends and seasonalities for alignment and applying a task-aware balanced reward to support coherent reasoning.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"PATRA improves time series question answering by aligning extracted trends and seasonalities with language models while balancing rewards across task difficulties to support deeper reasoning.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"cdde036bdf31ea32bdc831a18ab5a185a78b9d1d3b832ac6d81bb16ee846cb81"},"source":{"id":"2602.23161","kind":"arxiv","version":4},"verdict":{"id":"2d1755a5-dc67-46e2-a5f1-da37c2f01e97","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T19:01:50.499564Z","strongest_claim":"PATRA outperforms strong baselines across diverse Time Series Question Answering (TSQA) tasks, demonstrating superior cross-modal understanding and reasoning capability.","one_line_summary":"PATRA improves time series question answering by extracting patterns like trends and seasonalities for alignment and applying a task-aware balanced reward to support coherent reasoning.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the pattern-aware mechanism successfully captures relevant dynamics without introducing noise and that the balanced reward truly enables deeper reasoning rather than just averaging performance across tasks.","pith_extraction_headline":"PATRA improves time series question answering by aligning extracted trends and seasonalities with language models while balancing rewards across task difficulties to support deeper reasoning."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.23161/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":2,"snapshot_sha256":"bdafd5ece19ce838e608d7a982f5a3dcfdae26061ee0406627ebd4f16665f498"},"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":"2602.23161","created_at":"2026-06-02T02:04:51.833328+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.23161v4","created_at":"2026-06-02T02:04:51.833328+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.23161","created_at":"2026-06-02T02:04:51.833328+00:00"},{"alias_kind":"pith_short_12","alias_value":"C7NFY5N2AEDM","created_at":"2026-06-02T02:04:51.833328+00:00"},{"alias_kind":"pith_short_16","alias_value":"C7NFY5N2AEDMBA3W","created_at":"2026-06-02T02:04:51.833328+00:00"},{"alias_kind":"pith_short_8","alias_value":"C7NFY5N2","created_at":"2026-06-02T02:04:51.833328+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.03460","citing_title":"FinSTaR: Towards Financial Reasoning with Time Series Reasoning Models","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C7NFY5N2AEDMBA3W73VPICDIY6","json":"https://pith.science/pith/C7NFY5N2AEDMBA3W73VPICDIY6.json","graph_json":"https://pith.science/api/pith-number/C7NFY5N2AEDMBA3W73VPICDIY6/graph.json","events_json":"https://pith.science/api/pith-number/C7NFY5N2AEDMBA3W73VPICDIY6/events.json","paper":"https://pith.science/paper/C7NFY5N2"},"agent_actions":{"view_html":"https://pith.science/pith/C7NFY5N2AEDMBA3W73VPICDIY6","download_json":"https://pith.science/pith/C7NFY5N2AEDMBA3W73VPICDIY6.json","view_paper":"https://pith.science/paper/C7NFY5N2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.23161&json=true","fetch_graph":"https://pith.science/api/pith-number/C7NFY5N2AEDMBA3W73VPICDIY6/graph.json","fetch_events":"https://pith.science/api/pith-number/C7NFY5N2AEDMBA3W73VPICDIY6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C7NFY5N2AEDMBA3W73VPICDIY6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C7NFY5N2AEDMBA3W73VPICDIY6/action/storage_attestation","attest_author":"https://pith.science/pith/C7NFY5N2AEDMBA3W73VPICDIY6/action/author_attestation","sign_citation":"https://pith.science/pith/C7NFY5N2AEDMBA3W73VPICDIY6/action/citation_signature","submit_replication":"https://pith.science/pith/C7NFY5N2AEDMBA3W73VPICDIY6/action/replication_record"}},"created_at":"2026-06-02T02:04:51.833328+00:00","updated_at":"2026-06-02T02:04:51.833328+00:00"}