{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PIB7JFA3IHEQIATQZDMMU5ZUFF","short_pith_number":"pith:PIB7JFA3","schema_version":"1.0","canonical_sha256":"7a03f4941b41c9040270c8d8ca7734295adaea701135f4041c23fb040350d262","source":{"kind":"arxiv","id":"2506.20073","version":1},"attestation_state":"computed","paper":{"title":"A Modular Multitask Reasoning Framework Integrating Spatio-temporal Models and LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Cheng Long, Gao Cong, Jiahao Ji, Jingyuan Wang, Kethmi Hirushini Hettige, Shili Xiang","submitted_at":"2025-06-25T00:55:34Z","abstract_excerpt":"Spatio-temporal data mining plays a pivotal role in informed decision making across diverse domains. However, existing models are often restricted to narrow tasks, lacking the capacity for multi-task inference and complex long-form reasoning that require generation of in-depth, explanatory outputs. These limitations restrict their applicability to real-world, multi-faceted decision scenarios. In this work, we introduce STReason, a novel framework that integrates the reasoning strengths of large language models (LLMs) with the analytical capabilities of spatio-temporal models for multi-task inf"},"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":"2506.20073","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-25T00:55:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7dfaef0424387778dcc9ebb79f38422b37b109d9d52c8216f028881b2cf1da59","abstract_canon_sha256":"496be76c962196c88c4ec7186b5f90b85b22dd4767a5c31ec2c2f004a1ef27de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:59.863380Z","signature_b64":"x8GVQDZQD+9egHbkZ7X4wfeq/kwWkFGsp8jpY0m+plmsRoqK7hfkwaGF6WQ2fow/5dl03cocrrkxG+oSE7SiAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a03f4941b41c9040270c8d8ca7734295adaea701135f4041c23fb040350d262","last_reissued_at":"2026-07-05T11:26:59.862959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:59.862959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Modular Multitask Reasoning Framework Integrating Spatio-temporal Models and LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Cheng Long, Gao Cong, Jiahao Ji, Jingyuan Wang, Kethmi Hirushini Hettige, Shili Xiang","submitted_at":"2025-06-25T00:55:34Z","abstract_excerpt":"Spatio-temporal data mining plays a pivotal role in informed decision making across diverse domains. However, existing models are often restricted to narrow tasks, lacking the capacity for multi-task inference and complex long-form reasoning that require generation of in-depth, explanatory outputs. These limitations restrict their applicability to real-world, multi-faceted decision scenarios. In this work, we introduce STReason, a novel framework that integrates the reasoning strengths of large language models (LLMs) with the analytical capabilities of spatio-temporal models for multi-task inf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20073","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/2506.20073/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":"2506.20073","created_at":"2026-07-05T11:26:59.863017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.20073v1","created_at":"2026-07-05T11:26:59.863017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20073","created_at":"2026-07-05T11:26:59.863017+00:00"},{"alias_kind":"pith_short_12","alias_value":"PIB7JFA3IHEQ","created_at":"2026-07-05T11:26:59.863017+00:00"},{"alias_kind":"pith_short_16","alias_value":"PIB7JFA3IHEQIATQ","created_at":"2026-07-05T11:26:59.863017+00:00"},{"alias_kind":"pith_short_8","alias_value":"PIB7JFA3","created_at":"2026-07-05T11:26:59.863017+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/PIB7JFA3IHEQIATQZDMMU5ZUFF","json":"https://pith.science/pith/PIB7JFA3IHEQIATQZDMMU5ZUFF.json","graph_json":"https://pith.science/api/pith-number/PIB7JFA3IHEQIATQZDMMU5ZUFF/graph.json","events_json":"https://pith.science/api/pith-number/PIB7JFA3IHEQIATQZDMMU5ZUFF/events.json","paper":"https://pith.science/paper/PIB7JFA3"},"agent_actions":{"view_html":"https://pith.science/pith/PIB7JFA3IHEQIATQZDMMU5ZUFF","download_json":"https://pith.science/pith/PIB7JFA3IHEQIATQZDMMU5ZUFF.json","view_paper":"https://pith.science/paper/PIB7JFA3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.20073&json=true","fetch_graph":"https://pith.science/api/pith-number/PIB7JFA3IHEQIATQZDMMU5ZUFF/graph.json","fetch_events":"https://pith.science/api/pith-number/PIB7JFA3IHEQIATQZDMMU5ZUFF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PIB7JFA3IHEQIATQZDMMU5ZUFF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PIB7JFA3IHEQIATQZDMMU5ZUFF/action/storage_attestation","attest_author":"https://pith.science/pith/PIB7JFA3IHEQIATQZDMMU5ZUFF/action/author_attestation","sign_citation":"https://pith.science/pith/PIB7JFA3IHEQIATQZDMMU5ZUFF/action/citation_signature","submit_replication":"https://pith.science/pith/PIB7JFA3IHEQIATQZDMMU5ZUFF/action/replication_record"}},"created_at":"2026-07-05T11:26:59.863017+00:00","updated_at":"2026-07-05T11:26:59.863017+00:00"}