{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MOWK6EVDZWADL7B63OJWS5RRJQ","short_pith_number":"pith:MOWK6EVD","schema_version":"1.0","canonical_sha256":"63acaf12a3cd8035fc3edb936976314c3bf11040d0993c855cfd8e247e1d9ae4","source":{"kind":"arxiv","id":"2506.20093","version":1},"attestation_state":"computed","paper":{"title":"ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jie Song, Lei Jia, Peixuan Lei, Tao Chen, Yilin Wang, Yuanxiang Li, Yuxuan Zhang, Yuzhe Hao, Zhongyu Wei","submitted_at":"2025-06-25T02:33:47Z","abstract_excerpt":"Time-series data are critical in diverse applications, such as industrial monitoring, medical diagnostics, and climate research. However, effectively integrating these high-dimensional temporal signals with natural language for dynamic, interactive tasks remains a significant challenge. To address this, we introduce the Time-Series Question Answering (Time-Series QA) task and release EngineMT-QA, the first large-scale, multi-task, temporal-textual QA dataset designed to capture complex interactions between time-series signals and natural language. Building on this resource, we propose the Inst"},"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":"2506.20093","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-25T02:33:47Z","cross_cats_sorted":[],"title_canon_sha256":"0fb277367b48f947697ee2ed8d0d271d82a4fee99c0821ff96b784b87b389016","abstract_canon_sha256":"d77126374f998b198687c3aaba2659e7be499e12ceef79951f5d5cbfe64dcee0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:00.210615Z","signature_b64":"jreJz7GaWrQce+MYIGoC9fx5O0ZHz7/HwrrySGp6K3GaC2EItuCDJzsJz8EjWMPPi8KtqJgltwhP4pi3earnBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63acaf12a3cd8035fc3edb936976314c3bf11040d0993c855cfd8e247e1d9ae4","last_reissued_at":"2026-07-05T11:27:00.210100Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:00.210100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jie Song, Lei Jia, Peixuan Lei, Tao Chen, Yilin Wang, Yuanxiang Li, Yuxuan Zhang, Yuzhe Hao, Zhongyu Wei","submitted_at":"2025-06-25T02:33:47Z","abstract_excerpt":"Time-series data are critical in diverse applications, such as industrial monitoring, medical diagnostics, and climate research. However, effectively integrating these high-dimensional temporal signals with natural language for dynamic, interactive tasks remains a significant challenge. To address this, we introduce the Time-Series Question Answering (Time-Series QA) task and release EngineMT-QA, the first large-scale, multi-task, temporal-textual QA dataset designed to capture complex interactions between time-series signals and natural language. Building on this resource, we propose the Inst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20093","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/2506.20093/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":"2506.20093","created_at":"2026-07-05T11:27:00.210162+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.20093v1","created_at":"2026-07-05T11:27:00.210162+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20093","created_at":"2026-07-05T11:27:00.210162+00:00"},{"alias_kind":"pith_short_12","alias_value":"MOWK6EVDZWAD","created_at":"2026-07-05T11:27:00.210162+00:00"},{"alias_kind":"pith_short_16","alias_value":"MOWK6EVDZWADL7B6","created_at":"2026-07-05T11:27:00.210162+00:00"},{"alias_kind":"pith_short_8","alias_value":"MOWK6EVD","created_at":"2026-07-05T11:27:00.210162+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.14200","citing_title":"TS-Haystack: A Multi-Task Retrieval Benchmark for Long-Context Time-Series Reasoning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08614","citing_title":"DiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic Rules","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24935","citing_title":"CAN-QA: A Question-Answering Benchmark for Reasoning over In-Vehicle CAN Traffic","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10291","citing_title":"TimeSeriesExamAgent: Creating Time Series Reasoning Benchmarks at Scale","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MOWK6EVDZWADL7B63OJWS5RRJQ","json":"https://pith.science/pith/MOWK6EVDZWADL7B63OJWS5RRJQ.json","graph_json":"https://pith.science/api/pith-number/MOWK6EVDZWADL7B63OJWS5RRJQ/graph.json","events_json":"https://pith.science/api/pith-number/MOWK6EVDZWADL7B63OJWS5RRJQ/events.json","paper":"https://pith.science/paper/MOWK6EVD"},"agent_actions":{"view_html":"https://pith.science/pith/MOWK6EVDZWADL7B63OJWS5RRJQ","download_json":"https://pith.science/pith/MOWK6EVDZWADL7B63OJWS5RRJQ.json","view_paper":"https://pith.science/paper/MOWK6EVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.20093&json=true","fetch_graph":"https://pith.science/api/pith-number/MOWK6EVDZWADL7B63OJWS5RRJQ/graph.json","fetch_events":"https://pith.science/api/pith-number/MOWK6EVDZWADL7B63OJWS5RRJQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MOWK6EVDZWADL7B63OJWS5RRJQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MOWK6EVDZWADL7B63OJWS5RRJQ/action/storage_attestation","attest_author":"https://pith.science/pith/MOWK6EVDZWADL7B63OJWS5RRJQ/action/author_attestation","sign_citation":"https://pith.science/pith/MOWK6EVDZWADL7B63OJWS5RRJQ/action/citation_signature","submit_replication":"https://pith.science/pith/MOWK6EVDZWADL7B63OJWS5RRJQ/action/replication_record"}},"created_at":"2026-07-05T11:27:00.210162+00:00","updated_at":"2026-07-05T11:27:00.210162+00:00"}