{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EKFMUH2S2RVPUTFK2HSOBDK52Q","short_pith_number":"pith:EKFMUH2S","schema_version":"1.0","canonical_sha256":"228aca1f52d46afa4caad1e4e08d5dd42ead11090fdbf2ee46447ae291dd42f3","source":{"kind":"arxiv","id":"2405.03140","version":2},"attestation_state":"computed","paper":{"title":"TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abolfazl Razi, Aristeidis Sotiras, Hao Wang, Huayu Li, Peijie Qiu, Wenhui Zhu, Xiwen Chen, Yalin Wang","submitted_at":"2024-05-06T03:27:23Z","abstract_excerpt":"Deep neural networks, including transformers and convolutional neural networks, have significantly improved multivariate time series classification (MTSC). However, these methods often rely on supervised learning, which does not fully account for the sparsity and locality of patterns in time series data (e.g., diseases-related anomalous points in ECG). To address this challenge, we formally reformulate MTSC as a weakly supervised problem, introducing a novel multiple-instance learning (MIL) framework for better localization of patterns of interest and modeling time dependencies within time ser"},"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":"2405.03140","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-06T03:27:23Z","cross_cats_sorted":[],"title_canon_sha256":"7af7927d961a20f47081e6ff187316a401a449f375d62446c924942f3d40398c","abstract_canon_sha256":"48f4823ecb0f2dfc84f6a73ee88c3cc34576a623faa98f5629ffe3bdc6114fa4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:22.342155Z","signature_b64":"7TnBVLgDCcmCaIpAaTFdpuAxVzQBVwbOuA0ZuD7iOG/kYrcV0zs/Z7jyc8MIw8jk67Zg+BYWxALwQPBIF19TDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"228aca1f52d46afa4caad1e4e08d5dd42ead11090fdbf2ee46447ae291dd42f3","last_reissued_at":"2026-07-05T08:23:22.341688Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:22.341688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abolfazl Razi, Aristeidis Sotiras, Hao Wang, Huayu Li, Peijie Qiu, Wenhui Zhu, Xiwen Chen, Yalin Wang","submitted_at":"2024-05-06T03:27:23Z","abstract_excerpt":"Deep neural networks, including transformers and convolutional neural networks, have significantly improved multivariate time series classification (MTSC). However, these methods often rely on supervised learning, which does not fully account for the sparsity and locality of patterns in time series data (e.g., diseases-related anomalous points in ECG). To address this challenge, we formally reformulate MTSC as a weakly supervised problem, introducing a novel multiple-instance learning (MIL) framework for better localization of patterns of interest and modeling time dependencies within time ser"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03140","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/2405.03140/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":"2405.03140","created_at":"2026-07-05T08:23:22.341745+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.03140v2","created_at":"2026-07-05T08:23:22.341745+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03140","created_at":"2026-07-05T08:23:22.341745+00:00"},{"alias_kind":"pith_short_12","alias_value":"EKFMUH2S2RVP","created_at":"2026-07-05T08:23:22.341745+00:00"},{"alias_kind":"pith_short_16","alias_value":"EKFMUH2S2RVPUTFK","created_at":"2026-07-05T08:23:22.341745+00:00"},{"alias_kind":"pith_short_8","alias_value":"EKFMUH2S","created_at":"2026-07-05T08:23:22.341745+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22055","citing_title":"Prototype-Guided Classification Sub-Task Decoupling Framework: Enhancing Generalization and Interpretability for Multivariate Time Series","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EKFMUH2S2RVPUTFK2HSOBDK52Q","json":"https://pith.science/pith/EKFMUH2S2RVPUTFK2HSOBDK52Q.json","graph_json":"https://pith.science/api/pith-number/EKFMUH2S2RVPUTFK2HSOBDK52Q/graph.json","events_json":"https://pith.science/api/pith-number/EKFMUH2S2RVPUTFK2HSOBDK52Q/events.json","paper":"https://pith.science/paper/EKFMUH2S"},"agent_actions":{"view_html":"https://pith.science/pith/EKFMUH2S2RVPUTFK2HSOBDK52Q","download_json":"https://pith.science/pith/EKFMUH2S2RVPUTFK2HSOBDK52Q.json","view_paper":"https://pith.science/paper/EKFMUH2S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.03140&json=true","fetch_graph":"https://pith.science/api/pith-number/EKFMUH2S2RVPUTFK2HSOBDK52Q/graph.json","fetch_events":"https://pith.science/api/pith-number/EKFMUH2S2RVPUTFK2HSOBDK52Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EKFMUH2S2RVPUTFK2HSOBDK52Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EKFMUH2S2RVPUTFK2HSOBDK52Q/action/storage_attestation","attest_author":"https://pith.science/pith/EKFMUH2S2RVPUTFK2HSOBDK52Q/action/author_attestation","sign_citation":"https://pith.science/pith/EKFMUH2S2RVPUTFK2HSOBDK52Q/action/citation_signature","submit_replication":"https://pith.science/pith/EKFMUH2S2RVPUTFK2HSOBDK52Q/action/replication_record"}},"created_at":"2026-07-05T08:23:22.341745+00:00","updated_at":"2026-07-05T08:23:22.341745+00:00"}