{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VK3GAS3ZQDPFGMDJNNS63W33FB","short_pith_number":"pith:VK3GAS3Z","schema_version":"1.0","canonical_sha256":"aab6604b7980de5330696b65eddb7b287b3aada7fa462cb3277a261051fc7cdc","source":{"kind":"arxiv","id":"2311.10049","version":3},"attestation_state":"computed","paper":{"title":"Inherently Interpretable Time Series Classification via Multiple Instance Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gavin KC Cheung, Hanting Xie, Jas Kandola, Joseph Early, Kurt Cutajar, Niall Twomey","submitted_at":"2023-11-16T17:45:37Z","abstract_excerpt":"Conventional Time Series Classification (TSC) methods are often black boxes that obscure inherent interpretation of their decision-making processes. In this work, we leverage Multiple Instance Learning (MIL) to overcome this issue, and propose a new framework called MILLET: Multiple Instance Learning for Locally Explainable Time series classification. We apply MILLET to existing deep learning TSC models and show how they become inherently interpretable without compromising (and in some cases, even improving) predictive performance. We evaluate MILLET on 85 UCR TSC datasets and also present a n"},"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":"2311.10049","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-16T17:45:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c9bc85e35c5aac9e0794c6e71f8aa4b60029c151df0c5a678475763016cd0b16","abstract_canon_sha256":"f8f492e383d57a709cb1c78d9ebac4e42c15711b12c474dd07b72b7f3d93fab9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:56.474451Z","signature_b64":"Jc8wqT0UFI1eS3YE2QKHEnprC3IwvT6qLAJFC/rmtmFMt1MtMr9YTXJ9q1eSeNWg2uBXtQQaDCtUfU/hGAlxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aab6604b7980de5330696b65eddb7b287b3aada7fa462cb3277a261051fc7cdc","last_reissued_at":"2026-07-05T07:56:56.474078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:56.474078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inherently Interpretable Time Series Classification via Multiple Instance Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gavin KC Cheung, Hanting Xie, Jas Kandola, Joseph Early, Kurt Cutajar, Niall Twomey","submitted_at":"2023-11-16T17:45:37Z","abstract_excerpt":"Conventional Time Series Classification (TSC) methods are often black boxes that obscure inherent interpretation of their decision-making processes. In this work, we leverage Multiple Instance Learning (MIL) to overcome this issue, and propose a new framework called MILLET: Multiple Instance Learning for Locally Explainable Time series classification. We apply MILLET to existing deep learning TSC models and show how they become inherently interpretable without compromising (and in some cases, even improving) predictive performance. We evaluate MILLET on 85 UCR TSC datasets and also present a n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.10049","kind":"arxiv","version":3},"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/2311.10049/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":"2311.10049","created_at":"2026-07-05T07:56:56.474136+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.10049v3","created_at":"2026-07-05T07:56:56.474136+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.10049","created_at":"2026-07-05T07:56:56.474136+00:00"},{"alias_kind":"pith_short_12","alias_value":"VK3GAS3ZQDPF","created_at":"2026-07-05T07:56:56.474136+00:00"},{"alias_kind":"pith_short_16","alias_value":"VK3GAS3ZQDPFGMDJ","created_at":"2026-07-05T07:56:56.474136+00:00"},{"alias_kind":"pith_short_8","alias_value":"VK3GAS3Z","created_at":"2026-07-05T07:56:56.474136+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03267","citing_title":"On the Necessity of Multi-Domain Explanation: An Uncertainty Principle Approach for Deep Time Series Models","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VK3GAS3ZQDPFGMDJNNS63W33FB","json":"https://pith.science/pith/VK3GAS3ZQDPFGMDJNNS63W33FB.json","graph_json":"https://pith.science/api/pith-number/VK3GAS3ZQDPFGMDJNNS63W33FB/graph.json","events_json":"https://pith.science/api/pith-number/VK3GAS3ZQDPFGMDJNNS63W33FB/events.json","paper":"https://pith.science/paper/VK3GAS3Z"},"agent_actions":{"view_html":"https://pith.science/pith/VK3GAS3ZQDPFGMDJNNS63W33FB","download_json":"https://pith.science/pith/VK3GAS3ZQDPFGMDJNNS63W33FB.json","view_paper":"https://pith.science/paper/VK3GAS3Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.10049&json=true","fetch_graph":"https://pith.science/api/pith-number/VK3GAS3ZQDPFGMDJNNS63W33FB/graph.json","fetch_events":"https://pith.science/api/pith-number/VK3GAS3ZQDPFGMDJNNS63W33FB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VK3GAS3ZQDPFGMDJNNS63W33FB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VK3GAS3ZQDPFGMDJNNS63W33FB/action/storage_attestation","attest_author":"https://pith.science/pith/VK3GAS3ZQDPFGMDJNNS63W33FB/action/author_attestation","sign_citation":"https://pith.science/pith/VK3GAS3ZQDPFGMDJNNS63W33FB/action/citation_signature","submit_replication":"https://pith.science/pith/VK3GAS3ZQDPFGMDJNNS63W33FB/action/replication_record"}},"created_at":"2026-07-05T07:56:56.474136+00:00","updated_at":"2026-07-05T07:56:56.474136+00:00"}