{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AL2AI5FMCCPYZY42NIAXEGOF4S","short_pith_number":"pith:AL2AI5FM","schema_version":"1.0","canonical_sha256":"02f40474ac109f8ce39a6a017219c5e48b515acc68d39596a8dfd4c67843aebf","source":{"kind":"arxiv","id":"2405.09308","version":1},"attestation_state":"computed","paper":{"title":"TimeX++: Learning Time-Series Explanations with Information Bottleneck","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dongsheng Luo, Farhad Shirani, Jayantha Obeysekera, Jimeng Shi, Lei Song, Tianchun Wang, Wenqian Dong, Xu Zheng, Zhuomin Chen, Zichuan Liu","submitted_at":"2024-05-15T13:03:41Z","abstract_excerpt":"Explaining deep learning models operating on time series data is crucial in various applications of interest which require interpretable and transparent insights from time series signals. In this work, we investigate this problem from an information theoretic perspective and show that most existing measures of explainability may suffer from trivial solutions and distributional shift issues. To address these issues, we introduce a simple yet practical objective function for time series explainable learning. The design of the objective function builds upon the principle of information bottleneck"},"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":"2405.09308","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-15T13:03:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c24799b981c35825be75daadd3980fdeb112b377f2e4028945e6ad720b4d6eab","abstract_canon_sha256":"69a2f3136f6eb61c9bb62cd0ba89673a2f6c7ce2f2c3bcc5bd6b395931d5c926"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:28.920140Z","signature_b64":"bHhAE1EyZO76FN6ihM5oeBJdpqPfhy83/hRuqDiEbG7y4FDmv+Op+fKYyl0U9jx7HsChm4fr+MOuSf8SxOsbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02f40474ac109f8ce39a6a017219c5e48b515acc68d39596a8dfd4c67843aebf","last_reissued_at":"2026-07-05T08:19:28.919624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:28.919624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TimeX++: Learning Time-Series Explanations with Information Bottleneck","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dongsheng Luo, Farhad Shirani, Jayantha Obeysekera, Jimeng Shi, Lei Song, Tianchun Wang, Wenqian Dong, Xu Zheng, Zhuomin Chen, Zichuan Liu","submitted_at":"2024-05-15T13:03:41Z","abstract_excerpt":"Explaining deep learning models operating on time series data is crucial in various applications of interest which require interpretable and transparent insights from time series signals. In this work, we investigate this problem from an information theoretic perspective and show that most existing measures of explainability may suffer from trivial solutions and distributional shift issues. To address these issues, we introduce a simple yet practical objective function for time series explainable learning. The design of the objective function builds upon the principle of information bottleneck"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.09308","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/2405.09308/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":"2405.09308","created_at":"2026-07-05T08:19:28.919694+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.09308v1","created_at":"2026-07-05T08:19:28.919694+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.09308","created_at":"2026-07-05T08:19:28.919694+00:00"},{"alias_kind":"pith_short_12","alias_value":"AL2AI5FMCCPY","created_at":"2026-07-05T08:19:28.919694+00:00"},{"alias_kind":"pith_short_16","alias_value":"AL2AI5FMCCPYZY42","created_at":"2026-07-05T08:19:28.919694+00:00"},{"alias_kind":"pith_short_8","alias_value":"AL2AI5FM","created_at":"2026-07-05T08:19:28.919694+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.23036","citing_title":"Delta-XAI: A Unified Framework for Explaining Prediction Changes in Online Time Series Monitoring","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AL2AI5FMCCPYZY42NIAXEGOF4S","json":"https://pith.science/pith/AL2AI5FMCCPYZY42NIAXEGOF4S.json","graph_json":"https://pith.science/api/pith-number/AL2AI5FMCCPYZY42NIAXEGOF4S/graph.json","events_json":"https://pith.science/api/pith-number/AL2AI5FMCCPYZY42NIAXEGOF4S/events.json","paper":"https://pith.science/paper/AL2AI5FM"},"agent_actions":{"view_html":"https://pith.science/pith/AL2AI5FMCCPYZY42NIAXEGOF4S","download_json":"https://pith.science/pith/AL2AI5FMCCPYZY42NIAXEGOF4S.json","view_paper":"https://pith.science/paper/AL2AI5FM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.09308&json=true","fetch_graph":"https://pith.science/api/pith-number/AL2AI5FMCCPYZY42NIAXEGOF4S/graph.json","fetch_events":"https://pith.science/api/pith-number/AL2AI5FMCCPYZY42NIAXEGOF4S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AL2AI5FMCCPYZY42NIAXEGOF4S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AL2AI5FMCCPYZY42NIAXEGOF4S/action/storage_attestation","attest_author":"https://pith.science/pith/AL2AI5FMCCPYZY42NIAXEGOF4S/action/author_attestation","sign_citation":"https://pith.science/pith/AL2AI5FMCCPYZY42NIAXEGOF4S/action/citation_signature","submit_replication":"https://pith.science/pith/AL2AI5FMCCPYZY42NIAXEGOF4S/action/replication_record"}},"created_at":"2026-07-05T08:19:28.919694+00:00","updated_at":"2026-07-05T08:19:28.919694+00:00"}