{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KCE35VGE3N7TR6KWUEYPGRBFPW","short_pith_number":"pith:KCE35VGE","schema_version":"1.0","canonical_sha256":"5089bed4c4db7f38f956a130f344257d8d7f07d3cb5c38143632c3ca0dedd703","source":{"kind":"arxiv","id":"1904.08935","version":3},"attestation_state":"computed","paper":{"title":"Explaining Deep Classification of Time-Series Data with Learned Prototypes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alan H. Gee, David Paydarfar, Diego Garcia-Olano, Joydeep Ghosh","submitted_at":"2019-04-18T07:14:45Z","abstract_excerpt":"The emergence of deep learning networks raises a need for explainable AI so that users and domain experts can be confident applying them to high-risk decisions. In this paper, we leverage data from the latent space induced by deep learning models to learn stereotypical representations or \"prototypes\" during training to elucidate the algorithmic decision-making process. We study how leveraging prototypes effect classification decisions of two dimensional time-series data in a few different settings: (1) electrocardiogram (ECG) waveforms to detect clinical bradycardia, a slowing of heart rate, i"},"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":"1904.08935","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-18T07:14:45Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8677dc0e8d22e7026c604277da39217ff1007e972177c79e8ea3ae46bcd3c233","abstract_canon_sha256":"f44df6d12e00c5b76632e6bd0b4f48f624ac066ab7d17f84d9cb20d6088235a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:58.194596Z","signature_b64":"SdeTPkBYD2wbjQO7ToF4BfA1Ahop1j9gITwBIMn/f7QT4Abzot4KicuqbiLck8+N9EGyj1qHdeqcTb8eh8RSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5089bed4c4db7f38f956a130f344257d8d7f07d3cb5c38143632c3ca0dedd703","last_reissued_at":"2026-07-05T00:02:58.194108Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:58.194108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explaining Deep Classification of Time-Series Data with Learned Prototypes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alan H. Gee, David Paydarfar, Diego Garcia-Olano, Joydeep Ghosh","submitted_at":"2019-04-18T07:14:45Z","abstract_excerpt":"The emergence of deep learning networks raises a need for explainable AI so that users and domain experts can be confident applying them to high-risk decisions. In this paper, we leverage data from the latent space induced by deep learning models to learn stereotypical representations or \"prototypes\" during training to elucidate the algorithmic decision-making process. We study how leveraging prototypes effect classification decisions of two dimensional time-series data in a few different settings: (1) electrocardiogram (ECG) waveforms to detect clinical bradycardia, a slowing of heart rate, i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.08935","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/1904.08935/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":"1904.08935","created_at":"2026-07-05T00:02:58.194167+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.08935v3","created_at":"2026-07-05T00:02:58.194167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.08935","created_at":"2026-07-05T00:02:58.194167+00:00"},{"alias_kind":"pith_short_12","alias_value":"KCE35VGE3N7T","created_at":"2026-07-05T00:02:58.194167+00:00"},{"alias_kind":"pith_short_16","alias_value":"KCE35VGE3N7TR6KW","created_at":"2026-07-05T00:02:58.194167+00:00"},{"alias_kind":"pith_short_8","alias_value":"KCE35VGE","created_at":"2026-07-05T00:02:58.194167+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2106.09636","citing_title":"Multi-Stage Prototype Learning for Interpretable Time Series Classification","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KCE35VGE3N7TR6KWUEYPGRBFPW","json":"https://pith.science/pith/KCE35VGE3N7TR6KWUEYPGRBFPW.json","graph_json":"https://pith.science/api/pith-number/KCE35VGE3N7TR6KWUEYPGRBFPW/graph.json","events_json":"https://pith.science/api/pith-number/KCE35VGE3N7TR6KWUEYPGRBFPW/events.json","paper":"https://pith.science/paper/KCE35VGE"},"agent_actions":{"view_html":"https://pith.science/pith/KCE35VGE3N7TR6KWUEYPGRBFPW","download_json":"https://pith.science/pith/KCE35VGE3N7TR6KWUEYPGRBFPW.json","view_paper":"https://pith.science/paper/KCE35VGE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.08935&json=true","fetch_graph":"https://pith.science/api/pith-number/KCE35VGE3N7TR6KWUEYPGRBFPW/graph.json","fetch_events":"https://pith.science/api/pith-number/KCE35VGE3N7TR6KWUEYPGRBFPW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KCE35VGE3N7TR6KWUEYPGRBFPW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KCE35VGE3N7TR6KWUEYPGRBFPW/action/storage_attestation","attest_author":"https://pith.science/pith/KCE35VGE3N7TR6KWUEYPGRBFPW/action/author_attestation","sign_citation":"https://pith.science/pith/KCE35VGE3N7TR6KWUEYPGRBFPW/action/citation_signature","submit_replication":"https://pith.science/pith/KCE35VGE3N7TR6KWUEYPGRBFPW/action/replication_record"}},"created_at":"2026-07-05T00:02:58.194167+00:00","updated_at":"2026-07-05T00:02:58.194167+00:00"}