{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:STJDKA5PXPVFHXDPSA3YZFPO4F","short_pith_number":"pith:STJDKA5P","schema_version":"1.0","canonical_sha256":"94d23503afbbea53dc6f90378c95eee158f46d57be2262ed68a1178e6d679ea9","source":{"kind":"arxiv","id":"1907.08532","version":1},"attestation_state":"computed","paper":{"title":"Multi-Granular Text Encoding for Self-Explaining Categorization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Kun Xu, Linfeng Song, Lin Pan, Mo Yu, Wei Zhang, Yousef El-Kurdi, Yue Zhang, Zhiguo Wang","submitted_at":"2019-07-19T14:43:51Z","abstract_excerpt":"Self-explaining text categorization requires a classifier to make a prediction along with supporting evidence. A popular type of evidence is sub-sequences extracted from the input text which are sufficient for the classifier to make the prediction. In this work, we define multi-granular ngrams as basic units for explanation, and organize all ngrams into a hierarchical structure, so that shorter ngrams can be reused while computing longer ngrams. We leverage a tree-structured LSTM to learn a context-independent representation for each unit via parameter sharing. Experiments on medical disease c"},"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":"1907.08532","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-07-19T14:43:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0b0f6121b6b32315addfe3e9266a07838598464c2fdf4398adc618a950b03a81","abstract_canon_sha256":"885d95661ba2ace6b3dcbbff51ae3da20ec5cb848c8a4883bb01407bafbf3a8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:09.528937Z","signature_b64":"MuCP7NQ4WSRtgY4BWDanEck0dmhVOxRsE5jIFyigXa07c9vgWhggVCoAA/hrpqT1q56u0SPFKxJIQ4Em+kM3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94d23503afbbea53dc6f90378c95eee158f46d57be2262ed68a1178e6d679ea9","last_reissued_at":"2026-05-17T23:40:09.528206Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:09.528206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Granular Text Encoding for Self-Explaining Categorization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Kun Xu, Linfeng Song, Lin Pan, Mo Yu, Wei Zhang, Yousef El-Kurdi, Yue Zhang, Zhiguo Wang","submitted_at":"2019-07-19T14:43:51Z","abstract_excerpt":"Self-explaining text categorization requires a classifier to make a prediction along with supporting evidence. A popular type of evidence is sub-sequences extracted from the input text which are sufficient for the classifier to make the prediction. In this work, we define multi-granular ngrams as basic units for explanation, and organize all ngrams into a hierarchical structure, so that shorter ngrams can be reused while computing longer ngrams. We leverage a tree-structured LSTM to learn a context-independent representation for each unit via parameter sharing. Experiments on medical disease c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.08532","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":""},"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":"1907.08532","created_at":"2026-05-17T23:40:09.528333+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.08532v1","created_at":"2026-05-17T23:40:09.528333+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.08532","created_at":"2026-05-17T23:40:09.528333+00:00"},{"alias_kind":"pith_short_12","alias_value":"STJDKA5PXPVF","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"STJDKA5PXPVFHXDP","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"STJDKA5P","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/STJDKA5PXPVFHXDPSA3YZFPO4F","json":"https://pith.science/pith/STJDKA5PXPVFHXDPSA3YZFPO4F.json","graph_json":"https://pith.science/api/pith-number/STJDKA5PXPVFHXDPSA3YZFPO4F/graph.json","events_json":"https://pith.science/api/pith-number/STJDKA5PXPVFHXDPSA3YZFPO4F/events.json","paper":"https://pith.science/paper/STJDKA5P"},"agent_actions":{"view_html":"https://pith.science/pith/STJDKA5PXPVFHXDPSA3YZFPO4F","download_json":"https://pith.science/pith/STJDKA5PXPVFHXDPSA3YZFPO4F.json","view_paper":"https://pith.science/paper/STJDKA5P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.08532&json=true","fetch_graph":"https://pith.science/api/pith-number/STJDKA5PXPVFHXDPSA3YZFPO4F/graph.json","fetch_events":"https://pith.science/api/pith-number/STJDKA5PXPVFHXDPSA3YZFPO4F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/STJDKA5PXPVFHXDPSA3YZFPO4F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/STJDKA5PXPVFHXDPSA3YZFPO4F/action/storage_attestation","attest_author":"https://pith.science/pith/STJDKA5PXPVFHXDPSA3YZFPO4F/action/author_attestation","sign_citation":"https://pith.science/pith/STJDKA5PXPVFHXDPSA3YZFPO4F/action/citation_signature","submit_replication":"https://pith.science/pith/STJDKA5PXPVFHXDPSA3YZFPO4F/action/replication_record"}},"created_at":"2026-05-17T23:40:09.528333+00:00","updated_at":"2026-05-17T23:40:09.528333+00:00"}