{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:NSENP4KPKF3Y63MMZPIQEIKJPB","short_pith_number":"pith:NSENP4KP","schema_version":"1.0","canonical_sha256":"6c88d7f14f51778f6d8ccbd1022149787c41867af32973aa7586bab61d3fbe39","source":{"kind":"arxiv","id":"1612.07843","version":1},"attestation_state":"computed","paper":{"title":"\"What is Relevant in a Text Document?\": An Interpretable Machine Learning Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Franziska Horn, Gr\\'egoire Montavon, Klaus-Robert M\\\"uller, Leila Arras, Wojciech Samek","submitted_at":"2016-12-23T00:31:30Z","abstract_excerpt":"Text documents can be described by a number of abstract concepts such as semantic category, writing style, or sentiment. Machine learning (ML) models have been trained to automatically map documents to these abstract concepts, allowing to annotate very large text collections, more than could be processed by a human in a lifetime. Besides predicting the text's category very accurately, it is also highly desirable to understand how and why the categorization process takes place. In this paper, we demonstrate that such understanding can be achieved by tracing the classification decision back to 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":"1612.07843","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-23T00:31:30Z","cross_cats_sorted":["cs.IR","cs.LG","stat.ML"],"title_canon_sha256":"8acdd25f84464d4ba9e33d7f069658a2c55240b56c05617fc4906d84a053d8b3","abstract_canon_sha256":"7ed84bd2eec01de80eb22679dff06d799aa2e9cd65f96a984cb976ac009d5bb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:41.815730Z","signature_b64":"pl0J370TNLvo05iDCpiPEMWqqxtBFIETDAmyFqR6ro/vBa5/qBZtcNbLaBdVN+XklK/MPwwMLVhbzPARnXBKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c88d7f14f51778f6d8ccbd1022149787c41867af32973aa7586bab61d3fbe39","last_reissued_at":"2026-05-18T00:31:41.815332Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:41.815332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"\"What is Relevant in a Text Document?\": An Interpretable Machine Learning Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Franziska Horn, Gr\\'egoire Montavon, Klaus-Robert M\\\"uller, Leila Arras, Wojciech Samek","submitted_at":"2016-12-23T00:31:30Z","abstract_excerpt":"Text documents can be described by a number of abstract concepts such as semantic category, writing style, or sentiment. Machine learning (ML) models have been trained to automatically map documents to these abstract concepts, allowing to annotate very large text collections, more than could be processed by a human in a lifetime. Besides predicting the text's category very accurately, it is also highly desirable to understand how and why the categorization process takes place. In this paper, we demonstrate that such understanding can be achieved by tracing the classification decision back to i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.07843","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":"1612.07843","created_at":"2026-05-18T00:31:41.815395+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.07843v1","created_at":"2026-05-18T00:31:41.815395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.07843","created_at":"2026-05-18T00:31:41.815395+00:00"},{"alias_kind":"pith_short_12","alias_value":"NSENP4KPKF3Y","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_16","alias_value":"NSENP4KPKF3Y63MM","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_8","alias_value":"NSENP4KP","created_at":"2026-05-18T12:30:36.002864+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/NSENP4KPKF3Y63MMZPIQEIKJPB","json":"https://pith.science/pith/NSENP4KPKF3Y63MMZPIQEIKJPB.json","graph_json":"https://pith.science/api/pith-number/NSENP4KPKF3Y63MMZPIQEIKJPB/graph.json","events_json":"https://pith.science/api/pith-number/NSENP4KPKF3Y63MMZPIQEIKJPB/events.json","paper":"https://pith.science/paper/NSENP4KP"},"agent_actions":{"view_html":"https://pith.science/pith/NSENP4KPKF3Y63MMZPIQEIKJPB","download_json":"https://pith.science/pith/NSENP4KPKF3Y63MMZPIQEIKJPB.json","view_paper":"https://pith.science/paper/NSENP4KP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.07843&json=true","fetch_graph":"https://pith.science/api/pith-number/NSENP4KPKF3Y63MMZPIQEIKJPB/graph.json","fetch_events":"https://pith.science/api/pith-number/NSENP4KPKF3Y63MMZPIQEIKJPB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NSENP4KPKF3Y63MMZPIQEIKJPB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NSENP4KPKF3Y63MMZPIQEIKJPB/action/storage_attestation","attest_author":"https://pith.science/pith/NSENP4KPKF3Y63MMZPIQEIKJPB/action/author_attestation","sign_citation":"https://pith.science/pith/NSENP4KPKF3Y63MMZPIQEIKJPB/action/citation_signature","submit_replication":"https://pith.science/pith/NSENP4KPKF3Y63MMZPIQEIKJPB/action/replication_record"}},"created_at":"2026-05-18T00:31:41.815395+00:00","updated_at":"2026-05-18T00:31:41.815395+00:00"}