{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:3A26FQA4LDTWCWIWZ5EOI7B4RA","short_pith_number":"pith:3A26FQA4","schema_version":"1.0","canonical_sha256":"d835e2c01c58e7615916cf48e47c3c881e7f23a606324673930b549718b37042","source":{"kind":"arxiv","id":"1707.03217","version":1},"attestation_state":"computed","paper":{"title":"Document Retrieval for Large Scale Content Analysis using Contextualized Dictionaries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Andreas Niekler, Gregor Wiedemann","submitted_at":"2017-07-11T11:00:44Z","abstract_excerpt":"This paper presents a procedure to retrieve subsets of relevant documents from large text collections for Content Analysis, e.g. in social sciences. Document retrieval for this purpose needs to take account of the fact that analysts often cannot describe their research objective with a small set of key terms, especially when dealing with theoretical or rather abstract research interests. Instead, it is much easier to define a set of paradigmatic documents which reflect topics of interest as well as targeted manner of speech. Thus, in contrast to classic information retrieval tasks we employ ma"},"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":"1707.03217","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-07-11T11:00:44Z","cross_cats_sorted":[],"title_canon_sha256":"fdbfa83260823b3b65f919ab571ca2b98318484148eba64bc6f6c49cd85fc077","abstract_canon_sha256":"3d8f36ad6c3a5768b7bc491e8d4dc576db7e4ffd3f665de7f1d1ce3ff4f28cfe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:29.555333Z","signature_b64":"D4RnNLcU7111DDOaUwsah7im0wZrmjfUTKgcwdFuPToGj03enewcUs9UcBcBNVdlQ5UmcCBLkTxHgZUTIPBICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d835e2c01c58e7615916cf48e47c3c881e7f23a606324673930b549718b37042","last_reissued_at":"2026-05-18T00:40:29.554790Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:29.554790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Document Retrieval for Large Scale Content Analysis using Contextualized Dictionaries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Andreas Niekler, Gregor Wiedemann","submitted_at":"2017-07-11T11:00:44Z","abstract_excerpt":"This paper presents a procedure to retrieve subsets of relevant documents from large text collections for Content Analysis, e.g. in social sciences. Document retrieval for this purpose needs to take account of the fact that analysts often cannot describe their research objective with a small set of key terms, especially when dealing with theoretical or rather abstract research interests. Instead, it is much easier to define a set of paradigmatic documents which reflect topics of interest as well as targeted manner of speech. Thus, in contrast to classic information retrieval tasks we employ ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.03217","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":"1707.03217","created_at":"2026-05-18T00:40:29.554889+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.03217v1","created_at":"2026-05-18T00:40:29.554889+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.03217","created_at":"2026-05-18T00:40:29.554889+00:00"},{"alias_kind":"pith_short_12","alias_value":"3A26FQA4LDTW","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"3A26FQA4LDTWCWIW","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"3A26FQA4","created_at":"2026-05-18T12:30:58.224056+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/3A26FQA4LDTWCWIWZ5EOI7B4RA","json":"https://pith.science/pith/3A26FQA4LDTWCWIWZ5EOI7B4RA.json","graph_json":"https://pith.science/api/pith-number/3A26FQA4LDTWCWIWZ5EOI7B4RA/graph.json","events_json":"https://pith.science/api/pith-number/3A26FQA4LDTWCWIWZ5EOI7B4RA/events.json","paper":"https://pith.science/paper/3A26FQA4"},"agent_actions":{"view_html":"https://pith.science/pith/3A26FQA4LDTWCWIWZ5EOI7B4RA","download_json":"https://pith.science/pith/3A26FQA4LDTWCWIWZ5EOI7B4RA.json","view_paper":"https://pith.science/paper/3A26FQA4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.03217&json=true","fetch_graph":"https://pith.science/api/pith-number/3A26FQA4LDTWCWIWZ5EOI7B4RA/graph.json","fetch_events":"https://pith.science/api/pith-number/3A26FQA4LDTWCWIWZ5EOI7B4RA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3A26FQA4LDTWCWIWZ5EOI7B4RA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3A26FQA4LDTWCWIWZ5EOI7B4RA/action/storage_attestation","attest_author":"https://pith.science/pith/3A26FQA4LDTWCWIWZ5EOI7B4RA/action/author_attestation","sign_citation":"https://pith.science/pith/3A26FQA4LDTWCWIWZ5EOI7B4RA/action/citation_signature","submit_replication":"https://pith.science/pith/3A26FQA4LDTWCWIWZ5EOI7B4RA/action/replication_record"}},"created_at":"2026-05-18T00:40:29.554889+00:00","updated_at":"2026-05-18T00:40:29.554889+00:00"}