{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:JSFRPO35HWYPEMSMYSIQ2RAWVP","short_pith_number":"pith:JSFRPO35","schema_version":"1.0","canonical_sha256":"4c8b17bb7d3db0f2324cc4910d4416abd414de8739067f27a23a6b605a6ec6b5","source":{"kind":"arxiv","id":"2012.07565","version":1},"attestation_state":"computed","paper":{"title":"Automating Document Classification with Distant Supervision to Increase the Efficiency of Systematic Reviews","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Amy Zhang, C. Lee Giles, Le Bao, Rabah Al-Zaidy, Stefan Baral, Xiaoxiao Li","submitted_at":"2020-12-09T22:45:40Z","abstract_excerpt":"Objective: Systematic reviews of scholarly documents often provide complete and exhaustive summaries of literature relevant to a research question. However, well-done systematic reviews are expensive, time-demanding, and labor-intensive. Here, we propose an automatic document classification approach to significantly reduce the effort in reviewing documents. Methods: We first describe a manual document classification procedure that is used to curate a pertinent training dataset and then propose three classifiers: a keyword-guided method, a cluster analysis-based refined method, and a random for"},"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":"2012.07565","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-09T22:45:40Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"e6de7504c865b290eebff19d2d0d4d933a2f28163615c2cc70d425a310e3a1b3","abstract_canon_sha256":"28d24cf3f1f1ad27a9a739c3f63a7fe455c80dd8d7050ea9cc8a68d21fb57a11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:59:22.010232Z","signature_b64":"Xe5ARmWw6aC0zxiC89z5ojmDZ1KMP/SGR/b6QUy8CGjUB4csmgiTJe20f3hBbAbzNM2PFrlJ4sIikP8BURcUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c8b17bb7d3db0f2324cc4910d4416abd414de8739067f27a23a6b605a6ec6b5","last_reissued_at":"2026-07-05T01:59:22.009843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:59:22.009843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automating Document Classification with Distant Supervision to Increase the Efficiency of Systematic Reviews","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Amy Zhang, C. Lee Giles, Le Bao, Rabah Al-Zaidy, Stefan Baral, Xiaoxiao Li","submitted_at":"2020-12-09T22:45:40Z","abstract_excerpt":"Objective: Systematic reviews of scholarly documents often provide complete and exhaustive summaries of literature relevant to a research question. However, well-done systematic reviews are expensive, time-demanding, and labor-intensive. Here, we propose an automatic document classification approach to significantly reduce the effort in reviewing documents. Methods: We first describe a manual document classification procedure that is used to curate a pertinent training dataset and then propose three classifiers: a keyword-guided method, a cluster analysis-based refined method, and a random for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.07565","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/2012.07565/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":"2012.07565","created_at":"2026-07-05T01:59:22.009898+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.07565v1","created_at":"2026-07-05T01:59:22.009898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.07565","created_at":"2026-07-05T01:59:22.009898+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSFRPO35HWYP","created_at":"2026-07-05T01:59:22.009898+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSFRPO35HWYPEMSM","created_at":"2026-07-05T01:59:22.009898+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSFRPO35","created_at":"2026-07-05T01:59:22.009898+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/JSFRPO35HWYPEMSMYSIQ2RAWVP","json":"https://pith.science/pith/JSFRPO35HWYPEMSMYSIQ2RAWVP.json","graph_json":"https://pith.science/api/pith-number/JSFRPO35HWYPEMSMYSIQ2RAWVP/graph.json","events_json":"https://pith.science/api/pith-number/JSFRPO35HWYPEMSMYSIQ2RAWVP/events.json","paper":"https://pith.science/paper/JSFRPO35"},"agent_actions":{"view_html":"https://pith.science/pith/JSFRPO35HWYPEMSMYSIQ2RAWVP","download_json":"https://pith.science/pith/JSFRPO35HWYPEMSMYSIQ2RAWVP.json","view_paper":"https://pith.science/paper/JSFRPO35","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.07565&json=true","fetch_graph":"https://pith.science/api/pith-number/JSFRPO35HWYPEMSMYSIQ2RAWVP/graph.json","fetch_events":"https://pith.science/api/pith-number/JSFRPO35HWYPEMSMYSIQ2RAWVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSFRPO35HWYPEMSMYSIQ2RAWVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSFRPO35HWYPEMSMYSIQ2RAWVP/action/storage_attestation","attest_author":"https://pith.science/pith/JSFRPO35HWYPEMSMYSIQ2RAWVP/action/author_attestation","sign_citation":"https://pith.science/pith/JSFRPO35HWYPEMSMYSIQ2RAWVP/action/citation_signature","submit_replication":"https://pith.science/pith/JSFRPO35HWYPEMSMYSIQ2RAWVP/action/replication_record"}},"created_at":"2026-07-05T01:59:22.009898+00:00","updated_at":"2026-07-05T01:59:22.009898+00:00"}