{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RIIHRPHYIIOLA2PXR47LEFRGVV","short_pith_number":"pith:RIIHRPHY","schema_version":"1.0","canonical_sha256":"8a1078bcf8421cb069f78f3eb21626ad4e6dcb2196bd47252a2506fbaa1f1914","source":{"kind":"arxiv","id":"1801.00644","version":7},"attestation_state":"computed","paper":{"title":"Matching with Text Data: An Experimental Evaluation of Methods for Matching Documents and of Measuring Match Quality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"stat.ME","authors_text":"Aaron Russell Kaufman, L. Jason Anastasopoulos, Luke Miratrix, Reagan Mozer","submitted_at":"2018-01-02T13:47:43Z","abstract_excerpt":"Matching for causal inference is a well-studied problem, but standard methods fail when the units to match are text documents: the high-dimensional and rich nature of the data renders exact matching infeasible, causes propensity scores to produce incomparable matches, and makes assessing match quality difficult. In this paper, we characterize a framework for matching text documents that decomposes existing methods into: (1) the choice of text representation, and (2) the choice of distance metric. We investigate how different choices within this framework affect both the quantity and quality of"},"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":"1801.00644","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2018-01-02T13:47:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c187446ba782179b033b14a47e4b7415e6d928c61c9f54b70304ef065405dc17","abstract_canon_sha256":"29e4fa29f65818f5ce69b3f948c5c769122741c964814cd328602a61b835ac32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:19.975561Z","signature_b64":"INHVitgKEI4H3EdQ2+JeJCIhlSZVlNDoOF13I89bF3Awnhxm/pIvyNWxVGM/Z8L7nNtDxB521T/oj73l1SSyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a1078bcf8421cb069f78f3eb21626ad4e6dcb2196bd47252a2506fbaa1f1914","last_reissued_at":"2026-05-17T23:51:19.974832Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:19.974832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Matching with Text Data: An Experimental Evaluation of Methods for Matching Documents and of Measuring Match Quality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"stat.ME","authors_text":"Aaron Russell Kaufman, L. Jason Anastasopoulos, Luke Miratrix, Reagan Mozer","submitted_at":"2018-01-02T13:47:43Z","abstract_excerpt":"Matching for causal inference is a well-studied problem, but standard methods fail when the units to match are text documents: the high-dimensional and rich nature of the data renders exact matching infeasible, causes propensity scores to produce incomparable matches, and makes assessing match quality difficult. In this paper, we characterize a framework for matching text documents that decomposes existing methods into: (1) the choice of text representation, and (2) the choice of distance metric. We investigate how different choices within this framework affect both the quantity and quality of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.00644","kind":"arxiv","version":7},"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":"1801.00644","created_at":"2026-05-17T23:51:19.974923+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.00644v7","created_at":"2026-05-17T23:51:19.974923+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.00644","created_at":"2026-05-17T23:51:19.974923+00:00"},{"alias_kind":"pith_short_12","alias_value":"RIIHRPHYIIOL","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RIIHRPHYIIOLA2PX","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RIIHRPHY","created_at":"2026-05-18T12:32:50.500415+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/RIIHRPHYIIOLA2PXR47LEFRGVV","json":"https://pith.science/pith/RIIHRPHYIIOLA2PXR47LEFRGVV.json","graph_json":"https://pith.science/api/pith-number/RIIHRPHYIIOLA2PXR47LEFRGVV/graph.json","events_json":"https://pith.science/api/pith-number/RIIHRPHYIIOLA2PXR47LEFRGVV/events.json","paper":"https://pith.science/paper/RIIHRPHY"},"agent_actions":{"view_html":"https://pith.science/pith/RIIHRPHYIIOLA2PXR47LEFRGVV","download_json":"https://pith.science/pith/RIIHRPHYIIOLA2PXR47LEFRGVV.json","view_paper":"https://pith.science/paper/RIIHRPHY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.00644&json=true","fetch_graph":"https://pith.science/api/pith-number/RIIHRPHYIIOLA2PXR47LEFRGVV/graph.json","fetch_events":"https://pith.science/api/pith-number/RIIHRPHYIIOLA2PXR47LEFRGVV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RIIHRPHYIIOLA2PXR47LEFRGVV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RIIHRPHYIIOLA2PXR47LEFRGVV/action/storage_attestation","attest_author":"https://pith.science/pith/RIIHRPHYIIOLA2PXR47LEFRGVV/action/author_attestation","sign_citation":"https://pith.science/pith/RIIHRPHYIIOLA2PXR47LEFRGVV/action/citation_signature","submit_replication":"https://pith.science/pith/RIIHRPHYIIOLA2PXR47LEFRGVV/action/replication_record"}},"created_at":"2026-05-17T23:51:19.974923+00:00","updated_at":"2026-05-17T23:51:19.974923+00:00"}