{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RIIHRPHYIIOLA2PXR47LEFRGVV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"29e4fa29f65818f5ce69b3f948c5c769122741c964814cd328602a61b835ac32","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2018-01-02T13:47:43Z","title_canon_sha256":"c187446ba782179b033b14a47e4b7415e6d928c61c9f54b70304ef065405dc17"},"schema_version":"1.0","source":{"id":"1801.00644","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.00644","created_at":"2026-05-17T23:51:19Z"},{"alias_kind":"arxiv_version","alias_value":"1801.00644v7","created_at":"2026-05-17T23:51:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.00644","created_at":"2026-05-17T23:51:19Z"},{"alias_kind":"pith_short_12","alias_value":"RIIHRPHYIIOL","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RIIHRPHYIIOLA2PX","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RIIHRPHY","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:0c797f2c011d8301cbc3ada1c7222cc0f9260f810c8bdd3e0198a66df68d26ee","target":"graph","created_at":"2026-05-17T23:51:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Aaron Russell Kaufman, L. Jason Anastasopoulos, Luke Miratrix, Reagan Mozer","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2018-01-02T13:47:43Z","title":"Matching with Text Data: An Experimental Evaluation of Methods for Matching Documents and of Measuring Match Quality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.00644","kind":"arxiv","version":7},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:aabadb1d6a00d8f2a257ee81a4adb3047983909c29becbac23c604d2c96ced47","target":"record","created_at":"2026-05-17T23:51:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"29e4fa29f65818f5ce69b3f948c5c769122741c964814cd328602a61b835ac32","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2018-01-02T13:47:43Z","title_canon_sha256":"c187446ba782179b033b14a47e4b7415e6d928c61c9f54b70304ef065405dc17"},"schema_version":"1.0","source":{"id":"1801.00644","kind":"arxiv","version":7}},"canonical_sha256":"8a1078bcf8421cb069f78f3eb21626ad4e6dcb2196bd47252a2506fbaa1f1914","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a1078bcf8421cb069f78f3eb21626ad4e6dcb2196bd47252a2506fbaa1f1914","first_computed_at":"2026-05-17T23:51:19.974832Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:19.974832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"INHVitgKEI4H3EdQ2+JeJCIhlSZVlNDoOF13I89bF3Awnhxm/pIvyNWxVGM/Z8L7nNtDxB521T/oj73l1SSyBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:19.975561Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.00644","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aabadb1d6a00d8f2a257ee81a4adb3047983909c29becbac23c604d2c96ced47","sha256:0c797f2c011d8301cbc3ada1c7222cc0f9260f810c8bdd3e0198a66df68d26ee"],"state_sha256":"29b52938830fbb22c5d941ea0cc1fe66f43e1fa4193fc97986f9c2870b375269"}