{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RIIHRPHYIIOLA2PXR47LEFRGVV","short_pith_number":"pith:RIIHRPHY","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"},"canonical_sha256":"8a1078bcf8421cb069f78f3eb21626ad4e6dcb2196bd47252a2506fbaa1f1914","source":{"kind":"arxiv","id":"1801.00644","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RIIHRPHYIIOLA2PXR47LEFRGVV","target":"record","payload":{"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"},"canonical_sha256":"8a1078bcf8421cb069f78f3eb21626ad4e6dcb2196bd47252a2506fbaa1f1914","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"},"source_kind":"arxiv","source_id":"1801.00644","source_version":7,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wjdhGCqemuk9us7DH2yVD4l62+bQ4ySFFl5GswPIgsXkHeKWqo4crREG3Orm5nA+KhyNKBMI9vfyPo7lyl7qDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T07:23:41.218322Z"},"content_sha256":"aabadb1d6a00d8f2a257ee81a4adb3047983909c29becbac23c604d2c96ced47","schema_version":"1.0","event_id":"sha256:aabadb1d6a00d8f2a257ee81a4adb3047983909c29becbac23c604d2c96ced47"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RIIHRPHYIIOLA2PXR47LEFRGVV","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SknUDWYdKGUipiWiHT1mIepsmOUYsZvq0oznlSaq8upTzpbiaqg4fZPabD5Mf/LxXG4mQJJGJ0QMm2mTAyexDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T07:23:41.218685Z"},"content_sha256":"0c797f2c011d8301cbc3ada1c7222cc0f9260f810c8bdd3e0198a66df68d26ee","schema_version":"1.0","event_id":"sha256:0c797f2c011d8301cbc3ada1c7222cc0f9260f810c8bdd3e0198a66df68d26ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RIIHRPHYIIOLA2PXR47LEFRGVV/bundle.json","state_url":"https://pith.science/pith/RIIHRPHYIIOLA2PXR47LEFRGVV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RIIHRPHYIIOLA2PXR47LEFRGVV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-03T07:23:41Z","links":{"resolver":"https://pith.science/pith/RIIHRPHYIIOLA2PXR47LEFRGVV","bundle":"https://pith.science/pith/RIIHRPHYIIOLA2PXR47LEFRGVV/bundle.json","state":"https://pith.science/pith/RIIHRPHYIIOLA2PXR47LEFRGVV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RIIHRPHYIIOLA2PXR47LEFRGVV/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iHg+kuOcqaDGOUPk5y760e7LB7QSQoY+DWlSkPs+hiRhyuIyMwb/oRjwBNeWZpwFLNSz65MevE9aU7b6abB5Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T07:23:41.220831Z","bundle_sha256":"ccc9c3e220a6ec1658607b481cbf92feb8232737dbcb8693ea40054d04926213"}}