{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PGSZC4K3BA2NBT4XYOXF7Z7JMT","short_pith_number":"pith:PGSZC4K3","canonical_record":{"source":{"id":"2607.26309","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-07-28T22:10:43Z","cross_cats_sorted":["cs.CL","stat.AP","stat.ML"],"title_canon_sha256":"4bf6c689929772f053b49c51113b2f28f2e6ef3f6e8a352afb78dc66a26ba69a","abstract_canon_sha256":"094c3817859499ceac9e45888989004daafe7cafcc94bbfb74c4e1fd74592433"},"schema_version":"1.0"},"canonical_sha256":"79a591715b0834d0cf97c3ae5fe7e964e65d225201a6c254225ec7d0115bd294","source":{"kind":"arxiv","id":"2607.26309","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26309","created_at":"2026-07-30T01:17:58Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26309v1","created_at":"2026-07-30T01:17:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26309","created_at":"2026-07-30T01:17:58Z"},{"alias_kind":"pith_short_12","alias_value":"PGSZC4K3BA2N","created_at":"2026-07-30T01:17:58Z"},{"alias_kind":"pith_short_16","alias_value":"PGSZC4K3BA2NBT4X","created_at":"2026-07-30T01:17:58Z"},{"alias_kind":"pith_short_8","alias_value":"PGSZC4K3","created_at":"2026-07-30T01:17:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PGSZC4K3BA2NBT4XYOXF7Z7JMT","target":"record","payload":{"canonical_record":{"source":{"id":"2607.26309","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-07-28T22:10:43Z","cross_cats_sorted":["cs.CL","stat.AP","stat.ML"],"title_canon_sha256":"4bf6c689929772f053b49c51113b2f28f2e6ef3f6e8a352afb78dc66a26ba69a","abstract_canon_sha256":"094c3817859499ceac9e45888989004daafe7cafcc94bbfb74c4e1fd74592433"},"schema_version":"1.0"},"canonical_sha256":"79a591715b0834d0cf97c3ae5fe7e964e65d225201a6c254225ec7d0115bd294","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79a591715b0834d0cf97c3ae5fe7e964e65d225201a6c254225ec7d0115bd294","last_reissued_at":"2026-07-30T01:17:58.865756Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:17:58.865756Z"},"source_kind":"arxiv","source_id":"2607.26309","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-30T01:17:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Z9hzVeslEVaDRDTfu2btRjFglmx+5AwkoX3NCs58GdHyGd090nhKu+ycp0hgq7n4zwv9dcEr/Z97ijPpZQFBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:46:19.256568Z"},"content_sha256":"7a2f76e2394bc3e9e306a48eced6f24ab605209d617023bf702eff3e94473b35","schema_version":"1.0","event_id":"sha256:7a2f76e2394bc3e9e306a48eced6f24ab605209d617023bf702eff3e94473b35"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PGSZC4K3BA2NBT4XYOXF7Z7JMT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Confounder Trap: Treatment-Encoding Representations in Causal Inference with Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.AP","stat.ML"],"primary_cat":"stat.ME","authors_text":"Alexander Volfovsky, Graham Tierney, Marie Neubrander","submitted_at":"2026-07-28T22:10:43Z","abstract_excerpt":"Estimating causal effects of linguistic properties from observational text is difficult because the same document can contain both the treatment of interest and the non-treatment textual attributes needed for adjustment. Existing approaches often learn representations from the full text to capture latent confounding, but when treatment status is itself encoded by words in the text, these representations can directly encode treatment. This creates a confounder trap: richer representations can make treated and control documents separable, inducing overlap violations even when the underlying caus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26309","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/2607.26309/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-30T01:17:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GGcniJiOtzyPJfCG7DfT0uVLK2xYblQA8puIN0lh/UjlcEIPemo9qzevCTbok2Y4y906irdUQbf1voYNdcDkBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:46:19.257083Z"},"content_sha256":"07760df4cec4a46762615452b61df9da739c574b88ed841d15d75e0441aafa41","schema_version":"1.0","event_id":"sha256:07760df4cec4a46762615452b61df9da739c574b88ed841d15d75e0441aafa41"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PGSZC4K3BA2NBT4XYOXF7Z7JMT/bundle.json","state_url":"https://pith.science/pith/PGSZC4K3BA2NBT4XYOXF7Z7JMT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PGSZC4K3BA2NBT4XYOXF7Z7JMT/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":"2026-08-09T00:46:19Z","links":{"resolver":"https://pith.science/pith/PGSZC4K3BA2NBT4XYOXF7Z7JMT","bundle":"https://pith.science/pith/PGSZC4K3BA2NBT4XYOXF7Z7JMT/bundle.json","state":"https://pith.science/pith/PGSZC4K3BA2NBT4XYOXF7Z7JMT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PGSZC4K3BA2NBT4XYOXF7Z7JMT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PGSZC4K3BA2NBT4XYOXF7Z7JMT","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":"094c3817859499ceac9e45888989004daafe7cafcc94bbfb74c4e1fd74592433","cross_cats_sorted":["cs.CL","stat.AP","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-07-28T22:10:43Z","title_canon_sha256":"4bf6c689929772f053b49c51113b2f28f2e6ef3f6e8a352afb78dc66a26ba69a"},"schema_version":"1.0","source":{"id":"2607.26309","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26309","created_at":"2026-07-30T01:17:58Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26309v1","created_at":"2026-07-30T01:17:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26309","created_at":"2026-07-30T01:17:58Z"},{"alias_kind":"pith_short_12","alias_value":"PGSZC4K3BA2N","created_at":"2026-07-30T01:17:58Z"},{"alias_kind":"pith_short_16","alias_value":"PGSZC4K3BA2NBT4X","created_at":"2026-07-30T01:17:58Z"},{"alias_kind":"pith_short_8","alias_value":"PGSZC4K3","created_at":"2026-07-30T01:17:58Z"}],"graph_snapshots":[{"event_id":"sha256:07760df4cec4a46762615452b61df9da739c574b88ed841d15d75e0441aafa41","target":"graph","created_at":"2026-07-30T01:17:58Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.26309/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Estimating causal effects of linguistic properties from observational text is difficult because the same document can contain both the treatment of interest and the non-treatment textual attributes needed for adjustment. Existing approaches often learn representations from the full text to capture latent confounding, but when treatment status is itself encoded by words in the text, these representations can directly encode treatment. This creates a confounder trap: richer representations can make treated and control documents separable, inducing overlap violations even when the underlying caus","authors_text":"Alexander Volfovsky, Graham Tierney, Marie Neubrander","cross_cats":["cs.CL","stat.AP","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-07-28T22:10:43Z","title":"The Confounder Trap: Treatment-Encoding Representations in Causal Inference with Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26309","kind":"arxiv","version":1},"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":"sha256:7a2f76e2394bc3e9e306a48eced6f24ab605209d617023bf702eff3e94473b35","target":"record","created_at":"2026-07-30T01:17:58Z","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":"094c3817859499ceac9e45888989004daafe7cafcc94bbfb74c4e1fd74592433","cross_cats_sorted":["cs.CL","stat.AP","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-07-28T22:10:43Z","title_canon_sha256":"4bf6c689929772f053b49c51113b2f28f2e6ef3f6e8a352afb78dc66a26ba69a"},"schema_version":"1.0","source":{"id":"2607.26309","kind":"arxiv","version":1}},"canonical_sha256":"79a591715b0834d0cf97c3ae5fe7e964e65d225201a6c254225ec7d0115bd294","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79a591715b0834d0cf97c3ae5fe7e964e65d225201a6c254225ec7d0115bd294","first_computed_at":"2026-07-30T01:17:58.865756Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:17:58.865756Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.26309","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a2f76e2394bc3e9e306a48eced6f24ab605209d617023bf702eff3e94473b35","sha256:07760df4cec4a46762615452b61df9da739c574b88ed841d15d75e0441aafa41"],"state_sha256":"7b3da96916b30334cd0ce8b2df1e0e76e1aaf168ffcff300a9d8e655638ec9e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TlFTUB5uvvMYEXJzF1SzTvDaG5R5MEddXeX8XZj6EoHzXb63pLNuDKxZjM8QXnNlg60dQZa9E7PHHs3ScppxDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:46:19.261072Z","bundle_sha256":"208f398d94124487327804a11e8b4c7e67bff4ac2c2e183d955154d9e8a03b9d"}}