{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KHLGLZURYEPZVPM7XOI65BNJE5","short_pith_number":"pith:KHLGLZUR","canonical_record":{"source":{"id":"2606.28460","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T13:04:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c626851746577202cb8daf45eaaeafda74134dabde6ad71e755e9fbe5f6da0a3","abstract_canon_sha256":"27485fd506056948c20036e00f585312001d5a9d76b698671e4078227a26d175"},"schema_version":"1.0"},"canonical_sha256":"51d665e691c11f9abd9fbb91ee85a9274673ab654481e82c2964d0cc9a8d0424","source":{"kind":"arxiv","id":"2606.28460","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.28460","created_at":"2026-06-30T00:15:14Z"},{"alias_kind":"arxiv_version","alias_value":"2606.28460v1","created_at":"2026-06-30T00:15:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28460","created_at":"2026-06-30T00:15:14Z"},{"alias_kind":"pith_short_12","alias_value":"KHLGLZURYEPZ","created_at":"2026-06-30T00:15:14Z"},{"alias_kind":"pith_short_16","alias_value":"KHLGLZURYEPZVPM7","created_at":"2026-06-30T00:15:14Z"},{"alias_kind":"pith_short_8","alias_value":"KHLGLZUR","created_at":"2026-06-30T00:15:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KHLGLZURYEPZVPM7XOI65BNJE5","target":"record","payload":{"canonical_record":{"source":{"id":"2606.28460","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T13:04:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c626851746577202cb8daf45eaaeafda74134dabde6ad71e755e9fbe5f6da0a3","abstract_canon_sha256":"27485fd506056948c20036e00f585312001d5a9d76b698671e4078227a26d175"},"schema_version":"1.0"},"canonical_sha256":"51d665e691c11f9abd9fbb91ee85a9274673ab654481e82c2964d0cc9a8d0424","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T00:15:14.871915Z","signature_b64":"/sDtCIdyEPffa20c4PcBpn5BH6Ur3ER8BQe6C1gNF7+wKkjyHMfVUDJU/Y8Zc16G/gUYZ79AaRMclDfteMVJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51d665e691c11f9abd9fbb91ee85a9274673ab654481e82c2964d0cc9a8d0424","last_reissued_at":"2026-06-30T00:15:14.870912Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T00:15:14.870912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.28460","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":"2026-06-30T00:15:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wumPDHed/5o+QDjZlEPSyaq9SXPRQh+In79Jl1IYAXkc9SSTpMUBRcABbAKFjUEhjIHp5xQ5om6JyweGQi9ZBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T04:08:06.747611Z"},"content_sha256":"9da5903d9f1f304d33f4e9ad622743ef5eb23c81fe1f91c4fab83348f623b8ad","schema_version":"1.0","event_id":"sha256:9da5903d9f1f304d33f4e9ad622743ef5eb23c81fe1f91c4fab83348f623b8ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KHLGLZURYEPZVPM7XOI65BNJE5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Counterfactual Residual Data Augmentation for Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hossein Mohebbi, Ke Li, Oliver Schulte, Pascal Poupart","submitted_at":"2026-06-26T13:04:37Z","abstract_excerpt":"Data-driven modeling in real-world regression tasks often suffers from limited training samples, high collection costs, and noisy observations. Inspired by the impact of data augmentation in vision and language, we propose a novel Counterfactual Residual Data Augmentation (CRDA) technique for tabular regression. Our key insight is that once a regressor has modeled the systematic component of the data, the remaining noise can be viewed as an invariant residual that remains stable under small perturbations of carefully selected features. We exploit this residual invariance to generate new, yet r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28460","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/2606.28460/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":"2026-06-30T00:15:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OEO/pxcyusZXac6XJI2IZYf2pUXL7PuBlm/9BSqzJHIAEaqFNLjW79Vk3qfBSnck8+XRNtPyR8NyfKrZhmwGDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T04:08:06.747984Z"},"content_sha256":"f54e2c2914f4ad43c29eae85430f3a6c5eb8fa05a6189eefdd88226574c6a777","schema_version":"1.0","event_id":"sha256:f54e2c2914f4ad43c29eae85430f3a6c5eb8fa05a6189eefdd88226574c6a777"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KHLGLZURYEPZVPM7XOI65BNJE5/bundle.json","state_url":"https://pith.science/pith/KHLGLZURYEPZVPM7XOI65BNJE5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KHLGLZURYEPZVPM7XOI65BNJE5/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":"2026-07-02T04:08:06Z","links":{"resolver":"https://pith.science/pith/KHLGLZURYEPZVPM7XOI65BNJE5","bundle":"https://pith.science/pith/KHLGLZURYEPZVPM7XOI65BNJE5/bundle.json","state":"https://pith.science/pith/KHLGLZURYEPZVPM7XOI65BNJE5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KHLGLZURYEPZVPM7XOI65BNJE5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KHLGLZURYEPZVPM7XOI65BNJE5","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":"27485fd506056948c20036e00f585312001d5a9d76b698671e4078227a26d175","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T13:04:37Z","title_canon_sha256":"c626851746577202cb8daf45eaaeafda74134dabde6ad71e755e9fbe5f6da0a3"},"schema_version":"1.0","source":{"id":"2606.28460","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.28460","created_at":"2026-06-30T00:15:14Z"},{"alias_kind":"arxiv_version","alias_value":"2606.28460v1","created_at":"2026-06-30T00:15:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28460","created_at":"2026-06-30T00:15:14Z"},{"alias_kind":"pith_short_12","alias_value":"KHLGLZURYEPZ","created_at":"2026-06-30T00:15:14Z"},{"alias_kind":"pith_short_16","alias_value":"KHLGLZURYEPZVPM7","created_at":"2026-06-30T00:15:14Z"},{"alias_kind":"pith_short_8","alias_value":"KHLGLZUR","created_at":"2026-06-30T00:15:14Z"}],"graph_snapshots":[{"event_id":"sha256:f54e2c2914f4ad43c29eae85430f3a6c5eb8fa05a6189eefdd88226574c6a777","target":"graph","created_at":"2026-06-30T00:15:14Z","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/2606.28460/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data-driven modeling in real-world regression tasks often suffers from limited training samples, high collection costs, and noisy observations. Inspired by the impact of data augmentation in vision and language, we propose a novel Counterfactual Residual Data Augmentation (CRDA) technique for tabular regression. Our key insight is that once a regressor has modeled the systematic component of the data, the remaining noise can be viewed as an invariant residual that remains stable under small perturbations of carefully selected features. We exploit this residual invariance to generate new, yet r","authors_text":"Hossein Mohebbi, Ke Li, Oliver Schulte, Pascal Poupart","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T13:04:37Z","title":"Counterfactual Residual Data Augmentation for Regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28460","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":"sha256:9da5903d9f1f304d33f4e9ad622743ef5eb23c81fe1f91c4fab83348f623b8ad","target":"record","created_at":"2026-06-30T00:15:14Z","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":"27485fd506056948c20036e00f585312001d5a9d76b698671e4078227a26d175","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T13:04:37Z","title_canon_sha256":"c626851746577202cb8daf45eaaeafda74134dabde6ad71e755e9fbe5f6da0a3"},"schema_version":"1.0","source":{"id":"2606.28460","kind":"arxiv","version":1}},"canonical_sha256":"51d665e691c11f9abd9fbb91ee85a9274673ab654481e82c2964d0cc9a8d0424","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51d665e691c11f9abd9fbb91ee85a9274673ab654481e82c2964d0cc9a8d0424","first_computed_at":"2026-06-30T00:15:14.870912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T00:15:14.870912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/sDtCIdyEPffa20c4PcBpn5BH6Ur3ER8BQe6C1gNF7+wKkjyHMfVUDJU/Y8Zc16G/gUYZ79AaRMclDfteMVJCA==","signature_status":"signed_v1","signed_at":"2026-06-30T00:15:14.871915Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.28460","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9da5903d9f1f304d33f4e9ad622743ef5eb23c81fe1f91c4fab83348f623b8ad","sha256:f54e2c2914f4ad43c29eae85430f3a6c5eb8fa05a6189eefdd88226574c6a777"],"state_sha256":"d4b9497a8bdbcf7db945a0c9324bb8cfd199dedf96b02c10323479b311f08f38"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rLD/60w3dW2Eme+2f6M/E0y1zx1ocQEhF0SDl7nMSy18P74T4UncHc+e8dE+OY+S3w4ofuqNf7FKL7I/nvQNDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T04:08:06.750308Z","bundle_sha256":"120b98ee23fb4b6349cd7ccf668a6d894c813fdad0b533436bf6c818f8618f9c"}}