{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MR7OAPQB5UGBHODDHWH7QW4U7C","short_pith_number":"pith:MR7OAPQB","canonical_record":{"source":{"id":"2605.14280","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T02:26:34Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"cab922bc611b9364badeda283d335b82f4bc07a37a4e2d18c0fbea8f69c9ac6f","abstract_canon_sha256":"08bcddc4dbe97e64f2c3caa4af0c30f64d44d1fe03b4f481470ccb67f120162f"},"schema_version":"1.0"},"canonical_sha256":"647ee03e01ed0c13b8633d8ff85b94f8a54a93512fd1332897b48317b2e2dc02","source":{"kind":"arxiv","id":"2605.14280","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14280","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14280v1","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14280","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"pith_short_12","alias_value":"MR7OAPQB5UGB","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"MR7OAPQB5UGBHODD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"MR7OAPQB","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MR7OAPQB5UGBHODDHWH7QW4U7C","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14280","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T02:26:34Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"cab922bc611b9364badeda283d335b82f4bc07a37a4e2d18c0fbea8f69c9ac6f","abstract_canon_sha256":"08bcddc4dbe97e64f2c3caa4af0c30f64d44d1fe03b4f481470ccb67f120162f"},"schema_version":"1.0"},"canonical_sha256":"647ee03e01ed0c13b8633d8ff85b94f8a54a93512fd1332897b48317b2e2dc02","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:10.297227Z","signature_b64":"70uptICrleMsHZ29PPcCxgQ1hB9OCPEklof4icUI0XaOZ49KL8aQLd5yukugEkTkOuI68J5I665wLinIimBPCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"647ee03e01ed0c13b8633d8ff85b94f8a54a93512fd1332897b48317b2e2dc02","last_reissued_at":"2026-05-17T23:39:10.296601Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:10.296601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14280","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":"2026-05-17T23:39:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZwoInIl/huS/0FKx/ZXPXvbOSR5uYp2KjprjOhlzDR3xktVp7HtevohLlxkSTRgWDujN0QMld27QwYnxOV+bAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T18:13:06.717902Z"},"content_sha256":"8628a3fc403ef19881c5a2d6005d165372d9c1cd578c5c8564e12a1b778d38e2","schema_version":"1.0","event_id":"sha256:8628a3fc403ef19881c5a2d6005d165372d9c1cd578c5c8564e12a1b778d38e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MR7OAPQB5UGBHODDHWH7QW4U7C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TILT: Target-induced loss tilting under covariate shift","license":"http://creativecommons.org/licenses/by/4.0/","headline":"The target-side penalty on an auxiliary predictor component induces implicit relative importance weighting that stays bounded even with disjoint supports.","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kakei Yamamoto, Martin J. Wainwright","submitted_at":"2026-05-14T02:26:34Z","abstract_excerpt":"We introduce and analyze Target-Induced Loss Tilting (TILT) for unsupervised domain adaptation under covariate shift. It is based on a novel objective function that decomposes the source predictor as $f+b$, fits $f+b$ on labeled source data while simultaneously penalizing the auxiliary component $b$ on unlabeled target inputs. The resulting fit $f$ is deployed as the final target predictor. At the population level, we show that this target-side penalty implicitly induces relative importance weighting at the population level, but in terms of an estimand $b^*_f$ that is self-localized to the cur"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"At the population level, the target-side penalty on b implicitly induces relative importance weighting in terms of an estimand b*_f that is self-localized to the current error and remains uniformly bounded for any source-target pair, even those with disjoint supports; a general finite-sample oracle inequality holds and yields an end-to-end guarantee for sparse ReLU networks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The analysis assumes the existence of a decomposition f + b where the penalty on b on target data produces a useful weighting without requiring the supports of source and target to overlap or any explicit density estimation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"TILT adds a target-data penalty on an auxiliary predictor component to induce effective importance weighting for unsupervised domain adaptation under covariate shift.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The target-side penalty on an auxiliary predictor component induces implicit relative importance weighting that stays bounded even with disjoint supports.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"127adcba1b860c889fda8a3d77108e87cd85f7c456209098ac185230b1237569"},"source":{"id":"2605.14280","kind":"arxiv","version":1},"verdict":{"id":"d770991c-ad92-4e37-ad65-f797ca48a70a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:25:24.880973Z","strongest_claim":"At the population level, the target-side penalty on b implicitly induces relative importance weighting in terms of an estimand b*_f that is self-localized to the current error and remains uniformly bounded for any source-target pair, even those with disjoint supports; a general finite-sample oracle inequality holds and yields an end-to-end guarantee for sparse ReLU networks.","one_line_summary":"TILT adds a target-data penalty on an auxiliary predictor component to induce effective importance weighting for unsupervised domain adaptation under covariate shift.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The analysis assumes the existence of a decomposition f + b where the penalty on b on target data produces a useful weighting without requiring the supports of source and target to overlap or any explicit density estimation.","pith_extraction_headline":"The target-side penalty on an auxiliary predictor component induces implicit relative importance weighting that stays bounded even with disjoint supports."},"references":{"count":144,"sample":[{"doi":"","year":null,"title":"Tyrrell Rockafellar and Ren","work_id":"ba3a8e18-5c32-4b7e-86c0-775112546ed9","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2009,"title":"2009 , publisher =","work_id":"21422820-909c-4f56-9bfd-76bc6834a77d","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Tyrrell Rockafellar and Roger J.-B","work_id":"923f93d7-5e68-4db1-9247-7c11527b2706","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2014,"title":"Foundations and Trends in Optimization , volume =","work_id":"594ac684-7262-42d4-8272-bad3725b35d3","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"Proceedings of the 29th Annual Conference on Learning Theory , series =","work_id":"8ec44617-4c2f-4e9f-9978-18b58ca564eb","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":144,"snapshot_sha256":"7ad11daebb02e721965cbfd6ccc29c3ff70d93ca8b4cc5a8b65013050517275a","internal_anchors":4},"formal_canon":{"evidence_count":2,"snapshot_sha256":"31ce2be4f2c59a0461c92f596d01663f3dfaddf4aa7204d1349bf7d0cdf8eefc"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"d770991c-ad92-4e37-ad65-f797ca48a70a"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3MHwu8yCWMstJHDsoeKVtn6RXKA2SXqayu+AH6fJ58hSbHT3VdU+okEPVjaflB1Kk907hWsio0hx7ySXd5+2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T18:13:06.718427Z"},"content_sha256":"e88158c3084aadf2e9076969aa405058519ee9d32d24988a96c56aabedbfb442","schema_version":"1.0","event_id":"sha256:e88158c3084aadf2e9076969aa405058519ee9d32d24988a96c56aabedbfb442"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MR7OAPQB5UGBHODDHWH7QW4U7C/bundle.json","state_url":"https://pith.science/pith/MR7OAPQB5UGBHODDHWH7QW4U7C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MR7OAPQB5UGBHODDHWH7QW4U7C/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":"2026-05-27T18:13:06Z","links":{"resolver":"https://pith.science/pith/MR7OAPQB5UGBHODDHWH7QW4U7C","bundle":"https://pith.science/pith/MR7OAPQB5UGBHODDHWH7QW4U7C/bundle.json","state":"https://pith.science/pith/MR7OAPQB5UGBHODDHWH7QW4U7C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MR7OAPQB5UGBHODDHWH7QW4U7C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MR7OAPQB5UGBHODDHWH7QW4U7C","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":"08bcddc4dbe97e64f2c3caa4af0c30f64d44d1fe03b4f481470ccb67f120162f","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T02:26:34Z","title_canon_sha256":"cab922bc611b9364badeda283d335b82f4bc07a37a4e2d18c0fbea8f69c9ac6f"},"schema_version":"1.0","source":{"id":"2605.14280","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14280","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14280v1","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14280","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"pith_short_12","alias_value":"MR7OAPQB5UGB","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"MR7OAPQB5UGBHODD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"MR7OAPQB","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:e88158c3084aadf2e9076969aa405058519ee9d32d24988a96c56aabedbfb442","target":"graph","created_at":"2026-05-17T23:39:10Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"At the population level, the target-side penalty on b implicitly induces relative importance weighting in terms of an estimand b*_f that is self-localized to the current error and remains uniformly bounded for any source-target pair, even those with disjoint supports; a general finite-sample oracle inequality holds and yields an end-to-end guarantee for sparse ReLU networks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The analysis assumes the existence of a decomposition f + b where the penalty on b on target data produces a useful weighting without requiring the supports of source and target to overlap or any explicit density estimation."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"TILT adds a target-data penalty on an auxiliary predictor component to induce effective importance weighting for unsupervised domain adaptation under covariate shift."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"The target-side penalty on an auxiliary predictor component induces implicit relative importance weighting that stays bounded even with disjoint supports."}],"snapshot_sha256":"127adcba1b860c889fda8a3d77108e87cd85f7c456209098ac185230b1237569"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"31ce2be4f2c59a0461c92f596d01663f3dfaddf4aa7204d1349bf7d0cdf8eefc"},"paper":{"abstract_excerpt":"We introduce and analyze Target-Induced Loss Tilting (TILT) for unsupervised domain adaptation under covariate shift. It is based on a novel objective function that decomposes the source predictor as $f+b$, fits $f+b$ on labeled source data while simultaneously penalizing the auxiliary component $b$ on unlabeled target inputs. The resulting fit $f$ is deployed as the final target predictor. At the population level, we show that this target-side penalty implicitly induces relative importance weighting at the population level, but in terms of an estimand $b^*_f$ that is self-localized to the cur","authors_text":"Kakei Yamamoto, Martin J. Wainwright","cross_cats":["stat.ML"],"headline":"The target-side penalty on an auxiliary predictor component induces implicit relative importance weighting that stays bounded even with disjoint supports.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T02:26:34Z","title":"TILT: Target-induced loss tilting under covariate shift"},"references":{"count":144,"internal_anchors":4,"resolved_work":144,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Tyrrell Rockafellar and Ren","work_id":"ba3a8e18-5c32-4b7e-86c0-775112546ed9","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"2009 , publisher =","work_id":"21422820-909c-4f56-9bfd-76bc6834a77d","year":2009},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Tyrrell Rockafellar and Roger J.-B","work_id":"923f93d7-5e68-4db1-9247-7c11527b2706","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Foundations and Trends in Optimization , volume =","work_id":"594ac684-7262-42d4-8272-bad3725b35d3","year":2014},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Proceedings of the 29th Annual Conference on Learning Theory , series =","work_id":"8ec44617-4c2f-4e9f-9978-18b58ca564eb","year":2016}],"snapshot_sha256":"7ad11daebb02e721965cbfd6ccc29c3ff70d93ca8b4cc5a8b65013050517275a"},"source":{"id":"2605.14280","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T02:25:24.880973Z","id":"d770991c-ad92-4e37-ad65-f797ca48a70a","model_set":{"reader":"grok-4.3"},"one_line_summary":"TILT adds a target-data penalty on an auxiliary predictor component to induce effective importance weighting for unsupervised domain adaptation under covariate shift.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"The target-side penalty on an auxiliary predictor component induces implicit relative importance weighting that stays bounded even with disjoint supports.","strongest_claim":"At the population level, the target-side penalty on b implicitly induces relative importance weighting in terms of an estimand b*_f that is self-localized to the current error and remains uniformly bounded for any source-target pair, even those with disjoint supports; a general finite-sample oracle inequality holds and yields an end-to-end guarantee for sparse ReLU networks.","weakest_assumption":"The analysis assumes the existence of a decomposition f + b where the penalty on b on target data produces a useful weighting without requiring the supports of source and target to overlap or any explicit density estimation."}},"verdict_id":"d770991c-ad92-4e37-ad65-f797ca48a70a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8628a3fc403ef19881c5a2d6005d165372d9c1cd578c5c8564e12a1b778d38e2","target":"record","created_at":"2026-05-17T23:39:10Z","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":"08bcddc4dbe97e64f2c3caa4af0c30f64d44d1fe03b4f481470ccb67f120162f","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T02:26:34Z","title_canon_sha256":"cab922bc611b9364badeda283d335b82f4bc07a37a4e2d18c0fbea8f69c9ac6f"},"schema_version":"1.0","source":{"id":"2605.14280","kind":"arxiv","version":1}},"canonical_sha256":"647ee03e01ed0c13b8633d8ff85b94f8a54a93512fd1332897b48317b2e2dc02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"647ee03e01ed0c13b8633d8ff85b94f8a54a93512fd1332897b48317b2e2dc02","first_computed_at":"2026-05-17T23:39:10.296601Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:10.296601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"70uptICrleMsHZ29PPcCxgQ1hB9OCPEklof4icUI0XaOZ49KL8aQLd5yukugEkTkOuI68J5I665wLinIimBPCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:10.297227Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14280","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8628a3fc403ef19881c5a2d6005d165372d9c1cd578c5c8564e12a1b778d38e2","sha256:e88158c3084aadf2e9076969aa405058519ee9d32d24988a96c56aabedbfb442"],"state_sha256":"fda8cbb80b6dd585e9d08eeeea82a9e7d9bd956b80c93b40e041e9237eba7a75"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qWUAueo93RDuLHtPjXoN5TnzE59aQp8RFFkI7Ag9yYGClf/o0lgbgMpENkLAzi6pcS43OMz7Z36G7Np8E9DUBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T18:13:06.721368Z","bundle_sha256":"43e71c3a2071aeeefff88ee17c0cbba3ae03469af14fca3ca10aa0764696e6ee"}}