{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XRXTHHTXBJOUQMCESSSOEA7FJ6","short_pith_number":"pith:XRXTHHTX","canonical_record":{"source":{"id":"2607.10116","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-11T04:35:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9171f2bc0905fb84da576f2c0176f4f206cc5a3c257d4dff4e44b03d22afdb48","abstract_canon_sha256":"b405898188a29287e4450a0ce2f9aed48c67c4c83a11fd5617c03e17f766a162"},"schema_version":"1.0"},"canonical_sha256":"bc6f339e770a5d48304494a4e203e54f862914d6df220bce9bd43ba529bbbf5d","source":{"kind":"arxiv","id":"2607.10116","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.10116","created_at":"2026-07-14T01:20:26Z"},{"alias_kind":"arxiv_version","alias_value":"2607.10116v1","created_at":"2026-07-14T01:20:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10116","created_at":"2026-07-14T01:20:26Z"},{"alias_kind":"pith_short_12","alias_value":"XRXTHHTXBJOU","created_at":"2026-07-14T01:20:26Z"},{"alias_kind":"pith_short_16","alias_value":"XRXTHHTXBJOUQMCE","created_at":"2026-07-14T01:20:26Z"},{"alias_kind":"pith_short_8","alias_value":"XRXTHHTX","created_at":"2026-07-14T01:20:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XRXTHHTXBJOUQMCESSSOEA7FJ6","target":"record","payload":{"canonical_record":{"source":{"id":"2607.10116","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-11T04:35:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9171f2bc0905fb84da576f2c0176f4f206cc5a3c257d4dff4e44b03d22afdb48","abstract_canon_sha256":"b405898188a29287e4450a0ce2f9aed48c67c4c83a11fd5617c03e17f766a162"},"schema_version":"1.0"},"canonical_sha256":"bc6f339e770a5d48304494a4e203e54f862914d6df220bce9bd43ba529bbbf5d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:20:26.033266Z","signature_b64":"Ip5JkFE/IHFMZUUGyEEJsymlW93U3KG7fXRmjh53yTFTfFCBOw/tUmikU5jfPmrwh34K85TT5LXxjWZ7Wy7oCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc6f339e770a5d48304494a4e203e54f862914d6df220bce9bd43ba529bbbf5d","last_reissued_at":"2026-07-14T01:20:26.032284Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:20:26.032284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.10116","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":"2026-07-14T01:20:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XX1Rb112xrLu99n1CNfyqr00ftfxXMrcJBGU6LtT9SD4RXfzOC0BAq/kwY3+2rj54jH+NVYKn+VDji90s3uqAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T07:59:45.039488Z"},"content_sha256":"c97f5c284468177f011aca32a9d12c7b2135e15692164ec3938b351db46375c0","schema_version":"1.0","event_id":"sha256:c97f5c284468177f011aca32a9d12c7b2135e15692164ec3938b351db46375c0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XRXTHHTXBJOUQMCESSSOEA7FJ6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Data Imbalance Helps: Robust Generalization Through Shortcut Saturation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cheng-Ting Chou, Duc Binh Hoang","submitted_at":"2026-07-11T04:35:04Z","abstract_excerpt":"We study robust generalization under spurious correlations: tasks where a shortcut feature is correlated with the true label in training but anti-correlated in an adversarial held-out split. Varying the spurious ratio $r$ (the fraction of training examples where shortcut = true label) and model capacity, we find a counterintuitive result: data imbalance promotes generalization in sufficiently capable models. On a synthetic task where the true label is sum parity of an integer sequence and the shortcut is the parity of the maximum-valued element, a 2-layer, 2-head transformer generalized (reach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10116","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/2607.10116/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":"2026-07-14T01:20:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GSyR1mkqXdTcUyXxp+ww6RQ+frXKUcZ/6z0K1rh+FTQ9ttapF4KLzHTif/GdiYst2gM7jy1ST6wg3GQobFYqCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T07:59:45.039986Z"},"content_sha256":"b1a38bc24644a9599eb0db66d00619666f86303eeb93ffc9a1b5535a6569a62b","schema_version":"1.0","event_id":"sha256:b1a38bc24644a9599eb0db66d00619666f86303eeb93ffc9a1b5535a6569a62b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XRXTHHTXBJOUQMCESSSOEA7FJ6/bundle.json","state_url":"https://pith.science/pith/XRXTHHTXBJOUQMCESSSOEA7FJ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XRXTHHTXBJOUQMCESSSOEA7FJ6/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":"2026-08-14T07:59:45Z","links":{"resolver":"https://pith.science/pith/XRXTHHTXBJOUQMCESSSOEA7FJ6","bundle":"https://pith.science/pith/XRXTHHTXBJOUQMCESSSOEA7FJ6/bundle.json","state":"https://pith.science/pith/XRXTHHTXBJOUQMCESSSOEA7FJ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XRXTHHTXBJOUQMCESSSOEA7FJ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XRXTHHTXBJOUQMCESSSOEA7FJ6","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":"b405898188a29287e4450a0ce2f9aed48c67c4c83a11fd5617c03e17f766a162","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-11T04:35:04Z","title_canon_sha256":"9171f2bc0905fb84da576f2c0176f4f206cc5a3c257d4dff4e44b03d22afdb48"},"schema_version":"1.0","source":{"id":"2607.10116","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.10116","created_at":"2026-07-14T01:20:26Z"},{"alias_kind":"arxiv_version","alias_value":"2607.10116v1","created_at":"2026-07-14T01:20:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10116","created_at":"2026-07-14T01:20:26Z"},{"alias_kind":"pith_short_12","alias_value":"XRXTHHTXBJOU","created_at":"2026-07-14T01:20:26Z"},{"alias_kind":"pith_short_16","alias_value":"XRXTHHTXBJOUQMCE","created_at":"2026-07-14T01:20:26Z"},{"alias_kind":"pith_short_8","alias_value":"XRXTHHTX","created_at":"2026-07-14T01:20:26Z"}],"graph_snapshots":[{"event_id":"sha256:b1a38bc24644a9599eb0db66d00619666f86303eeb93ffc9a1b5535a6569a62b","target":"graph","created_at":"2026-07-14T01:20:26Z","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/2607.10116/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study robust generalization under spurious correlations: tasks where a shortcut feature is correlated with the true label in training but anti-correlated in an adversarial held-out split. Varying the spurious ratio $r$ (the fraction of training examples where shortcut = true label) and model capacity, we find a counterintuitive result: data imbalance promotes generalization in sufficiently capable models. On a synthetic task where the true label is sum parity of an integer sequence and the shortcut is the parity of the maximum-valued element, a 2-layer, 2-head transformer generalized (reach","authors_text":"Cheng-Ting Chou, Duc Binh Hoang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-11T04:35:04Z","title":"When Data Imbalance Helps: Robust Generalization Through Shortcut Saturation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10116","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:c97f5c284468177f011aca32a9d12c7b2135e15692164ec3938b351db46375c0","target":"record","created_at":"2026-07-14T01:20:26Z","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":"b405898188a29287e4450a0ce2f9aed48c67c4c83a11fd5617c03e17f766a162","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-11T04:35:04Z","title_canon_sha256":"9171f2bc0905fb84da576f2c0176f4f206cc5a3c257d4dff4e44b03d22afdb48"},"schema_version":"1.0","source":{"id":"2607.10116","kind":"arxiv","version":1}},"canonical_sha256":"bc6f339e770a5d48304494a4e203e54f862914d6df220bce9bd43ba529bbbf5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc6f339e770a5d48304494a4e203e54f862914d6df220bce9bd43ba529bbbf5d","first_computed_at":"2026-07-14T01:20:26.032284Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T01:20:26.032284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ip5JkFE/IHFMZUUGyEEJsymlW93U3KG7fXRmjh53yTFTfFCBOw/tUmikU5jfPmrwh34K85TT5LXxjWZ7Wy7oCQ==","signature_status":"signed_v1","signed_at":"2026-07-14T01:20:26.033266Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.10116","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c97f5c284468177f011aca32a9d12c7b2135e15692164ec3938b351db46375c0","sha256:b1a38bc24644a9599eb0db66d00619666f86303eeb93ffc9a1b5535a6569a62b"],"state_sha256":"e0a8c59e2e9d9204602aa0fbc3c16a41a492a62362cb744f0557790f9d4fc7a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6d+vEHKya8vma08nnQGxOQB3PVVJrCsdB8y6ZnMTBEb+g53aUQdroratTAnkgRNcbelQDVbbnmXewacrKN21Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T07:59:45.046046Z","bundle_sha256":"a32c3356227b1de6f54cdf8257b3df16ed8c872cfeb6ac243e4acc9ddeae2cdb"}}