{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VK65K5MHEUO6ICMUVBEEO6GGXA","short_pith_number":"pith:VK65K5MH","canonical_record":{"source":{"id":"2505.16126","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T02:03:34Z","cross_cats_sorted":[],"title_canon_sha256":"4af22b1ad236540b3319d8b674f0505bb524cea0fdb86561dce470a84d09fd9a","abstract_canon_sha256":"cb61b59f42b0a92e89993774f0d6bc6503ffb5f2e2342580819781204c7625cc"},"schema_version":"1.0"},"canonical_sha256":"aabdd57587251de40994a8484778c6b805be0f7459c9fac379af815ba86174b3","source":{"kind":"arxiv","id":"2505.16126","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16126","created_at":"2026-07-05T11:08:21Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16126v2","created_at":"2026-07-05T11:08:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16126","created_at":"2026-07-05T11:08:21Z"},{"alias_kind":"pith_short_12","alias_value":"VK65K5MHEUO6","created_at":"2026-07-05T11:08:21Z"},{"alias_kind":"pith_short_16","alias_value":"VK65K5MHEUO6ICMU","created_at":"2026-07-05T11:08:21Z"},{"alias_kind":"pith_short_8","alias_value":"VK65K5MH","created_at":"2026-07-05T11:08:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VK65K5MHEUO6ICMUVBEEO6GGXA","target":"record","payload":{"canonical_record":{"source":{"id":"2505.16126","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T02:03:34Z","cross_cats_sorted":[],"title_canon_sha256":"4af22b1ad236540b3319d8b674f0505bb524cea0fdb86561dce470a84d09fd9a","abstract_canon_sha256":"cb61b59f42b0a92e89993774f0d6bc6503ffb5f2e2342580819781204c7625cc"},"schema_version":"1.0"},"canonical_sha256":"aabdd57587251de40994a8484778c6b805be0f7459c9fac379af815ba86174b3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:21.909722Z","signature_b64":"CiSXbwvEXusKEc9alBN5O/tIcfUqxI8SXuc+LSjwgBbeIsnwGL23ittM4zxWWdWrm+hQ/CSci4FPULnO6YrYBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aabdd57587251de40994a8484778c6b805be0f7459c9fac379af815ba86174b3","last_reissued_at":"2026-07-05T11:08:21.908555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:21.908555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.16126","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:08:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"to4TG+Q8+yX/1oZyLbLVEvhV7RFZYTfOaQ1+VLJ2iEmHhrKV1AzvB7+NiD5d0hKGSfOVM9S1yDrvzkiN6dN1AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T15:39:03.681705Z"},"content_sha256":"192174e7126d285d78db311966a24ee2fbac0f2d5d57bc88ac114a133e9e06fa","schema_version":"1.0","event_id":"sha256:192174e7126d285d78db311966a24ee2fbac0f2d5d57bc88ac114a133e9e06fa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VK65K5MHEUO6ICMUVBEEO6GGXA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Invariant Representation Learning by Distribution Extrapolation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Konstantinos Slavakis, Kotaro Yoshida","submitted_at":"2025-05-22T02:03:34Z","abstract_excerpt":"Invariant risk minimization (IRM) aims to enable out-of-distribution (OOD) generalization in deep learning by learning invariant representations. As IRM poses an inherently challenging bi-level optimization problem, most existing approaches -- including IRMv1 -- adopt penalty-based single-level approximations. However, empirical studies consistently show that these methods often fail to outperform well-tuned empirical risk minimization (ERM), highlighting the need for more robust IRM implementations. This work theoretically identifies a key limitation common to many IRM variants: their penalty"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16126","kind":"arxiv","version":2},"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/2505.16126/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":"2026-07-05T11:08:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KuhnQZTbCo21dmCO2IXpHCeZho4hOmBO6xYkdZpKUorUAJm6K5y1LJ/92qMs9Vk7B4O7mCeQcT6pHqR0WuxJAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T15:39:03.682233Z"},"content_sha256":"4ea38c5a448e8b2edb6e10bb8ab7b486890d83bbe02baa8d18254d94d77d265e","schema_version":"1.0","event_id":"sha256:4ea38c5a448e8b2edb6e10bb8ab7b486890d83bbe02baa8d18254d94d77d265e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VK65K5MHEUO6ICMUVBEEO6GGXA/bundle.json","state_url":"https://pith.science/pith/VK65K5MHEUO6ICMUVBEEO6GGXA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VK65K5MHEUO6ICMUVBEEO6GGXA/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":"2026-08-13T15:39:03Z","links":{"resolver":"https://pith.science/pith/VK65K5MHEUO6ICMUVBEEO6GGXA","bundle":"https://pith.science/pith/VK65K5MHEUO6ICMUVBEEO6GGXA/bundle.json","state":"https://pith.science/pith/VK65K5MHEUO6ICMUVBEEO6GGXA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VK65K5MHEUO6ICMUVBEEO6GGXA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VK65K5MHEUO6ICMUVBEEO6GGXA","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":"cb61b59f42b0a92e89993774f0d6bc6503ffb5f2e2342580819781204c7625cc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T02:03:34Z","title_canon_sha256":"4af22b1ad236540b3319d8b674f0505bb524cea0fdb86561dce470a84d09fd9a"},"schema_version":"1.0","source":{"id":"2505.16126","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16126","created_at":"2026-07-05T11:08:21Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16126v2","created_at":"2026-07-05T11:08:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16126","created_at":"2026-07-05T11:08:21Z"},{"alias_kind":"pith_short_12","alias_value":"VK65K5MHEUO6","created_at":"2026-07-05T11:08:21Z"},{"alias_kind":"pith_short_16","alias_value":"VK65K5MHEUO6ICMU","created_at":"2026-07-05T11:08:21Z"},{"alias_kind":"pith_short_8","alias_value":"VK65K5MH","created_at":"2026-07-05T11:08:21Z"}],"graph_snapshots":[{"event_id":"sha256:4ea38c5a448e8b2edb6e10bb8ab7b486890d83bbe02baa8d18254d94d77d265e","target":"graph","created_at":"2026-07-05T11:08:21Z","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/2505.16126/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Invariant risk minimization (IRM) aims to enable out-of-distribution (OOD) generalization in deep learning by learning invariant representations. As IRM poses an inherently challenging bi-level optimization problem, most existing approaches -- including IRMv1 -- adopt penalty-based single-level approximations. However, empirical studies consistently show that these methods often fail to outperform well-tuned empirical risk minimization (ERM), highlighting the need for more robust IRM implementations. This work theoretically identifies a key limitation common to many IRM variants: their penalty","authors_text":"Konstantinos Slavakis, Kotaro Yoshida","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T02:03:34Z","title":"Robust Invariant Representation Learning by Distribution Extrapolation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16126","kind":"arxiv","version":2},"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":"sha256:192174e7126d285d78db311966a24ee2fbac0f2d5d57bc88ac114a133e9e06fa","target":"record","created_at":"2026-07-05T11:08:21Z","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":"cb61b59f42b0a92e89993774f0d6bc6503ffb5f2e2342580819781204c7625cc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T02:03:34Z","title_canon_sha256":"4af22b1ad236540b3319d8b674f0505bb524cea0fdb86561dce470a84d09fd9a"},"schema_version":"1.0","source":{"id":"2505.16126","kind":"arxiv","version":2}},"canonical_sha256":"aabdd57587251de40994a8484778c6b805be0f7459c9fac379af815ba86174b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aabdd57587251de40994a8484778c6b805be0f7459c9fac379af815ba86174b3","first_computed_at":"2026-07-05T11:08:21.908555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:21.908555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CiSXbwvEXusKEc9alBN5O/tIcfUqxI8SXuc+LSjwgBbeIsnwGL23ittM4zxWWdWrm+hQ/CSci4FPULnO6YrYBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:21.909722Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16126","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:192174e7126d285d78db311966a24ee2fbac0f2d5d57bc88ac114a133e9e06fa","sha256:4ea38c5a448e8b2edb6e10bb8ab7b486890d83bbe02baa8d18254d94d77d265e"],"state_sha256":"79c524a630e20f8fbba992e624aeaa3fb5a1779f93cfffcadf0216ada1a8932e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y+Bri/nNIMTrthfSyxzYjfJF0902U2dOOmwlNiBSR1JH/0b70Ir67DRC7Pvte3BjsZsuJ5WSgf6myBWAAXJAAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T15:39:03.687541Z","bundle_sha256":"b98ef6037cd4d0bf5a2483b746a943064cbf5863591b1b615d1cb62246bf9e73"}}