{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GSLSDQHXLI75JTXJIQZ3G722PH","short_pith_number":"pith:GSLSDQHX","canonical_record":{"source":{"id":"2507.05527","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-07T22:49:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9ce5fe64d6b021d275b23635a43e563b4df94f1978fa3214a1e275ed5ada89eb","abstract_canon_sha256":"88c3aeec896a255992c0125dd4f386cdb92a7762b3bdc359cffb07777b3d18c2"},"schema_version":"1.0"},"canonical_sha256":"349721c0f75a3fd4cee94433b37f5a79e54505bc4b5555767b71218910ab4432","source":{"kind":"arxiv","id":"2507.05527","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05527","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05527v1","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05527","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"pith_short_12","alias_value":"GSLSDQHXLI75","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"pith_short_16","alias_value":"GSLSDQHXLI75JTXJ","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"pith_short_8","alias_value":"GSLSDQHX","created_at":"2026-07-05T11:33:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GSLSDQHXLI75JTXJIQZ3G722PH","target":"record","payload":{"canonical_record":{"source":{"id":"2507.05527","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-07T22:49:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9ce5fe64d6b021d275b23635a43e563b4df94f1978fa3214a1e275ed5ada89eb","abstract_canon_sha256":"88c3aeec896a255992c0125dd4f386cdb92a7762b3bdc359cffb07777b3d18c2"},"schema_version":"1.0"},"canonical_sha256":"349721c0f75a3fd4cee94433b37f5a79e54505bc4b5555767b71218910ab4432","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:31.771756Z","signature_b64":"scrbYGKUZNJ5o38Qlds9VNR5GlzaQYmpK1EcUZp1yLpHt9STaMWJmrHdMI4BMMsz+AZVeuGa5SEzVq0gU/wyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"349721c0f75a3fd4cee94433b37f5a79e54505bc4b5555767b71218910ab4432","last_reissued_at":"2026-07-05T11:33:31.771312Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:31.771312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.05527","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":"2026-07-05T11:33:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xsBNo3DvU6CFjUJZZ/O8UEuo4SgIj2kuOB30M27aJoX5Sl/smkAB694iorJhY+oKM955AWE4A2bFg3d9vQyIBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:53:04.516083Z"},"content_sha256":"89e7420fd25524a01c699ed74ba24df5bc33288fb034b1f48fbb7440d49b31b6","schema_version":"1.0","event_id":"sha256:89e7420fd25524a01c699ed74ba24df5bc33288fb034b1f48fbb7440d49b31b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GSLSDQHXLI75JTXJIQZ3G722PH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mitigating Shortcut Learning with InterpoLated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adrian Weller, Andreas Vlachos, Michalis Korakakis","submitted_at":"2025-07-07T22:49:46Z","abstract_excerpt":"Empirical risk minimization (ERM) incentivizes models to exploit shortcuts, i.e., spurious correlations between input attributes and labels that are prevalent in the majority of the training data but unrelated to the task at hand. This reliance hinders generalization on minority examples, where such correlations do not hold. Existing shortcut mitigation approaches are model-specific, difficult to tune, computationally expensive, and fail to improve learned representations. To address these issues, we propose InterpoLated Learning (InterpoLL) which interpolates the representations of majority e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05527","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/2507.05527/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":"2026-07-05T11:33:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LW7hcCId2JbS1ZmI+uTM/DHeZs32U6/aYJyBYT3QPtNFIxCT/BlkB+Tr7ABlHSngC/fBLUqSCzJg8kOhIeNEAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:53:04.516577Z"},"content_sha256":"594726b20eeb01c8d9b3d26a771119d0022f13ba7824ea0e8463877b844cb9c2","schema_version":"1.0","event_id":"sha256:594726b20eeb01c8d9b3d26a771119d0022f13ba7824ea0e8463877b844cb9c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GSLSDQHXLI75JTXJIQZ3G722PH/bundle.json","state_url":"https://pith.science/pith/GSLSDQHXLI75JTXJIQZ3G722PH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GSLSDQHXLI75JTXJIQZ3G722PH/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":"2026-08-07T23:53:04Z","links":{"resolver":"https://pith.science/pith/GSLSDQHXLI75JTXJIQZ3G722PH","bundle":"https://pith.science/pith/GSLSDQHXLI75JTXJIQZ3G722PH/bundle.json","state":"https://pith.science/pith/GSLSDQHXLI75JTXJIQZ3G722PH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GSLSDQHXLI75JTXJIQZ3G722PH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GSLSDQHXLI75JTXJIQZ3G722PH","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":"88c3aeec896a255992c0125dd4f386cdb92a7762b3bdc359cffb07777b3d18c2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-07T22:49:46Z","title_canon_sha256":"9ce5fe64d6b021d275b23635a43e563b4df94f1978fa3214a1e275ed5ada89eb"},"schema_version":"1.0","source":{"id":"2507.05527","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05527","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05527v1","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05527","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"pith_short_12","alias_value":"GSLSDQHXLI75","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"pith_short_16","alias_value":"GSLSDQHXLI75JTXJ","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"pith_short_8","alias_value":"GSLSDQHX","created_at":"2026-07-05T11:33:31Z"}],"graph_snapshots":[{"event_id":"sha256:594726b20eeb01c8d9b3d26a771119d0022f13ba7824ea0e8463877b844cb9c2","target":"graph","created_at":"2026-07-05T11:33:31Z","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/2507.05527/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Empirical risk minimization (ERM) incentivizes models to exploit shortcuts, i.e., spurious correlations between input attributes and labels that are prevalent in the majority of the training data but unrelated to the task at hand. This reliance hinders generalization on minority examples, where such correlations do not hold. Existing shortcut mitigation approaches are model-specific, difficult to tune, computationally expensive, and fail to improve learned representations. To address these issues, we propose InterpoLated Learning (InterpoLL) which interpolates the representations of majority e","authors_text":"Adrian Weller, Andreas Vlachos, Michalis Korakakis","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-07T22:49:46Z","title":"Mitigating Shortcut Learning with InterpoLated Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05527","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":"sha256:89e7420fd25524a01c699ed74ba24df5bc33288fb034b1f48fbb7440d49b31b6","target":"record","created_at":"2026-07-05T11:33:31Z","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":"88c3aeec896a255992c0125dd4f386cdb92a7762b3bdc359cffb07777b3d18c2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-07T22:49:46Z","title_canon_sha256":"9ce5fe64d6b021d275b23635a43e563b4df94f1978fa3214a1e275ed5ada89eb"},"schema_version":"1.0","source":{"id":"2507.05527","kind":"arxiv","version":1}},"canonical_sha256":"349721c0f75a3fd4cee94433b37f5a79e54505bc4b5555767b71218910ab4432","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"349721c0f75a3fd4cee94433b37f5a79e54505bc4b5555767b71218910ab4432","first_computed_at":"2026-07-05T11:33:31.771312Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:31.771312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"scrbYGKUZNJ5o38Qlds9VNR5GlzaQYmpK1EcUZp1yLpHt9STaMWJmrHdMI4BMMsz+AZVeuGa5SEzVq0gU/wyCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:31.771756Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.05527","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89e7420fd25524a01c699ed74ba24df5bc33288fb034b1f48fbb7440d49b31b6","sha256:594726b20eeb01c8d9b3d26a771119d0022f13ba7824ea0e8463877b844cb9c2"],"state_sha256":"cbad6b41deb3ad9eb31aae78cfdb69d68125964a2439474afb59db5c6750020a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FJATjQGoBbnXs+T5E7s8if3ZFo/bitD2KgRU08sAQtxZPyAt2va3MvfNdjAOz1M+LhNfBrKXSFHk3WvzqkqbAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:53:04.520597Z","bundle_sha256":"e3b6ba35a988f612e19ab543667204faaa1bece81af0891fc9346acb7f3fe9c9"}}