{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AMCPRJ73ZPFS3FX43Z37MZASK6","short_pith_number":"pith:AMCPRJ73","canonical_record":{"source":{"id":"2406.10742","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-15T21:41:25Z","cross_cats_sorted":[],"title_canon_sha256":"d2ccdfb8203ce07bf8deb7f21832cff35d9788e932cbd93888d942f46b6488a6","abstract_canon_sha256":"1287bd49e84a01a0781f7e9ce73c1267dd737ccfa3ced20edb1d5a9265cef716"},"schema_version":"1.0"},"canonical_sha256":"0304f8a7fbcbcb2d96fcde77f6641257894031eac63aae6469fd480eff41075c","source":{"kind":"arxiv","id":"2406.10742","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10742","created_at":"2026-07-05T08:32:21Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10742v1","created_at":"2026-07-05T08:32:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10742","created_at":"2026-07-05T08:32:21Z"},{"alias_kind":"pith_short_12","alias_value":"AMCPRJ73ZPFS","created_at":"2026-07-05T08:32:21Z"},{"alias_kind":"pith_short_16","alias_value":"AMCPRJ73ZPFS3FX4","created_at":"2026-07-05T08:32:21Z"},{"alias_kind":"pith_short_8","alias_value":"AMCPRJ73","created_at":"2026-07-05T08:32:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AMCPRJ73ZPFS3FX43Z37MZASK6","target":"record","payload":{"canonical_record":{"source":{"id":"2406.10742","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-15T21:41:25Z","cross_cats_sorted":[],"title_canon_sha256":"d2ccdfb8203ce07bf8deb7f21832cff35d9788e932cbd93888d942f46b6488a6","abstract_canon_sha256":"1287bd49e84a01a0781f7e9ce73c1267dd737ccfa3ced20edb1d5a9265cef716"},"schema_version":"1.0"},"canonical_sha256":"0304f8a7fbcbcb2d96fcde77f6641257894031eac63aae6469fd480eff41075c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:21.391177Z","signature_b64":"05m0DbnioqnP2jAKMN1cPYoKh6HKX7Rfg9sybfC91CiOuOt7eJx85QW3uWQ+laQICXfjt+8DT2TPfigW3eRuCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0304f8a7fbcbcb2d96fcde77f6641257894031eac63aae6469fd480eff41075c","last_reissued_at":"2026-07-05T08:32:21.390703Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:21.390703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.10742","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":"2026-07-05T08:32:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AvqKzViz9oVPl8tNlW3t4Zrn1hlrF0WHMdfyUUrdlvkUba9Q9tbWxfMKPA5ebq3PXDpq2wtWNNnqi5eAF2eEDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:32:58.546025Z"},"content_sha256":"9fc23c83030b415c66e2d8bc32bf1036be22cc519a21737a3decb67296f41032","schema_version":"1.0","event_id":"sha256:9fc23c83030b415c66e2d8bc32bf1036be22cc519a21737a3decb67296f41032"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AMCPRJ73ZPFS3FX43Z37MZASK6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Spuriousness-Aware Meta-Learning for Learning Robust Classifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aidong Zhang, Guangtao Zheng, Wenqian Ye","submitted_at":"2024-06-15T21:41:25Z","abstract_excerpt":"Spurious correlations are brittle associations between certain attributes of inputs and target variables, such as the correlation between an image background and an object class. Deep image classifiers often leverage them for predictions, leading to poor generalization on the data where the correlations do not hold. Mitigating the impact of spurious correlations is crucial towards robust model generalization, but it often requires annotations of the spurious correlations in data -- a strong assumption in practice. In this paper, we propose a novel learning framework based on meta-learning, ter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10742","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/2406.10742/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":"2026-07-05T08:32:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wfqKMbZADPzIRpDyDakmppFxhNAoqOiBTMOnU0Pv7CzzvoiDTN5UV0fXoSiIkC9bdyRsjcslImsV12VtK5TdBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:32:58.546460Z"},"content_sha256":"a6d56c9611ae9019a7f0c4b4425bef5349998ec6d77eb3b61c93e337d2572a8e","schema_version":"1.0","event_id":"sha256:a6d56c9611ae9019a7f0c4b4425bef5349998ec6d77eb3b61c93e337d2572a8e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AMCPRJ73ZPFS3FX43Z37MZASK6/bundle.json","state_url":"https://pith.science/pith/AMCPRJ73ZPFS3FX43Z37MZASK6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AMCPRJ73ZPFS3FX43Z37MZASK6/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":"2026-07-09T05:32:58Z","links":{"resolver":"https://pith.science/pith/AMCPRJ73ZPFS3FX43Z37MZASK6","bundle":"https://pith.science/pith/AMCPRJ73ZPFS3FX43Z37MZASK6/bundle.json","state":"https://pith.science/pith/AMCPRJ73ZPFS3FX43Z37MZASK6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AMCPRJ73ZPFS3FX43Z37MZASK6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AMCPRJ73ZPFS3FX43Z37MZASK6","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":"1287bd49e84a01a0781f7e9ce73c1267dd737ccfa3ced20edb1d5a9265cef716","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-15T21:41:25Z","title_canon_sha256":"d2ccdfb8203ce07bf8deb7f21832cff35d9788e932cbd93888d942f46b6488a6"},"schema_version":"1.0","source":{"id":"2406.10742","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10742","created_at":"2026-07-05T08:32:21Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10742v1","created_at":"2026-07-05T08:32:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10742","created_at":"2026-07-05T08:32:21Z"},{"alias_kind":"pith_short_12","alias_value":"AMCPRJ73ZPFS","created_at":"2026-07-05T08:32:21Z"},{"alias_kind":"pith_short_16","alias_value":"AMCPRJ73ZPFS3FX4","created_at":"2026-07-05T08:32:21Z"},{"alias_kind":"pith_short_8","alias_value":"AMCPRJ73","created_at":"2026-07-05T08:32:21Z"}],"graph_snapshots":[{"event_id":"sha256:a6d56c9611ae9019a7f0c4b4425bef5349998ec6d77eb3b61c93e337d2572a8e","target":"graph","created_at":"2026-07-05T08:32:21Z","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/2406.10742/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spurious correlations are brittle associations between certain attributes of inputs and target variables, such as the correlation between an image background and an object class. Deep image classifiers often leverage them for predictions, leading to poor generalization on the data where the correlations do not hold. Mitigating the impact of spurious correlations is crucial towards robust model generalization, but it often requires annotations of the spurious correlations in data -- a strong assumption in practice. In this paper, we propose a novel learning framework based on meta-learning, ter","authors_text":"Aidong Zhang, Guangtao Zheng, Wenqian Ye","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-15T21:41:25Z","title":"Spuriousness-Aware Meta-Learning for Learning Robust Classifiers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10742","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":"sha256:9fc23c83030b415c66e2d8bc32bf1036be22cc519a21737a3decb67296f41032","target":"record","created_at":"2026-07-05T08:32:21Z","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":"1287bd49e84a01a0781f7e9ce73c1267dd737ccfa3ced20edb1d5a9265cef716","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-15T21:41:25Z","title_canon_sha256":"d2ccdfb8203ce07bf8deb7f21832cff35d9788e932cbd93888d942f46b6488a6"},"schema_version":"1.0","source":{"id":"2406.10742","kind":"arxiv","version":1}},"canonical_sha256":"0304f8a7fbcbcb2d96fcde77f6641257894031eac63aae6469fd480eff41075c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0304f8a7fbcbcb2d96fcde77f6641257894031eac63aae6469fd480eff41075c","first_computed_at":"2026-07-05T08:32:21.390703Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:21.390703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"05m0DbnioqnP2jAKMN1cPYoKh6HKX7Rfg9sybfC91CiOuOt7eJx85QW3uWQ+laQICXfjt+8DT2TPfigW3eRuCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:21.391177Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10742","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9fc23c83030b415c66e2d8bc32bf1036be22cc519a21737a3decb67296f41032","sha256:a6d56c9611ae9019a7f0c4b4425bef5349998ec6d77eb3b61c93e337d2572a8e"],"state_sha256":"6229b7cf5a92a2d008b586ba1aae3c941dcaec6a76ac63cf90a524d46e85d158"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AQQiUDYmo0bVsdgb5ETDcfJ6s2nXm0FsVVaekIEvtRgTevK4zvAQUl6O5I5/hZpo2t31pBUueGQCrKnol4mqAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:32:58.551465Z","bundle_sha256":"d2e411c627af7d21d5e3ee3b34bf1faf120ad1b6d524828427346b5882ca4ce0"}}