{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WTQQ5SRKBFTQLITDWJCURK4XJI","short_pith_number":"pith:WTQQ5SRK","canonical_record":{"source":{"id":"2502.09150","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T10:25:52Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"3bf7f3bb6d30abf551ec240445f73bbfff6e7618f516b7a126135301ef218078","abstract_canon_sha256":"3c8fa11e193d7d0cbb6db63eec9460c401aaee240896d0913ec46fbbc639dcf7"},"schema_version":"1.0"},"canonical_sha256":"b4e10eca2a096705a263b24548ab974a094400e646e823038165b219181712ed","source":{"kind":"arxiv","id":"2502.09150","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09150","created_at":"2026-07-05T12:02:40Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09150v2","created_at":"2026-07-05T12:02:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09150","created_at":"2026-07-05T12:02:40Z"},{"alias_kind":"pith_short_12","alias_value":"WTQQ5SRKBFTQ","created_at":"2026-07-05T12:02:40Z"},{"alias_kind":"pith_short_16","alias_value":"WTQQ5SRKBFTQLITD","created_at":"2026-07-05T12:02:40Z"},{"alias_kind":"pith_short_8","alias_value":"WTQQ5SRK","created_at":"2026-07-05T12:02:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WTQQ5SRKBFTQLITDWJCURK4XJI","target":"record","payload":{"canonical_record":{"source":{"id":"2502.09150","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T10:25:52Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"3bf7f3bb6d30abf551ec240445f73bbfff6e7618f516b7a126135301ef218078","abstract_canon_sha256":"3c8fa11e193d7d0cbb6db63eec9460c401aaee240896d0913ec46fbbc639dcf7"},"schema_version":"1.0"},"canonical_sha256":"b4e10eca2a096705a263b24548ab974a094400e646e823038165b219181712ed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:40.625094Z","signature_b64":"0QK31N7EfD2M46W5yhnvcx4dInCcEJUBHLj1wUzKz88C5M6T/HNxdHKB3vC6uTM5owt2sUEiDqNLFRa9/MS4AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4e10eca2a096705a263b24548ab974a094400e646e823038165b219181712ed","last_reissued_at":"2026-07-05T12:02:40.624612Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:40.624612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.09150","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":"2026-07-05T12:02:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v1g1+TxoiH6G8lWNtoJDivCe7KbhhOS1qrcpN/kDx0bZdLLRdp45lxZaMR91K6K55ARXKperUfbJpKfUmgxjDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:58:00.369442Z"},"content_sha256":"257f1b6874b29601c56b614912279254fed49a241dbba8d186c514e33ed346c1","schema_version":"1.0","event_id":"sha256:257f1b6874b29601c56b614912279254fed49a241dbba8d186c514e33ed346c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WTQQ5SRKBFTQLITDWJCURK4XJI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Shortcut Learning Susceptibility in Vision Classifiers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Amit Sethi, Pirzada Suhail, Vrinda Goel","submitted_at":"2025-02-13T10:25:52Z","abstract_excerpt":"Shortcut learning, where machine learning models exploit spurious correlations in data instead of capturing meaningful features, poses a significant challenge to building robust and generalizable models. This phenomenon is prevalent across various machine learning applications, including vision, natural language processing, and speech recognition, where models may find unintended cues that minimize training loss but fail to capture the underlying structure of the data. Vision classifiers based on Convolutional Neural Networks (CNNs), Multi-Layer Perceptrons (MLPs), and Vision Transformers (ViT"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09150","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/2502.09150/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":"2026-07-05T12:02:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TfMV9wxjo/d88GpxQtI3Uz+GaeXP3O1/3N/rVN4XOesOqYO987+CTjL8SowUdVf9Jh2oDlfUynkLLBrdCD/DCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:58:00.370539Z"},"content_sha256":"6821449d171584404aa1776d93597f1d482a922a7f1bc8ec6bab09176bcf0469","schema_version":"1.0","event_id":"sha256:6821449d171584404aa1776d93597f1d482a922a7f1bc8ec6bab09176bcf0469"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WTQQ5SRKBFTQLITDWJCURK4XJI/bundle.json","state_url":"https://pith.science/pith/WTQQ5SRKBFTQLITDWJCURK4XJI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WTQQ5SRKBFTQLITDWJCURK4XJI/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":"2026-08-05T03:58:00Z","links":{"resolver":"https://pith.science/pith/WTQQ5SRKBFTQLITDWJCURK4XJI","bundle":"https://pith.science/pith/WTQQ5SRKBFTQLITDWJCURK4XJI/bundle.json","state":"https://pith.science/pith/WTQQ5SRKBFTQLITDWJCURK4XJI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WTQQ5SRKBFTQLITDWJCURK4XJI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WTQQ5SRKBFTQLITDWJCURK4XJI","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":"3c8fa11e193d7d0cbb6db63eec9460c401aaee240896d0913ec46fbbc639dcf7","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T10:25:52Z","title_canon_sha256":"3bf7f3bb6d30abf551ec240445f73bbfff6e7618f516b7a126135301ef218078"},"schema_version":"1.0","source":{"id":"2502.09150","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09150","created_at":"2026-07-05T12:02:40Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09150v2","created_at":"2026-07-05T12:02:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09150","created_at":"2026-07-05T12:02:40Z"},{"alias_kind":"pith_short_12","alias_value":"WTQQ5SRKBFTQ","created_at":"2026-07-05T12:02:40Z"},{"alias_kind":"pith_short_16","alias_value":"WTQQ5SRKBFTQLITD","created_at":"2026-07-05T12:02:40Z"},{"alias_kind":"pith_short_8","alias_value":"WTQQ5SRK","created_at":"2026-07-05T12:02:40Z"}],"graph_snapshots":[{"event_id":"sha256:6821449d171584404aa1776d93597f1d482a922a7f1bc8ec6bab09176bcf0469","target":"graph","created_at":"2026-07-05T12:02:40Z","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/2502.09150/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Shortcut learning, where machine learning models exploit spurious correlations in data instead of capturing meaningful features, poses a significant challenge to building robust and generalizable models. This phenomenon is prevalent across various machine learning applications, including vision, natural language processing, and speech recognition, where models may find unintended cues that minimize training loss but fail to capture the underlying structure of the data. Vision classifiers based on Convolutional Neural Networks (CNNs), Multi-Layer Perceptrons (MLPs), and Vision Transformers (ViT","authors_text":"Amit Sethi, Pirzada Suhail, Vrinda Goel","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T10:25:52Z","title":"Shortcut Learning Susceptibility in Vision Classifiers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09150","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":"sha256:257f1b6874b29601c56b614912279254fed49a241dbba8d186c514e33ed346c1","target":"record","created_at":"2026-07-05T12:02:40Z","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":"3c8fa11e193d7d0cbb6db63eec9460c401aaee240896d0913ec46fbbc639dcf7","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T10:25:52Z","title_canon_sha256":"3bf7f3bb6d30abf551ec240445f73bbfff6e7618f516b7a126135301ef218078"},"schema_version":"1.0","source":{"id":"2502.09150","kind":"arxiv","version":2}},"canonical_sha256":"b4e10eca2a096705a263b24548ab974a094400e646e823038165b219181712ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4e10eca2a096705a263b24548ab974a094400e646e823038165b219181712ed","first_computed_at":"2026-07-05T12:02:40.624612Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:40.624612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0QK31N7EfD2M46W5yhnvcx4dInCcEJUBHLj1wUzKz88C5M6T/HNxdHKB3vC6uTM5owt2sUEiDqNLFRa9/MS4AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:40.625094Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.09150","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:257f1b6874b29601c56b614912279254fed49a241dbba8d186c514e33ed346c1","sha256:6821449d171584404aa1776d93597f1d482a922a7f1bc8ec6bab09176bcf0469"],"state_sha256":"bf7aa85d1541cf600c79f0be8a11e3544c4d8a890ab858672ac3180f395a0013"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nbPZD2IBxkQNw41JNjULCZroiBC14ESmfOGejp0ZtfegBZyiirCql8myoBulqZgD2uJ4bNL026aAraIsHEB2AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T03:58:00.399162Z","bundle_sha256":"81cf69848f6ca2f0654871a8b85234af53e69fb7aee9e2f1c700e44af135eb38"}}