{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:H7UFV2RQBHL5DUVY3KDHSQ6BZH","short_pith_number":"pith:H7UFV2RQ","canonical_record":{"source":{"id":"2110.04301","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T15:55:05Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"595394af497aaaf1f4c07c0353fa640a92a9f57853553808b37374eddbb89487","abstract_canon_sha256":"600af69d3a033c780bcdec76a80213fb3f961dbb3f16b842e565fdcdefd7bbde"},"schema_version":"1.0"},"canonical_sha256":"3fe85aea3009d7d1d2b8da867943c1c9edc27fb64902f5b8c6d613aa8c79eb13","source":{"kind":"arxiv","id":"2110.04301","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.04301","created_at":"2026-07-05T04:08:59Z"},{"alias_kind":"arxiv_version","alias_value":"2110.04301v4","created_at":"2026-07-05T04:08:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04301","created_at":"2026-07-05T04:08:59Z"},{"alias_kind":"pith_short_12","alias_value":"H7UFV2RQBHL5","created_at":"2026-07-05T04:08:59Z"},{"alias_kind":"pith_short_16","alias_value":"H7UFV2RQBHL5DUVY","created_at":"2026-07-05T04:08:59Z"},{"alias_kind":"pith_short_8","alias_value":"H7UFV2RQ","created_at":"2026-07-05T04:08:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:H7UFV2RQBHL5DUVY3KDHSQ6BZH","target":"record","payload":{"canonical_record":{"source":{"id":"2110.04301","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T15:55:05Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"595394af497aaaf1f4c07c0353fa640a92a9f57853553808b37374eddbb89487","abstract_canon_sha256":"600af69d3a033c780bcdec76a80213fb3f961dbb3f16b842e565fdcdefd7bbde"},"schema_version":"1.0"},"canonical_sha256":"3fe85aea3009d7d1d2b8da867943c1c9edc27fb64902f5b8c6d613aa8c79eb13","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:59.042633Z","signature_b64":"CGGV+jKKlDmrKUDeUgzbQZ/pCAhlE2bB5Tcii3jBiZ48CrilzdJg1dLoGlA6/6szb2VWcMjoqYm4NTGYwjcIBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fe85aea3009d7d1d2b8da867943c1c9edc27fb64902f5b8c6d613aa8c79eb13","last_reissued_at":"2026-07-05T04:08:59.042143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:59.042143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.04301","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:08:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OqbTR6+yt9yzTg71ong+z/nh2TnxKfnsUnfiHRhMjccTJHALhWJ+H7mZD4u/BWBGiIK28pN64TBUHEDuWWcnDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T18:25:27.290042Z"},"content_sha256":"8fc5fa0be365e9632959f6152a5d26bc7b55c6411c5f71dff2535dae9099d64e","schema_version":"1.0","event_id":"sha256:8fc5fa0be365e9632959f6152a5d26bc7b55c6411c5f71dff2535dae9099d64e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:H7UFV2RQBHL5DUVY3KDHSQ6BZH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Salient ImageNet: How to discover spurious features in Deep Learning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Sahil Singla, Soheil Feizi","submitted_at":"2021-10-08T15:55:05Z","abstract_excerpt":"Deep neural networks can be unreliable in the real world especially when they heavily use {\\it spurious} features for their predictions. Focusing on image classifications, we define {\\it core features} as the set of visual features that are always a part of the object definition while {\\it spurious features} are the ones that are likely to {\\it co-occur} with the object but not a part of it (e.g., attribute \"fingers\" for class \"band aid\"). Traditional methods for discovering spurious features either require extensive human annotations (thus, not scalable), or are useful on specific models. In "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04301","kind":"arxiv","version":4},"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/2110.04301/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":"2026-07-05T04:08:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4mllQgPmzvChCMwMrdqHmR3/SmT0gNJodlGw61p3is0xwjqIJjqn/TtwBD+0aFnyTXbY0wYMgJSfKwx2RYcwDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T18:25:27.291713Z"},"content_sha256":"61d4497039a8d2be9e708d730270413b0a1372059c740590627f8013aa752256","schema_version":"1.0","event_id":"sha256:61d4497039a8d2be9e708d730270413b0a1372059c740590627f8013aa752256"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H7UFV2RQBHL5DUVY3KDHSQ6BZH/bundle.json","state_url":"https://pith.science/pith/H7UFV2RQBHL5DUVY3KDHSQ6BZH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H7UFV2RQBHL5DUVY3KDHSQ6BZH/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":"2026-08-21T18:25:27Z","links":{"resolver":"https://pith.science/pith/H7UFV2RQBHL5DUVY3KDHSQ6BZH","bundle":"https://pith.science/pith/H7UFV2RQBHL5DUVY3KDHSQ6BZH/bundle.json","state":"https://pith.science/pith/H7UFV2RQBHL5DUVY3KDHSQ6BZH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H7UFV2RQBHL5DUVY3KDHSQ6BZH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:H7UFV2RQBHL5DUVY3KDHSQ6BZH","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":"600af69d3a033c780bcdec76a80213fb3f961dbb3f16b842e565fdcdefd7bbde","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T15:55:05Z","title_canon_sha256":"595394af497aaaf1f4c07c0353fa640a92a9f57853553808b37374eddbb89487"},"schema_version":"1.0","source":{"id":"2110.04301","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.04301","created_at":"2026-07-05T04:08:59Z"},{"alias_kind":"arxiv_version","alias_value":"2110.04301v4","created_at":"2026-07-05T04:08:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04301","created_at":"2026-07-05T04:08:59Z"},{"alias_kind":"pith_short_12","alias_value":"H7UFV2RQBHL5","created_at":"2026-07-05T04:08:59Z"},{"alias_kind":"pith_short_16","alias_value":"H7UFV2RQBHL5DUVY","created_at":"2026-07-05T04:08:59Z"},{"alias_kind":"pith_short_8","alias_value":"H7UFV2RQ","created_at":"2026-07-05T04:08:59Z"}],"graph_snapshots":[{"event_id":"sha256:61d4497039a8d2be9e708d730270413b0a1372059c740590627f8013aa752256","target":"graph","created_at":"2026-07-05T04:08:59Z","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/2110.04301/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural networks can be unreliable in the real world especially when they heavily use {\\it spurious} features for their predictions. Focusing on image classifications, we define {\\it core features} as the set of visual features that are always a part of the object definition while {\\it spurious features} are the ones that are likely to {\\it co-occur} with the object but not a part of it (e.g., attribute \"fingers\" for class \"band aid\"). Traditional methods for discovering spurious features either require extensive human annotations (thus, not scalable), or are useful on specific models. In ","authors_text":"Sahil Singla, Soheil Feizi","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T15:55:05Z","title":"Salient ImageNet: How to discover spurious features in Deep Learning?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04301","kind":"arxiv","version":4},"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":"sha256:8fc5fa0be365e9632959f6152a5d26bc7b55c6411c5f71dff2535dae9099d64e","target":"record","created_at":"2026-07-05T04:08:59Z","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":"600af69d3a033c780bcdec76a80213fb3f961dbb3f16b842e565fdcdefd7bbde","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T15:55:05Z","title_canon_sha256":"595394af497aaaf1f4c07c0353fa640a92a9f57853553808b37374eddbb89487"},"schema_version":"1.0","source":{"id":"2110.04301","kind":"arxiv","version":4}},"canonical_sha256":"3fe85aea3009d7d1d2b8da867943c1c9edc27fb64902f5b8c6d613aa8c79eb13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3fe85aea3009d7d1d2b8da867943c1c9edc27fb64902f5b8c6d613aa8c79eb13","first_computed_at":"2026-07-05T04:08:59.042143Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:08:59.042143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CGGV+jKKlDmrKUDeUgzbQZ/pCAhlE2bB5Tcii3jBiZ48CrilzdJg1dLoGlA6/6szb2VWcMjoqYm4NTGYwjcIBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:08:59.042633Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.04301","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fc5fa0be365e9632959f6152a5d26bc7b55c6411c5f71dff2535dae9099d64e","sha256:61d4497039a8d2be9e708d730270413b0a1372059c740590627f8013aa752256"],"state_sha256":"d0f77145a089700517d0e871b412d382bbd9d9d5cd7e4d72488b8535a83340d8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QN/AVfGGiEX35b9NnQoJX+hI0wf8m9t0Pct8AScmHqrcTpdePxX/QzJDYRjjgb87rvGprZ5TcLjukzbl7ncBDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T18:25:27.301689Z","bundle_sha256":"072cdda09a63054511bf8cc5d57b31fce3f47813c5d7d03d02ef08338ed70861"}}