{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:RICFXY3CW3T4OWDQZHBOURRE3L","short_pith_number":"pith:RICFXY3C","canonical_record":{"source":{"id":"2105.06506","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-13T18:40:57Z","cross_cats_sorted":[],"title_canon_sha256":"f38b4c1b4c12dd775ed1c0960d2f9a84654faa2d11ba3e8d337178bd1a0dfca5","abstract_canon_sha256":"68705aa1aa58999608286b9bebf1038c9181d41b0d357673badb7ad4b6725bc9"},"schema_version":"1.0"},"canonical_sha256":"8a045be362b6e7c75870c9c2ea4624daf47e86aa639ee9f3d4d8f991da1e606c","source":{"kind":"arxiv","id":"2105.06506","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.06506","created_at":"2026-07-05T04:32:25Z"},{"alias_kind":"arxiv_version","alias_value":"2105.06506v3","created_at":"2026-07-05T04:32:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.06506","created_at":"2026-07-05T04:32:25Z"},{"alias_kind":"pith_short_12","alias_value":"RICFXY3CW3T4","created_at":"2026-07-05T04:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"RICFXY3CW3T4OWDQ","created_at":"2026-07-05T04:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"RICFXY3C","created_at":"2026-07-05T04:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:RICFXY3CW3T4OWDQZHBOURRE3L","target":"record","payload":{"canonical_record":{"source":{"id":"2105.06506","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-13T18:40:57Z","cross_cats_sorted":[],"title_canon_sha256":"f38b4c1b4c12dd775ed1c0960d2f9a84654faa2d11ba3e8d337178bd1a0dfca5","abstract_canon_sha256":"68705aa1aa58999608286b9bebf1038c9181d41b0d357673badb7ad4b6725bc9"},"schema_version":"1.0"},"canonical_sha256":"8a045be362b6e7c75870c9c2ea4624daf47e86aa639ee9f3d4d8f991da1e606c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:25.831173Z","signature_b64":"Ulb3hUk/0JVWd8N9VAH329w4qL3TvWZrV2lybdtVXl3h+oJhSiHHS5q0pJAgF/4tpeGhxvwO2GLxnGSl9KviCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a045be362b6e7c75870c9c2ea4624daf47e86aa639ee9f3d4d8f991da1e606c","last_reissued_at":"2026-07-05T04:32:25.830699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:25.830699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.06506","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:32:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t8VEDmJknGMhnotp2UYhUyJb8wVPRb0ucuLnvMYBJIKmqhgn/zDGy5P5enbJcrGkEGuv93tDiQlwXRzoMz7wDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:42:09.077362Z"},"content_sha256":"455e315af33ea4c5957a75f2f3cee4d6e4571e397738dd0899cb778fa018456f","schema_version":"1.0","event_id":"sha256:455e315af33ea4c5957a75f2f3cee4d6e4571e397738dd0899cb778fa018456f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:RICFXY3CW3T4OWDQZHBOURRE3L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sanity Simulations for Saliency Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ameet Talwalkar, Gregory Plumb, Joon Sik Kim","submitted_at":"2021-05-13T18:40:57Z","abstract_excerpt":"Saliency methods are a popular class of feature attribution explanation methods that aim to capture a model's predictive reasoning by identifying \"important\" pixels in an input image. However, the development and adoption of these methods are hindered by the lack of access to ground-truth model reasoning, which prevents accurate evaluation. In this work, we design a synthetic benchmarking framework, SMERF, that allows us to perform ground-truth-based evaluation while controlling the complexity of the model's reasoning. Experimentally, SMERF reveals significant limitations in existing saliency "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.06506","kind":"arxiv","version":3},"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/2105.06506/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":"2026-07-05T04:32:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Sj3lg43+0Ag52kAknotF8j89ZLTAEUB5m+8YCtvD3oDQGJR9sSfYXCljUyAicz7kRP2wLGWajGwWk0oZS9ECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:42:09.077885Z"},"content_sha256":"7d557ebaf2a369fa2357e8096898316423983e3481ca2ee890eec463bdcd01b7","schema_version":"1.0","event_id":"sha256:7d557ebaf2a369fa2357e8096898316423983e3481ca2ee890eec463bdcd01b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RICFXY3CW3T4OWDQZHBOURRE3L/bundle.json","state_url":"https://pith.science/pith/RICFXY3CW3T4OWDQZHBOURRE3L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RICFXY3CW3T4OWDQZHBOURRE3L/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":"2026-08-06T05:42:09Z","links":{"resolver":"https://pith.science/pith/RICFXY3CW3T4OWDQZHBOURRE3L","bundle":"https://pith.science/pith/RICFXY3CW3T4OWDQZHBOURRE3L/bundle.json","state":"https://pith.science/pith/RICFXY3CW3T4OWDQZHBOURRE3L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RICFXY3CW3T4OWDQZHBOURRE3L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RICFXY3CW3T4OWDQZHBOURRE3L","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":"68705aa1aa58999608286b9bebf1038c9181d41b0d357673badb7ad4b6725bc9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-13T18:40:57Z","title_canon_sha256":"f38b4c1b4c12dd775ed1c0960d2f9a84654faa2d11ba3e8d337178bd1a0dfca5"},"schema_version":"1.0","source":{"id":"2105.06506","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.06506","created_at":"2026-07-05T04:32:25Z"},{"alias_kind":"arxiv_version","alias_value":"2105.06506v3","created_at":"2026-07-05T04:32:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.06506","created_at":"2026-07-05T04:32:25Z"},{"alias_kind":"pith_short_12","alias_value":"RICFXY3CW3T4","created_at":"2026-07-05T04:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"RICFXY3CW3T4OWDQ","created_at":"2026-07-05T04:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"RICFXY3C","created_at":"2026-07-05T04:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:7d557ebaf2a369fa2357e8096898316423983e3481ca2ee890eec463bdcd01b7","target":"graph","created_at":"2026-07-05T04:32:25Z","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/2105.06506/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Saliency methods are a popular class of feature attribution explanation methods that aim to capture a model's predictive reasoning by identifying \"important\" pixels in an input image. However, the development and adoption of these methods are hindered by the lack of access to ground-truth model reasoning, which prevents accurate evaluation. In this work, we design a synthetic benchmarking framework, SMERF, that allows us to perform ground-truth-based evaluation while controlling the complexity of the model's reasoning. Experimentally, SMERF reveals significant limitations in existing saliency ","authors_text":"Ameet Talwalkar, Gregory Plumb, Joon Sik Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-13T18:40:57Z","title":"Sanity Simulations for Saliency Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.06506","kind":"arxiv","version":3},"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":"sha256:455e315af33ea4c5957a75f2f3cee4d6e4571e397738dd0899cb778fa018456f","target":"record","created_at":"2026-07-05T04:32:25Z","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":"68705aa1aa58999608286b9bebf1038c9181d41b0d357673badb7ad4b6725bc9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-13T18:40:57Z","title_canon_sha256":"f38b4c1b4c12dd775ed1c0960d2f9a84654faa2d11ba3e8d337178bd1a0dfca5"},"schema_version":"1.0","source":{"id":"2105.06506","kind":"arxiv","version":3}},"canonical_sha256":"8a045be362b6e7c75870c9c2ea4624daf47e86aa639ee9f3d4d8f991da1e606c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a045be362b6e7c75870c9c2ea4624daf47e86aa639ee9f3d4d8f991da1e606c","first_computed_at":"2026-07-05T04:32:25.830699Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:32:25.830699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ulb3hUk/0JVWd8N9VAH329w4qL3TvWZrV2lybdtVXl3h+oJhSiHHS5q0pJAgF/4tpeGhxvwO2GLxnGSl9KviCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:32:25.831173Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.06506","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:455e315af33ea4c5957a75f2f3cee4d6e4571e397738dd0899cb778fa018456f","sha256:7d557ebaf2a369fa2357e8096898316423983e3481ca2ee890eec463bdcd01b7"],"state_sha256":"b0c009ea5b7b3e5088a8d7d9481e5371a22d5079ab162f366bd1491609388612"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HNOnohmryLy7l8MOqwQMcCD5/n1xXYRuIzQfE+5wWZGVd+jp8iM+hkWMhxuXyoYX1AiwlYxGewaND9D3741fDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:42:09.083655Z","bundle_sha256":"c3d79b5178389107d6c110fe3a2a6f77249a0415adf32ff5e921de3568095e30"}}