{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:VVQHGLXAFBSXXVLBJLIXIRIN4T","short_pith_number":"pith:VVQHGLXA","canonical_record":{"source":{"id":"1911.06473","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-11-15T04:20:11Z","cross_cats_sorted":[],"title_canon_sha256":"371cc27baf5aac81d969d7426b7464ac33be96bab15bdab231eba249f28993e6","abstract_canon_sha256":"243df4787119148fb4b47e0e2d6938abd3cf91d87559cde6dd9670f803c267b6"},"schema_version":"1.0"},"canonical_sha256":"ad60732ee028657bd5614ad174450de4cfbfecf21b4e21485d797b6c750dd6fc","source":{"kind":"arxiv","id":"1911.06473","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.06473","created_at":"2026-07-05T00:19:23Z"},{"alias_kind":"arxiv_version","alias_value":"1911.06473v1","created_at":"2026-07-05T00:19:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.06473","created_at":"2026-07-05T00:19:23Z"},{"alias_kind":"pith_short_12","alias_value":"VVQHGLXAFBSX","created_at":"2026-07-05T00:19:23Z"},{"alias_kind":"pith_short_16","alias_value":"VVQHGLXAFBSXXVLB","created_at":"2026-07-05T00:19:23Z"},{"alias_kind":"pith_short_8","alias_value":"VVQHGLXA","created_at":"2026-07-05T00:19:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:VVQHGLXAFBSXXVLBJLIXIRIN4T","target":"record","payload":{"canonical_record":{"source":{"id":"1911.06473","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-11-15T04:20:11Z","cross_cats_sorted":[],"title_canon_sha256":"371cc27baf5aac81d969d7426b7464ac33be96bab15bdab231eba249f28993e6","abstract_canon_sha256":"243df4787119148fb4b47e0e2d6938abd3cf91d87559cde6dd9670f803c267b6"},"schema_version":"1.0"},"canonical_sha256":"ad60732ee028657bd5614ad174450de4cfbfecf21b4e21485d797b6c750dd6fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:19:23.954482Z","signature_b64":"I+02/aP8irVwCN3MnT/ROj/XXBTJeNu5r+MdIzWjge2rdbZLDKQqBqyxBT0NMBS9jcfIwgF+w77Sfxc6+IgODw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad60732ee028657bd5614ad174450de4cfbfecf21b4e21485d797b6c750dd6fc","last_reissued_at":"2026-07-05T00:19:23.954068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:19:23.954068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.06473","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":"2026-07-05T00:19:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"188V1bftinZxjdhBs+Yo3rALxiIzaUKUjdVMW9r67n1JX+ZbpJFbMvqgytJm8wQjUB/3TEudIk7oamqVlFvkDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T20:19:53.758874Z"},"content_sha256":"401fc27876ba073bb80aa36bfd2d5e0e7930f3b121f8e3836850af24cf96f31c","schema_version":"1.0","event_id":"sha256:401fc27876ba073bb80aa36bfd2d5e0e7930f3b121f8e3836850af24cf96f31c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:VVQHGLXAFBSXXVLBJLIXIRIN4T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"\"How do I fool you?\": Manipulating User Trust via Misleading Black Box Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Himabindu Lakkaraju, Osbert Bastani","submitted_at":"2019-11-15T04:20:11Z","abstract_excerpt":"As machine learning black boxes are increasingly being deployed in critical domains such as healthcare and criminal justice, there has been a growing emphasis on developing techniques for explaining these black boxes in a human interpretable manner. It has recently become apparent that a high-fidelity explanation of a black box ML model may not accurately reflect the biases in the black box. As a consequence, explanations have the potential to mislead human users into trusting a problematic black box. In this work, we rigorously explore the notion of misleading explanations and how they influe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.06473","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/1911.06473/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":"2026-07-05T00:19:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IqE38XIYD4l4HbzFlqTs6MdmMh7aYvoaq0+/zt2/q96czpVPGxa745WQvuu+7wqAS35TfzAc1Lz9T/0kqllLAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T20:19:53.759872Z"},"content_sha256":"d3543eeb1d213ce9f1980956e473047520662ac6d069c660c63c9bcfbdc74a58","schema_version":"1.0","event_id":"sha256:d3543eeb1d213ce9f1980956e473047520662ac6d069c660c63c9bcfbdc74a58"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VVQHGLXAFBSXXVLBJLIXIRIN4T/bundle.json","state_url":"https://pith.science/pith/VVQHGLXAFBSXXVLBJLIXIRIN4T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VVQHGLXAFBSXXVLBJLIXIRIN4T/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":"2026-08-12T20:19:53Z","links":{"resolver":"https://pith.science/pith/VVQHGLXAFBSXXVLBJLIXIRIN4T","bundle":"https://pith.science/pith/VVQHGLXAFBSXXVLBJLIXIRIN4T/bundle.json","state":"https://pith.science/pith/VVQHGLXAFBSXXVLBJLIXIRIN4T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VVQHGLXAFBSXXVLBJLIXIRIN4T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:VVQHGLXAFBSXXVLBJLIXIRIN4T","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":"243df4787119148fb4b47e0e2d6938abd3cf91d87559cde6dd9670f803c267b6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-11-15T04:20:11Z","title_canon_sha256":"371cc27baf5aac81d969d7426b7464ac33be96bab15bdab231eba249f28993e6"},"schema_version":"1.0","source":{"id":"1911.06473","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.06473","created_at":"2026-07-05T00:19:23Z"},{"alias_kind":"arxiv_version","alias_value":"1911.06473v1","created_at":"2026-07-05T00:19:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.06473","created_at":"2026-07-05T00:19:23Z"},{"alias_kind":"pith_short_12","alias_value":"VVQHGLXAFBSX","created_at":"2026-07-05T00:19:23Z"},{"alias_kind":"pith_short_16","alias_value":"VVQHGLXAFBSXXVLB","created_at":"2026-07-05T00:19:23Z"},{"alias_kind":"pith_short_8","alias_value":"VVQHGLXA","created_at":"2026-07-05T00:19:23Z"}],"graph_snapshots":[{"event_id":"sha256:d3543eeb1d213ce9f1980956e473047520662ac6d069c660c63c9bcfbdc74a58","target":"graph","created_at":"2026-07-05T00:19:23Z","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/1911.06473/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As machine learning black boxes are increasingly being deployed in critical domains such as healthcare and criminal justice, there has been a growing emphasis on developing techniques for explaining these black boxes in a human interpretable manner. It has recently become apparent that a high-fidelity explanation of a black box ML model may not accurately reflect the biases in the black box. As a consequence, explanations have the potential to mislead human users into trusting a problematic black box. In this work, we rigorously explore the notion of misleading explanations and how they influe","authors_text":"Himabindu Lakkaraju, Osbert Bastani","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-11-15T04:20:11Z","title":"\"How do I fool you?\": Manipulating User Trust via Misleading Black Box Explanations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.06473","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":"sha256:401fc27876ba073bb80aa36bfd2d5e0e7930f3b121f8e3836850af24cf96f31c","target":"record","created_at":"2026-07-05T00:19:23Z","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":"243df4787119148fb4b47e0e2d6938abd3cf91d87559cde6dd9670f803c267b6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-11-15T04:20:11Z","title_canon_sha256":"371cc27baf5aac81d969d7426b7464ac33be96bab15bdab231eba249f28993e6"},"schema_version":"1.0","source":{"id":"1911.06473","kind":"arxiv","version":1}},"canonical_sha256":"ad60732ee028657bd5614ad174450de4cfbfecf21b4e21485d797b6c750dd6fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad60732ee028657bd5614ad174450de4cfbfecf21b4e21485d797b6c750dd6fc","first_computed_at":"2026-07-05T00:19:23.954068Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:19:23.954068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I+02/aP8irVwCN3MnT/ROj/XXBTJeNu5r+MdIzWjge2rdbZLDKQqBqyxBT0NMBS9jcfIwgF+w77Sfxc6+IgODw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:19:23.954482Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.06473","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:401fc27876ba073bb80aa36bfd2d5e0e7930f3b121f8e3836850af24cf96f31c","sha256:d3543eeb1d213ce9f1980956e473047520662ac6d069c660c63c9bcfbdc74a58"],"state_sha256":"c6d230318404f1b34f06e9bfd5cadbffe2d4707d60617d5dfb38023ca080649a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"su/RZDVDQY3/2lxHbwrHTgrOucauQtCHijefajDADKGlehjYblTvmw92L0EhRWyOt4oqeauN9cRm0gY9/rlWAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T20:19:53.766832Z","bundle_sha256":"258f5a7c1d7facda33bec6eafd10545932964d60c1cf6926900f02e5614f22e5"}}