{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OQTYUJZCCUB337M3Q7WKPBW4SD","short_pith_number":"pith:OQTYUJZC","canonical_record":{"source":{"id":"2607.14152","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2026-07-14T17:48:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"44f49a4c75d29b357c3a15e247eefdbf8a20b14e3f3711c3a095bb70dfa50b76","abstract_canon_sha256":"e785ff30e88bf1531fc2f0722b40ec9a9a80ace64cd4d08d6be3eefefcf7ed9a"},"schema_version":"1.0"},"canonical_sha256":"74278a27221503bdfd9b87eca786dc90e69748778c97823ce073a3c4140a519f","source":{"kind":"arxiv","id":"2607.14152","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14152","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14152v1","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14152","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"pith_short_12","alias_value":"OQTYUJZCCUB3","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"pith_short_16","alias_value":"OQTYUJZCCUB337M3","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"pith_short_8","alias_value":"OQTYUJZC","created_at":"2026-07-17T00:20:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OQTYUJZCCUB337M3Q7WKPBW4SD","target":"record","payload":{"canonical_record":{"source":{"id":"2607.14152","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2026-07-14T17:48:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"44f49a4c75d29b357c3a15e247eefdbf8a20b14e3f3711c3a095bb70dfa50b76","abstract_canon_sha256":"e785ff30e88bf1531fc2f0722b40ec9a9a80ace64cd4d08d6be3eefefcf7ed9a"},"schema_version":"1.0"},"canonical_sha256":"74278a27221503bdfd9b87eca786dc90e69748778c97823ce073a3c4140a519f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T00:20:54.173306Z","signature_b64":"NhJXsIpEH3sApGlX9cOLZO59hRBw1x7IeaCblxoohqJAYSR3M2Wq0hQErDRHxLWCHF10tJDcE180lbUqGAy2Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74278a27221503bdfd9b87eca786dc90e69748778c97823ce073a3c4140a519f","last_reissued_at":"2026-07-17T00:20:54.172451Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T00:20:54.172451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.14152","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":"2026-07-17T00:20:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/rRoS9ii5KFvIFeInszPYvBTot4H7S0eL8RRSEDVavv04HdmQKdEto0kLMjk/GsxSIvy/KDyeCu4nkSXLgfdBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T20:30:56.623011Z"},"content_sha256":"523319a548990375be25a39301d7490b88a38e659d27b7aadd7e6d68b04df636","schema_version":"1.0","event_id":"sha256:523319a548990375be25a39301d7490b88a38e659d27b7aadd7e6d68b04df636"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OQTYUJZCCUB337M3Q7WKPBW4SD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"\"Trust Junk\" Leads to Unjustified Support for Highly Discriminatory Predictive Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Lucy Havens, Mahsan Nourani, Michael Correll","submitted_at":"2026-07-14T17:48:35Z","abstract_excerpt":"The persuasive power of data visualizations can go awry: for instance, in an explainable AI (XAI) context, visualizations can produce over-trust of predictive models. In this paper, we use a crowdsourced study to show that providing accurate (but superfluous or irrelevant) data in a model explanation can, in fact, result in unjustified trust and other positive beliefs about a model, even when the model is patently discriminatory and unfair. Our results suggest that XAI designers and developers need to consider the implicit or explicit rhetorics of their work, and beware of the potential of vis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14152","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/2607.14152/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":"2026-07-17T00:20:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"81nIVMMrdTcFM/ShUvjGEkjqgFKjPWyPbqHoQ1QJ2b91VpclugDlE3p4YYCDz0v/9SEN9ZjXLRxoxWiIVK8aDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T20:30:56.623550Z"},"content_sha256":"ce94542bb4e8a0d43e5d0108d5b46d6a996059a596d73de58754842a25d69914","schema_version":"1.0","event_id":"sha256:ce94542bb4e8a0d43e5d0108d5b46d6a996059a596d73de58754842a25d69914"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:OQTYUJZCCUB337M3Q7WKPBW4SD","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1038/s41398-021-01224-x) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"M. Jacobs, M. F. Pradier, T. H. McCoy Jr, R. H. Perlis, F. Doshi-Velez, and K. Z. Gajos. How machine-learning recommendations influence clinician treatment selections: the example of antidepressant selection. Translational psychiatry, 11(1)","arxiv_id":"2607.14152","detector":"doi_compliance","evidence":{"ref_index":18,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1038/s41398-021","reconstructed_doi":"10.1038/s41398-021-01224-x"},"severity":"advisory","ref_index":18,"audited_at":"2026-08-02T06:21:04.117006Z","event_type":"pith.integrity.v1","detected_doi":"10.1038/s41398-021-01224-x","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"014535c1f339d362c67d7e207ccb17f8dd7bed807c3b24a490c7e5b3f72eb45b","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":17339,"payload_sha256":"8ca238e6f07bacc4e25d4e1f09682d588853c89f543cc5affaea181795f6140b","signature_b64":"gOUiwOPfSyoE3aGKXsyPpe68uCgGCpuI2IqJZCx8M8fyGo2Y8bZKsMRNsFbP8XFYNNFa2eatTUNdvNj5+jCiAw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-02T06:23:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5DzvcN4jVkcB3wv5Uxma6Vs3GcJCtddfgIVhnBlgmCPsyvTO6mEKDw1FfkUKziSHDbjTkudLIQG+4k+jKq6CBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T20:30:56.628261Z"},"content_sha256":"94f48e92e733f36537f8d0fdbb83613b700ddc7d28c246cfd277476d77a53dad","schema_version":"1.0","event_id":"sha256:94f48e92e733f36537f8d0fdbb83613b700ddc7d28c246cfd277476d77a53dad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OQTYUJZCCUB337M3Q7WKPBW4SD/bundle.json","state_url":"https://pith.science/pith/OQTYUJZCCUB337M3Q7WKPBW4SD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OQTYUJZCCUB337M3Q7WKPBW4SD/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":"2026-08-15T20:30:56Z","links":{"resolver":"https://pith.science/pith/OQTYUJZCCUB337M3Q7WKPBW4SD","bundle":"https://pith.science/pith/OQTYUJZCCUB337M3Q7WKPBW4SD/bundle.json","state":"https://pith.science/pith/OQTYUJZCCUB337M3Q7WKPBW4SD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OQTYUJZCCUB337M3Q7WKPBW4SD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OQTYUJZCCUB337M3Q7WKPBW4SD","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e785ff30e88bf1531fc2f0722b40ec9a9a80ace64cd4d08d6be3eefefcf7ed9a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2026-07-14T17:48:35Z","title_canon_sha256":"44f49a4c75d29b357c3a15e247eefdbf8a20b14e3f3711c3a095bb70dfa50b76"},"schema_version":"1.0","source":{"id":"2607.14152","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14152","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14152v1","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14152","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"pith_short_12","alias_value":"OQTYUJZCCUB3","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"pith_short_16","alias_value":"OQTYUJZCCUB337M3","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"pith_short_8","alias_value":"OQTYUJZC","created_at":"2026-07-17T00:20:54Z"}],"graph_snapshots":[{"event_id":"sha256:ce94542bb4e8a0d43e5d0108d5b46d6a996059a596d73de58754842a25d69914","target":"graph","created_at":"2026-07-17T00:20:54Z","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/2607.14152/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The persuasive power of data visualizations can go awry: for instance, in an explainable AI (XAI) context, visualizations can produce over-trust of predictive models. In this paper, we use a crowdsourced study to show that providing accurate (but superfluous or irrelevant) data in a model explanation can, in fact, result in unjustified trust and other positive beliefs about a model, even when the model is patently discriminatory and unfair. Our results suggest that XAI designers and developers need to consider the implicit or explicit rhetorics of their work, and beware of the potential of vis","authors_text":"Lucy Havens, Mahsan Nourani, Michael Correll","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2026-07-14T17:48:35Z","title":"\"Trust Junk\" Leads to Unjustified Support for Highly Discriminatory Predictive Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14152","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":"sha256:523319a548990375be25a39301d7490b88a38e659d27b7aadd7e6d68b04df636","target":"record","created_at":"2026-07-17T00:20:54Z","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":"e785ff30e88bf1531fc2f0722b40ec9a9a80ace64cd4d08d6be3eefefcf7ed9a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2026-07-14T17:48:35Z","title_canon_sha256":"44f49a4c75d29b357c3a15e247eefdbf8a20b14e3f3711c3a095bb70dfa50b76"},"schema_version":"1.0","source":{"id":"2607.14152","kind":"arxiv","version":1}},"canonical_sha256":"74278a27221503bdfd9b87eca786dc90e69748778c97823ce073a3c4140a519f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74278a27221503bdfd9b87eca786dc90e69748778c97823ce073a3c4140a519f","first_computed_at":"2026-07-17T00:20:54.172451Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T00:20:54.172451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NhJXsIpEH3sApGlX9cOLZO59hRBw1x7IeaCblxoohqJAYSR3M2Wq0hQErDRHxLWCHF10tJDcE180lbUqGAy2Cw==","signature_status":"signed_v1","signed_at":"2026-07-17T00:20:54.173306Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.14152","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:523319a548990375be25a39301d7490b88a38e659d27b7aadd7e6d68b04df636","sha256:ce94542bb4e8a0d43e5d0108d5b46d6a996059a596d73de58754842a25d69914","sha256:94f48e92e733f36537f8d0fdbb83613b700ddc7d28c246cfd277476d77a53dad"],"state_sha256":"004be671508403ec7d73b627e1ee501e8365d105ecd22f6c302b3d742cb380aa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hS5Gvv05xTHT7iTJVAjLcw8ENRh3gK9aO5XX1A6FEhIoPpVeBOH9C/fp56kpgpeFCeTSZKPm3V71JNVIEzUeAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T20:30:56.630623Z","bundle_sha256":"d2527ca27630a30e7da5036b77c4a334ac73c3bf1d0454da126feab2db5bfe2c"}}