{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DIIC6UJHK34GFYIPA5Z6GOQE5Q","short_pith_number":"pith:DIIC6UJH","schema_version":"1.0","canonical_sha256":"1a102f512756f862e10f0773e33a04ec0954a382014886ab85b690a19c632182","source":{"kind":"arxiv","id":"2606.09046","version":1},"attestation_state":"computed","paper":{"title":"Decoy-Calibrated Failure Audits for Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.LG","authors_text":"Ameya Gawde, Harshvardhan Singh, Vyzantinos Repantis","submitted_at":"2026-06-08T05:33:03Z","abstract_excerpt":"Useful audits reveal not only how often a model fails, but also where its failures concentrate. An auditor may test many candidate explanations: long inputs, indirect questions, distracting evidence, or combinations of these factors. The risk is selection. The largest observed effect may reflect a real failure mode, or it may simply be the best result among many tried. We introduce Janus, a procedure for deciding when a proposed error explanation is credible enough to report. The goal is not to generate new explanations, but to decide which ones hold up. The auditor starts with a fixed model, "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.09046","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T05:33:03Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"424f1479c018906ac297a315f415292a5740be39a543f64a20a37795c6c3014c","abstract_canon_sha256":"a3c9f576710fc74223b7a74436def62ed98de70a3f326a104fee090ab3523ea1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:55.457930Z","signature_b64":"FedNZlWdq7iVxgL8G6aNny+X7H5FqP893vtQrK3ii1lW+/mGoOYt7aqNMNj0Yvn9jVxsGuiT19Em07eN8QLHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a102f512756f862e10f0773e33a04ec0954a382014886ab85b690a19c632182","last_reissued_at":"2026-06-09T02:07:55.457053Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:55.457053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoy-Calibrated Failure Audits for Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.LG","authors_text":"Ameya Gawde, Harshvardhan Singh, Vyzantinos Repantis","submitted_at":"2026-06-08T05:33:03Z","abstract_excerpt":"Useful audits reveal not only how often a model fails, but also where its failures concentrate. An auditor may test many candidate explanations: long inputs, indirect questions, distracting evidence, or combinations of these factors. The risk is selection. The largest observed effect may reflect a real failure mode, or it may simply be the best result among many tried. We introduce Janus, a procedure for deciding when a proposed error explanation is credible enough to report. The goal is not to generate new explanations, but to decide which ones hold up. The auditor starts with a fixed model, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09046","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/2606.09046/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.09046","created_at":"2026-06-09T02:07:55.457217+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09046v1","created_at":"2026-06-09T02:07:55.457217+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09046","created_at":"2026-06-09T02:07:55.457217+00:00"},{"alias_kind":"pith_short_12","alias_value":"DIIC6UJHK34G","created_at":"2026-06-09T02:07:55.457217+00:00"},{"alias_kind":"pith_short_16","alias_value":"DIIC6UJHK34GFYIP","created_at":"2026-06-09T02:07:55.457217+00:00"},{"alias_kind":"pith_short_8","alias_value":"DIIC6UJH","created_at":"2026-06-09T02:07:55.457217+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DIIC6UJHK34GFYIPA5Z6GOQE5Q","json":"https://pith.science/pith/DIIC6UJHK34GFYIPA5Z6GOQE5Q.json","graph_json":"https://pith.science/api/pith-number/DIIC6UJHK34GFYIPA5Z6GOQE5Q/graph.json","events_json":"https://pith.science/api/pith-number/DIIC6UJHK34GFYIPA5Z6GOQE5Q/events.json","paper":"https://pith.science/paper/DIIC6UJH"},"agent_actions":{"view_html":"https://pith.science/pith/DIIC6UJHK34GFYIPA5Z6GOQE5Q","download_json":"https://pith.science/pith/DIIC6UJHK34GFYIPA5Z6GOQE5Q.json","view_paper":"https://pith.science/paper/DIIC6UJH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09046&json=true","fetch_graph":"https://pith.science/api/pith-number/DIIC6UJHK34GFYIPA5Z6GOQE5Q/graph.json","fetch_events":"https://pith.science/api/pith-number/DIIC6UJHK34GFYIPA5Z6GOQE5Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DIIC6UJHK34GFYIPA5Z6GOQE5Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DIIC6UJHK34GFYIPA5Z6GOQE5Q/action/storage_attestation","attest_author":"https://pith.science/pith/DIIC6UJHK34GFYIPA5Z6GOQE5Q/action/author_attestation","sign_citation":"https://pith.science/pith/DIIC6UJHK34GFYIPA5Z6GOQE5Q/action/citation_signature","submit_replication":"https://pith.science/pith/DIIC6UJHK34GFYIPA5Z6GOQE5Q/action/replication_record"}},"created_at":"2026-06-09T02:07:55.457217+00:00","updated_at":"2026-06-09T02:07:55.457217+00:00"}