{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F5X7JSFI5VTT3HFJVPYXSKR33R","short_pith_number":"pith:F5X7JSFI","schema_version":"1.0","canonical_sha256":"2f6ff4c8a8ed673d9ca9abf1792a3bdc73bd12c42f53f645a94850b3fec3b427","source":{"kind":"arxiv","id":"2605.12674","version":1},"attestation_state":"computed","paper":{"title":"Revealing Interpretable Failure Modes of VLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"REVELIO uncovers interpretable concept compositions that cause consistent failures in vision-language models.","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Gagandeep Singh, Isha Chaudhary, Kavya Sachdeva, Sayan Ranu, Vedaant V Jain","submitted_at":"2026-05-12T19:25:17Z","abstract_excerpt":"Vision-Language Models (VLMs) are increasingly used in safety-critical applications because of their broad reasoning capabilities and ability to generalize with minimal task-specific engineering. Despite these advantages, they can exhibit catastrophic failures in specific real-world situations, constituting failure modes.\n  We introduce REVELIO, a framework for systematically uncovering interpretable failure modes in VLMs. We define a failure mode as a composition of interpretable, domain-relevant concepts-such as pedestrian proximity or adverse weather conditions-under which a target VLM cons"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.12674","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T19:25:17Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"f08dd3004bd6c564804105a7d1f54d3e55105fa59590bbcacd6d209e926929a9","abstract_canon_sha256":"1c84029d03a85e273726e1ff54bc6df01590e0d1f25403f03d84ad349082b78c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:50.101504Z","signature_b64":"i6/n2hOEjLFSMxqsIrWQfMjx8QSSBK5WH60NCWEzQJbU1s7ywtXYmft0XEC79kHbXi73QNZSqIo4OtjTIK8CCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f6ff4c8a8ed673d9ca9abf1792a3bdc73bd12c42f53f645a94850b3fec3b427","last_reissued_at":"2026-05-18T03:09:50.100529Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:50.100529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revealing Interpretable Failure Modes of VLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"REVELIO uncovers interpretable concept compositions that cause consistent failures in vision-language models.","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Gagandeep Singh, Isha Chaudhary, Kavya Sachdeva, Sayan Ranu, Vedaant V Jain","submitted_at":"2026-05-12T19:25:17Z","abstract_excerpt":"Vision-Language Models (VLMs) are increasingly used in safety-critical applications because of their broad reasoning capabilities and ability to generalize with minimal task-specific engineering. Despite these advantages, they can exhibit catastrophic failures in specific real-world situations, constituting failure modes.\n  We introduce REVELIO, a framework for systematically uncovering interpretable failure modes in VLMs. We define a failure mode as a composition of interpretable, domain-relevant concepts-such as pedestrian proximity or adverse weather conditions-under which a target VLM cons"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We introduce REVELIO, a framework for systematically uncovering interpretable failure modes in VLMs... uncovering previously unreported vulnerabilities in state-of-the-art VLMs.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the searched concept compositions correspond to genuine, consistent real-world failure modes rather than artifacts of the simulation or search heuristics.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"REVELIO uncovers interpretable failure modes in VLMs by searching combinatorial concept spaces with diversity-aware beam search and Gaussian-process Thompson sampling, revealing vulnerabilities in autonomous driving and indoor robotics.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"REVELIO uncovers interpretable concept compositions that cause consistent failures in vision-language models.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5ee097f560c6dabd233b8134cd5222b6336b1b5393f3603f4a39ca5d910995b8"},"source":{"id":"2605.12674","kind":"arxiv","version":1},"verdict":{"id":"963a4c7c-278c-48e5-8987-37b50bf4cf64","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:24:46.550617Z","strongest_claim":"We introduce REVELIO, a framework for systematically uncovering interpretable failure modes in VLMs... uncovering previously unreported vulnerabilities in state-of-the-art VLMs.","one_line_summary":"REVELIO uncovers interpretable failure modes in VLMs by searching combinatorial concept spaces with diversity-aware beam search and Gaussian-process Thompson sampling, revealing vulnerabilities in autonomous driving and indoor robotics.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the searched concept compositions correspond to genuine, consistent real-world failure modes rather than artifacts of the simulation or search heuristics.","pith_extraction_headline":"REVELIO uncovers interpretable concept compositions that cause consistent failures in vision-language models."},"references":{"count":222,"sample":[{"doi":"","year":2025,"title":"Claude Sonnet","work_id":"f55b445a-ab6e-4e4d-b496-c3a74994d3ed","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Large language model-assisted autonomous vehicle recovery from immobilization, 2025","work_id":"0ffe6562-93d4-4fef-8d21-e5d1e61a4cba","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1998,"title":"The use of mmr, diversity-based reranking for reordering documents and producing summaries","work_id":"98357628-52da-45c9-8f07-1e7de5d019ca","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Gonzalez, and Ion Stoica","work_id":"7b049cb6-6a65-4610-bb33-d5863d8ae9eb","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Kevin Kai-Chun Chang, Ekin Beyazit, Alberto Sangiovanni-Vincentelli, Tichakorn Wongpirom- sarn, and Sanjit A. Seshia. Scenicrules: An autonomous driving benchmark with multi-objective specifications a","work_id":"34756ee5-9047-48e6-94a2-0bdd3a67767f","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":222,"snapshot_sha256":"7612c06159f671a97d092a461973de24bd8ddc6736d7d64bca477774a45c3ecc","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"72f7a87453b88f76e969da74fd45d0ed54029c0c5b87df5101475dcdfa1bd8c9"},"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":"2605.12674","created_at":"2026-05-18T03:09:50.100653+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.12674v1","created_at":"2026-05-18T03:09:50.100653+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12674","created_at":"2026-05-18T03:09:50.100653+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5X7JSFI5VTT","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5X7JSFI5VTT3HFJ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5X7JSFI","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F5X7JSFI5VTT3HFJVPYXSKR33R","json":"https://pith.science/pith/F5X7JSFI5VTT3HFJVPYXSKR33R.json","graph_json":"https://pith.science/api/pith-number/F5X7JSFI5VTT3HFJVPYXSKR33R/graph.json","events_json":"https://pith.science/api/pith-number/F5X7JSFI5VTT3HFJVPYXSKR33R/events.json","paper":"https://pith.science/paper/F5X7JSFI"},"agent_actions":{"view_html":"https://pith.science/pith/F5X7JSFI5VTT3HFJVPYXSKR33R","download_json":"https://pith.science/pith/F5X7JSFI5VTT3HFJVPYXSKR33R.json","view_paper":"https://pith.science/paper/F5X7JSFI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.12674&json=true","fetch_graph":"https://pith.science/api/pith-number/F5X7JSFI5VTT3HFJVPYXSKR33R/graph.json","fetch_events":"https://pith.science/api/pith-number/F5X7JSFI5VTT3HFJVPYXSKR33R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5X7JSFI5VTT3HFJVPYXSKR33R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5X7JSFI5VTT3HFJVPYXSKR33R/action/storage_attestation","attest_author":"https://pith.science/pith/F5X7JSFI5VTT3HFJVPYXSKR33R/action/author_attestation","sign_citation":"https://pith.science/pith/F5X7JSFI5VTT3HFJVPYXSKR33R/action/citation_signature","submit_replication":"https://pith.science/pith/F5X7JSFI5VTT3HFJVPYXSKR33R/action/replication_record"}},"created_at":"2026-05-18T03:09:50.100653+00:00","updated_at":"2026-05-18T03:09:50.100653+00:00"}