{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GTPZI2U66RREXMND4TVXBFAEHV","short_pith_number":"pith:GTPZI2U6","schema_version":"1.0","canonical_sha256":"34df946a9ef4624bb1a3e4eb7094043d7c1f6cdb0f5b60b7a2d716c0224d5671","source":{"kind":"arxiv","id":"2605.10408","version":2},"attestation_state":"computed","paper":{"title":"VISOR: A Vision-Language Model-based Test Oracle for Testing Robots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"VISOR uses vision-language models to automatically score robot task correctness, quality, and uncertainty from videos.","cross_cats":["cs.RO"],"primary_cat":"cs.SE","authors_text":"Aitor Arrieta, Pablo Valle, Paolo Arcaini, Prasun Saurabh, Shaukat Ali","submitted_at":"2026-05-11T11:46:57Z","abstract_excerpt":"Testing robots requires assessing whether they perform their intended tasks correctly, dependably, and with high quality, a challenge known as the test oracle problem in software testing. Traditionally, this assessment relies on task-specific symbolic oracles for task correctness and on human manual evaluation of robot behavior, which is time-consuming, subjective, and error-prone. To address this, we propose VISOR, a Vision-Language Model (VLM)-based approach for automated test oracle assessment that eliminates the need of expensive human evaluations. VISOR performs automated evaluation of ta"},"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":true},"canonical_record":{"source":{"id":"2605.10408","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-11T11:46:57Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"1599b5322227c8656f71f69588cecc589c9565f0ee2e7eb656639c6dd0aed675","abstract_canon_sha256":"f53a59a7f98ab23fcbaedf5b5f1e4342efe241fe944c3c0ebe1a527eb93217be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:16.797725Z","signature_b64":"PEYcyarkhUeMURCamG+SCIhT+N6yZMq+wzytiHr3EwCRBrxVT/mQDEvWe0HFofmC7GhEOmzRHrXTdOJfGIw+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34df946a9ef4624bb1a3e4eb7094043d7c1f6cdb0f5b60b7a2d716c0224d5671","last_reissued_at":"2026-05-20T00:03:16.796682Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:16.796682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VISOR: A Vision-Language Model-based Test Oracle for Testing Robots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"VISOR uses vision-language models to automatically score robot task correctness, quality, and uncertainty from videos.","cross_cats":["cs.RO"],"primary_cat":"cs.SE","authors_text":"Aitor Arrieta, Pablo Valle, Paolo Arcaini, Prasun Saurabh, Shaukat Ali","submitted_at":"2026-05-11T11:46:57Z","abstract_excerpt":"Testing robots requires assessing whether they perform their intended tasks correctly, dependably, and with high quality, a challenge known as the test oracle problem in software testing. Traditionally, this assessment relies on task-specific symbolic oracles for task correctness and on human manual evaluation of robot behavior, which is time-consuming, subjective, and error-prone. To address this, we propose VISOR, a Vision-Language Model (VLM)-based approach for automated test oracle assessment that eliminates the need of expensive human evaluations. VISOR performs automated evaluation of ta"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"VISOR performs automated evaluation of task correctness and quality, addressing the limitations of existing symbolic test oracles, which are task-specific and provide pass/fail judgments without explicitly quantifying task quality. Given the inherent uncertainty in VLMs, VISOR also explicitly quantifies its own uncertainty during test assessments.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That off-the-shelf vision-language models can accurately interpret and score complex, dynamic robot behaviors in videos without task-specific fine-tuning or symbolic grounding.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"VISOR applies VLMs to automate robot test oracles for correctness and quality assessment while reporting uncertainty, with evaluation on GPT and Gemini showing trade-offs in precision and recall but poor uncertainty calibration.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"VISOR uses vision-language models to automatically score robot task correctness, quality, and uncertainty from videos.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0f5bcdb1d242da8db8a1aea28a207eacab06badbdeacefceed3440a8d0ee0ef9"},"source":{"id":"2605.10408","kind":"arxiv","version":2},"verdict":{"id":"6dab8467-76c3-4365-9f96-55e50c56b1cf","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T05:13:20.417354Z","strongest_claim":"VISOR performs automated evaluation of task correctness and quality, addressing the limitations of existing symbolic test oracles, which are task-specific and provide pass/fail judgments without explicitly quantifying task quality. Given the inherent uncertainty in VLMs, VISOR also explicitly quantifies its own uncertainty during test assessments.","one_line_summary":"VISOR applies VLMs to automate robot test oracles for correctness and quality assessment while reporting uncertainty, with evaluation on GPT and Gemini showing trade-offs in precision and recall but poor uncertainty calibration.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That off-the-shelf vision-language models can accurately interpret and score complex, dynamic robot behaviors in videos without task-specific fine-tuning or symbolic grounding.","pith_extraction_headline":"VISOR uses vision-language models to automatically score robot task correctness, quality, and uncertainty from videos."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.10408/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T15:34:08.894681Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T11:31:18.101957Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T09:22:33.475475Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"00eb4d315217eab646312c45e8a3ee052af60aab2f428f7336b3a3ac98248d49"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":3,"snapshot_sha256":"abfe402594a550b644f7fb29f18e0e3cf86886ff208985794256136ff1216a74"},"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":"2605.10408","created_at":"2026-05-20T00:03:16.796815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.10408v2","created_at":"2026-05-20T00:03:16.796815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10408","created_at":"2026-05-20T00:03:16.796815+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTPZI2U66RRE","created_at":"2026-05-20T00:03:16.796815+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTPZI2U66RREXMND","created_at":"2026-05-20T00:03:16.796815+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTPZI2U6","created_at":"2026-05-20T00:03:16.796815+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":3,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GTPZI2U66RREXMND4TVXBFAEHV","json":"https://pith.science/pith/GTPZI2U66RREXMND4TVXBFAEHV.json","graph_json":"https://pith.science/api/pith-number/GTPZI2U66RREXMND4TVXBFAEHV/graph.json","events_json":"https://pith.science/api/pith-number/GTPZI2U66RREXMND4TVXBFAEHV/events.json","paper":"https://pith.science/paper/GTPZI2U6"},"agent_actions":{"view_html":"https://pith.science/pith/GTPZI2U66RREXMND4TVXBFAEHV","download_json":"https://pith.science/pith/GTPZI2U66RREXMND4TVXBFAEHV.json","view_paper":"https://pith.science/paper/GTPZI2U6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.10408&json=true","fetch_graph":"https://pith.science/api/pith-number/GTPZI2U66RREXMND4TVXBFAEHV/graph.json","fetch_events":"https://pith.science/api/pith-number/GTPZI2U66RREXMND4TVXBFAEHV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTPZI2U66RREXMND4TVXBFAEHV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTPZI2U66RREXMND4TVXBFAEHV/action/storage_attestation","attest_author":"https://pith.science/pith/GTPZI2U66RREXMND4TVXBFAEHV/action/author_attestation","sign_citation":"https://pith.science/pith/GTPZI2U66RREXMND4TVXBFAEHV/action/citation_signature","submit_replication":"https://pith.science/pith/GTPZI2U66RREXMND4TVXBFAEHV/action/replication_record"}},"created_at":"2026-05-20T00:03:16.796815+00:00","updated_at":"2026-05-20T00:03:16.796815+00:00"}