{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GTPZI2U66RREXMND4TVXBFAEHV","short_pith_number":"pith:GTPZI2U6","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"},"canonical_sha256":"34df946a9ef4624bb1a3e4eb7094043d7c1f6cdb0f5b60b7a2d716c0224d5671","source":{"kind":"arxiv","id":"2605.10408","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.10408","created_at":"2026-05-20T00:03:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.10408v2","created_at":"2026-05-20T00:03:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10408","created_at":"2026-05-20T00:03:16Z"},{"alias_kind":"pith_short_12","alias_value":"GTPZI2U66RRE","created_at":"2026-05-20T00:03:16Z"},{"alias_kind":"pith_short_16","alias_value":"GTPZI2U66RREXMND","created_at":"2026-05-20T00:03:16Z"},{"alias_kind":"pith_short_8","alias_value":"GTPZI2U6","created_at":"2026-05-20T00:03:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GTPZI2U66RREXMND4TVXBFAEHV","target":"record","payload":{"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"},"canonical_sha256":"34df946a9ef4624bb1a3e4eb7094043d7c1f6cdb0f5b60b7a2d716c0224d5671","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"},"source_kind":"arxiv","source_id":"2605.10408","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:03:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tF/O+9pvaqlGSdk/6nwmRH/ARVE/vA57Utj9kjJcEzrBBNIeRGcHh4sN43hWsY7n0EqTiwtl7RSEF6Pc4c7ACg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T02:39:47.316645Z"},"content_sha256":"be85e3e2b45b1e1ef22340fba5cf9c2417c6f8eabcfd68826213ce12a46b7efc","schema_version":"1.0","event_id":"sha256:be85e3e2b45b1e1ef22340fba5cf9c2417c6f8eabcfd68826213ce12a46b7efc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GTPZI2U66RREXMND4TVXBFAEHV","target":"graph","payload":{"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"},"verdict_id":"6dab8467-76c3-4365-9f96-55e50c56b1cf"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:03:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i0Q/gGu+DK3Osivaz3BRLOGNRIDwDsv8rxqzc0IHolx/MBTnmxfdMzP1nApWgpAjV++7SVvnOSbzpX5QuzA6Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T02:39:47.317586Z"},"content_sha256":"01f3a6fd1d5ef696c1a5f37701e1731d7be18b464d9cb64e2c473eeb8d26e285","schema_version":"1.0","event_id":"sha256:01f3a6fd1d5ef696c1a5f37701e1731d7be18b464d9cb64e2c473eeb8d26e285"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GTPZI2U66RREXMND4TVXBFAEHV/bundle.json","state_url":"https://pith.science/pith/GTPZI2U66RREXMND4TVXBFAEHV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GTPZI2U66RREXMND4TVXBFAEHV/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":"2026-06-09T02:39:47Z","links":{"resolver":"https://pith.science/pith/GTPZI2U66RREXMND4TVXBFAEHV","bundle":"https://pith.science/pith/GTPZI2U66RREXMND4TVXBFAEHV/bundle.json","state":"https://pith.science/pith/GTPZI2U66RREXMND4TVXBFAEHV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GTPZI2U66RREXMND4TVXBFAEHV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GTPZI2U66RREXMND4TVXBFAEHV","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":"f53a59a7f98ab23fcbaedf5b5f1e4342efe241fe944c3c0ebe1a527eb93217be","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-11T11:46:57Z","title_canon_sha256":"1599b5322227c8656f71f69588cecc589c9565f0ee2e7eb656639c6dd0aed675"},"schema_version":"1.0","source":{"id":"2605.10408","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.10408","created_at":"2026-05-20T00:03:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.10408v2","created_at":"2026-05-20T00:03:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10408","created_at":"2026-05-20T00:03:16Z"},{"alias_kind":"pith_short_12","alias_value":"GTPZI2U66RRE","created_at":"2026-05-20T00:03:16Z"},{"alias_kind":"pith_short_16","alias_value":"GTPZI2U66RREXMND","created_at":"2026-05-20T00:03:16Z"},{"alias_kind":"pith_short_8","alias_value":"GTPZI2U6","created_at":"2026-05-20T00:03:16Z"}],"graph_snapshots":[{"event_id":"sha256:01f3a6fd1d5ef696c1a5f37701e1731d7be18b464d9cb64e2c473eeb8d26e285","target":"graph","created_at":"2026-05-20T00:03:16Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"VISOR uses vision-language models to automatically score robot task correctness, quality, and uncertainty from videos."}],"snapshot_sha256":"0f5bcdb1d242da8db8a1aea28a207eacab06badbdeacefceed3440a8d0ee0ef9"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"abfe402594a550b644f7fb29f18e0e3cf86886ff208985794256136ff1216a74"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.10408/integrity.json","findings":[],"snapshot_sha256":"00eb4d315217eab646312c45e8a3ee052af60aab2f428f7336b3a3ac98248d49","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aitor Arrieta, Pablo Valle, Paolo Arcaini, Prasun Saurabh, Shaukat Ali","cross_cats":["cs.RO"],"headline":"VISOR uses vision-language models to automatically score robot task correctness, quality, and uncertainty from videos.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-11T11:46:57Z","title":"VISOR: A Vision-Language Model-based Test Oracle for Testing Robots"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.10408","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T05:13:20.417354Z","id":"6dab8467-76c3-4365-9f96-55e50c56b1cf","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"VISOR uses vision-language models to automatically score robot task correctness, quality, and uncertainty from videos.","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.","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."}},"verdict_id":"6dab8467-76c3-4365-9f96-55e50c56b1cf"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:be85e3e2b45b1e1ef22340fba5cf9c2417c6f8eabcfd68826213ce12a46b7efc","target":"record","created_at":"2026-05-20T00:03:16Z","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":"f53a59a7f98ab23fcbaedf5b5f1e4342efe241fe944c3c0ebe1a527eb93217be","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-11T11:46:57Z","title_canon_sha256":"1599b5322227c8656f71f69588cecc589c9565f0ee2e7eb656639c6dd0aed675"},"schema_version":"1.0","source":{"id":"2605.10408","kind":"arxiv","version":2}},"canonical_sha256":"34df946a9ef4624bb1a3e4eb7094043d7c1f6cdb0f5b60b7a2d716c0224d5671","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34df946a9ef4624bb1a3e4eb7094043d7c1f6cdb0f5b60b7a2d716c0224d5671","first_computed_at":"2026-05-20T00:03:16.796682Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:16.796682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PEYcyarkhUeMURCamG+SCIhT+N6yZMq+wzytiHr3EwCRBrxVT/mQDEvWe0HFofmC7GhEOmzRHrXTdOJfGIw+Cg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:16.797725Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.10408","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be85e3e2b45b1e1ef22340fba5cf9c2417c6f8eabcfd68826213ce12a46b7efc","sha256:01f3a6fd1d5ef696c1a5f37701e1731d7be18b464d9cb64e2c473eeb8d26e285"],"state_sha256":"326850d167339c85847fab9222f2d81e5addd795576af813c72d466295d15f9f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YTuZydE7N0R/rn8fxULeTl1s2tU8cfJMZh7uRCkNBw4xEkKGqU3COFjCEYnNFPJK1yz4yQannpJq42o+OBGZAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T02:39:47.322336Z","bundle_sha256":"c52f4d6c2a1bf46601a8b66a6666313bca94af10c1cd3b68bc42a215b9a5e99c"}}