{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CSGTW4RVAW7CTIDHNYHUA64ITD","short_pith_number":"pith:CSGTW4RV","schema_version":"1.0","canonical_sha256":"148d3b723505be29a0676e0f407b8898c90ba719a39dfa46b6910bc4b3b8c1b5","source":{"kind":"arxiv","id":"2607.25921","version":1},"attestation_state":"computed","paper":{"title":"Evaluating VLMs for Autonomous Agent-Driven Geometry Clipping Detection in Video Game QA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Adri\\'an Barahona-R\\'ios, Benedict Wilkins, Carlos Celemin, Nabajeet Barman, Saman Zadtootaghaj","submitted_at":"2026-07-28T16:10:47Z","abstract_excerpt":"In this work, we study the use of Vision-Language Models (VLMs) for anomaly detection in an agent-driven game Quality Assurance (QA) pipeline focusing on geometry clipping. In this evaluation, a custom exploration agent navigates a game level to collect visual observations, while the automatic annotation pipeline provides frame-level clipping labels. This setup allows us to evaluate recent VLMs on a controlled anomaly detection task without manual annotation. We benchmark six recent VLMs (Gemini, GPT, Qwen, Gemma, Llama, and Ministral) under a zero-shot prompting setting and analyse their sens"},"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":"2607.25921","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-28T16:10:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6bcb1e7360e71f433947c9b528c15008c016e3d12576f0bf7e462f9979caaa86","abstract_canon_sha256":"f8144b9e2755775a969f5b08e74504a5a05768714b025b9a82ee666af2baf13b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T01:26:11.276712Z","signature_b64":"+rNXqwht56JBQOVB8bfwWqVwL56BPiSqr9N/DeYYZdvas3v3nLoIQrE/X6lkEfyDTRLF4KOt9XL06XLFgBweDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"148d3b723505be29a0676e0f407b8898c90ba719a39dfa46b6910bc4b3b8c1b5","last_reissued_at":"2026-07-29T01:26:11.275921Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T01:26:11.275921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating VLMs for Autonomous Agent-Driven Geometry Clipping Detection in Video Game QA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Adri\\'an Barahona-R\\'ios, Benedict Wilkins, Carlos Celemin, Nabajeet Barman, Saman Zadtootaghaj","submitted_at":"2026-07-28T16:10:47Z","abstract_excerpt":"In this work, we study the use of Vision-Language Models (VLMs) for anomaly detection in an agent-driven game Quality Assurance (QA) pipeline focusing on geometry clipping. In this evaluation, a custom exploration agent navigates a game level to collect visual observations, while the automatic annotation pipeline provides frame-level clipping labels. This setup allows us to evaluate recent VLMs on a controlled anomaly detection task without manual annotation. We benchmark six recent VLMs (Gemini, GPT, Qwen, Gemma, Llama, and Ministral) under a zero-shot prompting setting and analyse their sens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25921","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/2607.25921/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":"2607.25921","created_at":"2026-07-29T01:26:11.276326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.25921v1","created_at":"2026-07-29T01:26:11.276326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25921","created_at":"2026-07-29T01:26:11.276326+00:00"},{"alias_kind":"pith_short_12","alias_value":"CSGTW4RVAW7C","created_at":"2026-07-29T01:26:11.276326+00:00"},{"alias_kind":"pith_short_16","alias_value":"CSGTW4RVAW7CTIDH","created_at":"2026-07-29T01:26:11.276326+00:00"},{"alias_kind":"pith_short_8","alias_value":"CSGTW4RV","created_at":"2026-07-29T01:26:11.276326+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/CSGTW4RVAW7CTIDHNYHUA64ITD","json":"https://pith.science/pith/CSGTW4RVAW7CTIDHNYHUA64ITD.json","graph_json":"https://pith.science/api/pith-number/CSGTW4RVAW7CTIDHNYHUA64ITD/graph.json","events_json":"https://pith.science/api/pith-number/CSGTW4RVAW7CTIDHNYHUA64ITD/events.json","paper":"https://pith.science/paper/CSGTW4RV"},"agent_actions":{"view_html":"https://pith.science/pith/CSGTW4RVAW7CTIDHNYHUA64ITD","download_json":"https://pith.science/pith/CSGTW4RVAW7CTIDHNYHUA64ITD.json","view_paper":"https://pith.science/paper/CSGTW4RV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.25921&json=true","fetch_graph":"https://pith.science/api/pith-number/CSGTW4RVAW7CTIDHNYHUA64ITD/graph.json","fetch_events":"https://pith.science/api/pith-number/CSGTW4RVAW7CTIDHNYHUA64ITD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CSGTW4RVAW7CTIDHNYHUA64ITD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CSGTW4RVAW7CTIDHNYHUA64ITD/action/storage_attestation","attest_author":"https://pith.science/pith/CSGTW4RVAW7CTIDHNYHUA64ITD/action/author_attestation","sign_citation":"https://pith.science/pith/CSGTW4RVAW7CTIDHNYHUA64ITD/action/citation_signature","submit_replication":"https://pith.science/pith/CSGTW4RVAW7CTIDHNYHUA64ITD/action/replication_record"}},"created_at":"2026-07-29T01:26:11.276326+00:00","updated_at":"2026-07-29T01:26:11.276326+00:00"}