{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:V6R7HTL2CSGXK3WX66FKRXLVPO","short_pith_number":"pith:V6R7HTL2","schema_version":"1.0","canonical_sha256":"afa3f3cd7a148d756ed7f78aa8dd757ba57be99d1bd0beab45ed8c8c04ee91df","source":{"kind":"arxiv","id":"2606.11078","version":1},"attestation_state":"computed","paper":{"title":"A History-Aware Visually Grounded Critic for Computer Use Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Archiki Prasad, Elias Stengel-Eskin, Hyunji Lee, Jaewoo Lee, Justin Chih-Yao Chen, Kartik Balasubramaniam, Mohit Bansal, Sambit Sahu, Supriyo Chakraborty, Zaid Khan","submitted_at":"2026-06-09T16:39:10Z","abstract_excerpt":"Various test-time interventions for Computer Use Agents (CUAs), including critic models, have been developed to improve performance through pre-execution action evaluation in complex Graphical User Interface (GUI) environments. However, existing critics suffer from two key limitations: they (1) focus primarily on short-sighted decision loops (e.g., forgetting earlier actions) and (2) lack the visual grounding needed to detect flawed actions (e.g., clicking wrong UI elements). To address these, we introduce HiViG, a History-aware Visually Grounded test-time framework, built around a multimodal "},"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":"2606.11078","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-09T16:39:10Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"7513e031189c3af1c83909051cadb1b678789422a1cf18cf521602a2607d8247","abstract_canon_sha256":"07f9a741f50d8d7a318c8d83521163be1de3309ce42b41c461ed3776f2cb137e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:11:08.899890Z","signature_b64":"7Dlz4GEtwjPBw4DoaZcsuJUGryON6nmfCbHYgKHHpzSzV5L/gXlfm2nyuGsjhLyaC4qCXz/0sc7/gOtQQVkwCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afa3f3cd7a148d756ed7f78aa8dd757ba57be99d1bd0beab45ed8c8c04ee91df","last_reissued_at":"2026-06-10T01:11:08.899017Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:11:08.899017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A History-Aware Visually Grounded Critic for Computer Use Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Archiki Prasad, Elias Stengel-Eskin, Hyunji Lee, Jaewoo Lee, Justin Chih-Yao Chen, Kartik Balasubramaniam, Mohit Bansal, Sambit Sahu, Supriyo Chakraborty, Zaid Khan","submitted_at":"2026-06-09T16:39:10Z","abstract_excerpt":"Various test-time interventions for Computer Use Agents (CUAs), including critic models, have been developed to improve performance through pre-execution action evaluation in complex Graphical User Interface (GUI) environments. However, existing critics suffer from two key limitations: they (1) focus primarily on short-sighted decision loops (e.g., forgetting earlier actions) and (2) lack the visual grounding needed to detect flawed actions (e.g., clicking wrong UI elements). To address these, we introduce HiViG, a History-aware Visually Grounded test-time framework, built around a multimodal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11078","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/2606.11078/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":"2606.11078","created_at":"2026-06-10T01:11:08.899166+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11078v1","created_at":"2026-06-10T01:11:08.899166+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11078","created_at":"2026-06-10T01:11:08.899166+00:00"},{"alias_kind":"pith_short_12","alias_value":"V6R7HTL2CSGX","created_at":"2026-06-10T01:11:08.899166+00:00"},{"alias_kind":"pith_short_16","alias_value":"V6R7HTL2CSGXK3WX","created_at":"2026-06-10T01:11:08.899166+00:00"},{"alias_kind":"pith_short_8","alias_value":"V6R7HTL2","created_at":"2026-06-10T01:11:08.899166+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/V6R7HTL2CSGXK3WX66FKRXLVPO","json":"https://pith.science/pith/V6R7HTL2CSGXK3WX66FKRXLVPO.json","graph_json":"https://pith.science/api/pith-number/V6R7HTL2CSGXK3WX66FKRXLVPO/graph.json","events_json":"https://pith.science/api/pith-number/V6R7HTL2CSGXK3WX66FKRXLVPO/events.json","paper":"https://pith.science/paper/V6R7HTL2"},"agent_actions":{"view_html":"https://pith.science/pith/V6R7HTL2CSGXK3WX66FKRXLVPO","download_json":"https://pith.science/pith/V6R7HTL2CSGXK3WX66FKRXLVPO.json","view_paper":"https://pith.science/paper/V6R7HTL2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11078&json=true","fetch_graph":"https://pith.science/api/pith-number/V6R7HTL2CSGXK3WX66FKRXLVPO/graph.json","fetch_events":"https://pith.science/api/pith-number/V6R7HTL2CSGXK3WX66FKRXLVPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V6R7HTL2CSGXK3WX66FKRXLVPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V6R7HTL2CSGXK3WX66FKRXLVPO/action/storage_attestation","attest_author":"https://pith.science/pith/V6R7HTL2CSGXK3WX66FKRXLVPO/action/author_attestation","sign_citation":"https://pith.science/pith/V6R7HTL2CSGXK3WX66FKRXLVPO/action/citation_signature","submit_replication":"https://pith.science/pith/V6R7HTL2CSGXK3WX66FKRXLVPO/action/replication_record"}},"created_at":"2026-06-10T01:11:08.899166+00:00","updated_at":"2026-06-10T01:11:08.899166+00:00"}