{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ALLL3IXFH3PBAKXDR3L7IGESRI","short_pith_number":"pith:ALLL3IXF","schema_version":"1.0","canonical_sha256":"02d6bda2e53ede102ae38ed7f418928a13e94cee98a92ace7bd6c4b4d710cd89","source":{"kind":"arxiv","id":"2607.26041","version":1},"attestation_state":"computed","paper":{"title":"Desktop-Delta Bench: Do Computer-Use Models Understand Desktop GUI Transitions?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Abhishek Pillai, Samir Kumar Nayak, Yuan Chen","submitted_at":"2026-07-28T17:49:51Z","abstract_excerpt":"Computer-use agents (CUAs) increasingly act through desktop GUIs to complete long-horizon tasks. Current benchmarks primarily measure end-task success or single-frame grounding. Neither isolates whether a model can reconstruct the causal, task-relevant transition produced by an action- crucial for rejecting stale observations, verifying progress, and recovering from failure. This is difficult because inference, remote input, app rendering, and screenshot capture are asynchronous: the next observation may be delayed, occluded, transient, or unrelated, then misread as progress and carried into s"},"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":"2607.26041","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-28T17:49:51Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b429568fde17db50d715eafbadc39a9a309c7097ae474a87b26b96b37d9ddc3f","abstract_canon_sha256":"6c757a9f3daf911631022fd4b279d541ae7703bf703be561bb2428d2f0bec0c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T01:26:21.189152Z","signature_b64":"aHAp+ocaYGxfYoUpGEGG0O7OfAZ+/a/M2XcgtBkwgJurg1Q8A2cJGvNpd7Spwj9+ir3Cgm44+R2BsxKzodjJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02d6bda2e53ede102ae38ed7f418928a13e94cee98a92ace7bd6c4b4d710cd89","last_reissued_at":"2026-07-29T01:26:21.188300Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T01:26:21.188300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Desktop-Delta Bench: Do Computer-Use Models Understand Desktop GUI Transitions?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Abhishek Pillai, Samir Kumar Nayak, Yuan Chen","submitted_at":"2026-07-28T17:49:51Z","abstract_excerpt":"Computer-use agents (CUAs) increasingly act through desktop GUIs to complete long-horizon tasks. Current benchmarks primarily measure end-task success or single-frame grounding. Neither isolates whether a model can reconstruct the causal, task-relevant transition produced by an action- crucial for rejecting stale observations, verifying progress, and recovering from failure. This is difficult because inference, remote input, app rendering, and screenshot capture are asynchronous: the next observation may be delayed, occluded, transient, or unrelated, then misread as progress and carried into s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26041","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/2607.26041/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":"2607.26041","created_at":"2026-07-29T01:26:21.188746+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.26041v1","created_at":"2026-07-29T01:26:21.188746+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26041","created_at":"2026-07-29T01:26:21.188746+00:00"},{"alias_kind":"pith_short_12","alias_value":"ALLL3IXFH3PB","created_at":"2026-07-29T01:26:21.188746+00:00"},{"alias_kind":"pith_short_16","alias_value":"ALLL3IXFH3PBAKXD","created_at":"2026-07-29T01:26:21.188746+00:00"},{"alias_kind":"pith_short_8","alias_value":"ALLL3IXF","created_at":"2026-07-29T01:26:21.188746+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/ALLL3IXFH3PBAKXDR3L7IGESRI","json":"https://pith.science/pith/ALLL3IXFH3PBAKXDR3L7IGESRI.json","graph_json":"https://pith.science/api/pith-number/ALLL3IXFH3PBAKXDR3L7IGESRI/graph.json","events_json":"https://pith.science/api/pith-number/ALLL3IXFH3PBAKXDR3L7IGESRI/events.json","paper":"https://pith.science/paper/ALLL3IXF"},"agent_actions":{"view_html":"https://pith.science/pith/ALLL3IXFH3PBAKXDR3L7IGESRI","download_json":"https://pith.science/pith/ALLL3IXFH3PBAKXDR3L7IGESRI.json","view_paper":"https://pith.science/paper/ALLL3IXF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.26041&json=true","fetch_graph":"https://pith.science/api/pith-number/ALLL3IXFH3PBAKXDR3L7IGESRI/graph.json","fetch_events":"https://pith.science/api/pith-number/ALLL3IXFH3PBAKXDR3L7IGESRI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ALLL3IXFH3PBAKXDR3L7IGESRI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ALLL3IXFH3PBAKXDR3L7IGESRI/action/storage_attestation","attest_author":"https://pith.science/pith/ALLL3IXFH3PBAKXDR3L7IGESRI/action/author_attestation","sign_citation":"https://pith.science/pith/ALLL3IXFH3PBAKXDR3L7IGESRI/action/citation_signature","submit_replication":"https://pith.science/pith/ALLL3IXFH3PBAKXDR3L7IGESRI/action/replication_record"}},"created_at":"2026-07-29T01:26:21.188746+00:00","updated_at":"2026-07-29T01:26:21.188746+00:00"}