{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WHKJJLPVG2W4ZHKAIPPLGIGQTM","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":"f9aa3f4d8cce2f99e5fe84a561b95c7dce3b2cc41509714ee11900fd95cd1ebe","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-30T05:26:51Z","title_canon_sha256":"101543c0d2c1b1026ebea191817868e1aa3248adf3571b9fb46b5d5100cba1c6"},"schema_version":"1.0","source":{"id":"2606.31154","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31154","created_at":"2026-07-01T01:17:30Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31154v1","created_at":"2026-07-01T01:17:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31154","created_at":"2026-07-01T01:17:30Z"},{"alias_kind":"pith_short_12","alias_value":"WHKJJLPVG2W4","created_at":"2026-07-01T01:17:30Z"},{"alias_kind":"pith_short_16","alias_value":"WHKJJLPVG2W4ZHKA","created_at":"2026-07-01T01:17:30Z"},{"alias_kind":"pith_short_8","alias_value":"WHKJJLPV","created_at":"2026-07-01T01:17:30Z"}],"graph_snapshots":[{"event_id":"sha256:06f75b03608f1e838d36c9636c04546fde81d22a47b62b0ba0b8abef00897c3f","target":"graph","created_at":"2026-07-01T01:17:30Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.31154/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Creating and editing slides is a rich, multimodal activity that is ubiquitous in professional and educational settings, making it an ideal testbed for real-world computer-use agents. Microsoft PowerPoint is among the most widely adopted and feature-rich environments for presentation creation. We introduce PPT-Eval, a benchmark of 120 PowerPoint tasks across 12 files that cover both content creation and presentation editing scenarios, organized by difficulty. A central challenge in this domain is evaluation: tasks are complex, multimodal, and often admit many valid solutions. Moreover, today's ","authors_text":"Apurva Gandhi, Firoz Shaik, Graham Neubig, Muhammad Taqi Raza, Raja Hasnain Anwar, Shubhang Desai, Thong Q. Nguyen, Vishal Chowdhary, Vishwas Suryanarayanan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-30T05:26:51Z","title":"PPT-Eval: A Benchmark for Computer-Use Agents on PowerPoint Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31154","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:018e476fb61ea9f907722e8b0462f844c38fedfad2e900078970d33e4fcde6cd","target":"record","created_at":"2026-07-01T01:17:30Z","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":"f9aa3f4d8cce2f99e5fe84a561b95c7dce3b2cc41509714ee11900fd95cd1ebe","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-30T05:26:51Z","title_canon_sha256":"101543c0d2c1b1026ebea191817868e1aa3248adf3571b9fb46b5d5100cba1c6"},"schema_version":"1.0","source":{"id":"2606.31154","kind":"arxiv","version":1}},"canonical_sha256":"b1d494adf536adcc9d4043deb320d09b01641fbd6339d6628b8476aafd36a63e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1d494adf536adcc9d4043deb320d09b01641fbd6339d6628b8476aafd36a63e","first_computed_at":"2026-07-01T01:17:30.726817Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:17:30.726817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jvdNS1ke4QPabx1GcHZBGmEAPNLA1yo5JlsyLaTmksPHlAVuW0Q4HASndziEpAf+Cvhpi68y3V7biJw7Yw8aDg==","signature_status":"signed_v1","signed_at":"2026-07-01T01:17:30.727232Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.31154","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:018e476fb61ea9f907722e8b0462f844c38fedfad2e900078970d33e4fcde6cd","sha256:06f75b03608f1e838d36c9636c04546fde81d22a47b62b0ba0b8abef00897c3f"],"state_sha256":"1ae75a8883e8de390009f5b47c68e4d084e89871f87b84d6e33520845e3466a4"}