{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SRSYAZ256RDG35LRO45ZOFX64E","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":"17c3c979983f8b3d4532cc512bd70fdf1dffc938e12bb3f1d85d01efd164460b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-13T16:53:29Z","title_canon_sha256":"6c3f3604baa44a964cae565b7057664623b669cc7831a5d80911741f265b18b7"},"schema_version":"1.0","source":{"id":"2411.08768","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.08768","created_at":"2026-07-05T09:35:02Z"},{"alias_kind":"arxiv_version","alias_value":"2411.08768v1","created_at":"2026-07-05T09:35:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08768","created_at":"2026-07-05T09:35:02Z"},{"alias_kind":"pith_short_12","alias_value":"SRSYAZ256RDG","created_at":"2026-07-05T09:35:02Z"},{"alias_kind":"pith_short_16","alias_value":"SRSYAZ256RDG35LR","created_at":"2026-07-05T09:35:02Z"},{"alias_kind":"pith_short_8","alias_value":"SRSYAZ25","created_at":"2026-07-05T09:35:02Z"}],"graph_snapshots":[{"event_id":"sha256:899a5df56733587277e895e8a21261ea2321165ccc03f5b68bcff04c58aec3f7","target":"graph","created_at":"2026-07-05T09:35:02Z","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/2411.08768/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video recordings of user activities, particularly desktop recordings, offer a rich source of data for understanding user behaviors and automating processes. However, despite advancements in Vision-Language Models (VLMs) and their increasing use in video analysis, extracting user actions from desktop recordings remains an underexplored area. This paper addresses this gap by proposing two novel VLM-based methods for user action extraction: the Direct Frame-Based Approach (DF), which inputs sampled frames directly into VLMs, and the Differential Frame-Based Approach (DiffF), which incorporates ex","authors_text":"Dongmei Zhang, Jue Zhang, Kehong Yuan, Lu Han, Qingwei Lin, Qi Zhang, Saravan Rajmohan, Xiaoting Qin, Yanting Chen, Yi Ren","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-13T16:53:29Z","title":"Sharingan: Extract User Action Sequence from Desktop Recordings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08768","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:fdadb2c89e05c94ae02ca70cfc207d0b2d7725866f7b61dfc8b3a87b774ed22e","target":"record","created_at":"2026-07-05T09:35:02Z","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":"17c3c979983f8b3d4532cc512bd70fdf1dffc938e12bb3f1d85d01efd164460b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-13T16:53:29Z","title_canon_sha256":"6c3f3604baa44a964cae565b7057664623b669cc7831a5d80911741f265b18b7"},"schema_version":"1.0","source":{"id":"2411.08768","kind":"arxiv","version":1}},"canonical_sha256":"946580675df4466df571773b9716fee10b293e3336b8e20478aacd00155a5442","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"946580675df4466df571773b9716fee10b293e3336b8e20478aacd00155a5442","first_computed_at":"2026-07-05T09:35:02.227737Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:35:02.227737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y87iFncI4CJbOhyjB6e3BmKRyiZQopRfwh+DtUeZPYGcBgjDcPiSvaURMCd/I/40wlQ1ZK29AozBpoYMFZCZDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:35:02.228179Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.08768","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fdadb2c89e05c94ae02ca70cfc207d0b2d7725866f7b61dfc8b3a87b774ed22e","sha256:899a5df56733587277e895e8a21261ea2321165ccc03f5b68bcff04c58aec3f7"],"state_sha256":"4180505df30081ac174dd08e08c3cab85977fe0aca6fa448fe51b766818fda4f"}