{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SRSYAZ256RDG35LRO45ZOFX64E","short_pith_number":"pith:SRSYAZ25","schema_version":"1.0","canonical_sha256":"946580675df4466df571773b9716fee10b293e3336b8e20478aacd00155a5442","source":{"kind":"arxiv","id":"2411.08768","version":1},"attestation_state":"computed","paper":{"title":"Sharingan: Extract User Action Sequence from Desktop Recordings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dongmei Zhang, Jue Zhang, Kehong Yuan, Lu Han, Qingwei Lin, Qi Zhang, Saravan Rajmohan, Xiaoting Qin, Yanting Chen, Yi Ren","submitted_at":"2024-11-13T16:53:29Z","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"},"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":"2411.08768","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-13T16:53:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6c3f3604baa44a964cae565b7057664623b669cc7831a5d80911741f265b18b7","abstract_canon_sha256":"17c3c979983f8b3d4532cc512bd70fdf1dffc938e12bb3f1d85d01efd164460b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:02.228179Z","signature_b64":"y87iFncI4CJbOhyjB6e3BmKRyiZQopRfwh+DtUeZPYGcBgjDcPiSvaURMCd/I/40wlQ1ZK29AozBpoYMFZCZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"946580675df4466df571773b9716fee10b293e3336b8e20478aacd00155a5442","last_reissued_at":"2026-07-05T09:35:02.227737Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:02.227737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sharingan: Extract User Action Sequence from Desktop Recordings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dongmei Zhang, Jue Zhang, Kehong Yuan, Lu Han, Qingwei Lin, Qi Zhang, Saravan Rajmohan, Xiaoting Qin, Yanting Chen, Yi Ren","submitted_at":"2024-11-13T16:53:29Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08768","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/2411.08768/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":"2411.08768","created_at":"2026-07-05T09:35:02.227805+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.08768v1","created_at":"2026-07-05T09:35:02.227805+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08768","created_at":"2026-07-05T09:35:02.227805+00:00"},{"alias_kind":"pith_short_12","alias_value":"SRSYAZ256RDG","created_at":"2026-07-05T09:35:02.227805+00:00"},{"alias_kind":"pith_short_16","alias_value":"SRSYAZ256RDG35LR","created_at":"2026-07-05T09:35:02.227805+00:00"},{"alias_kind":"pith_short_8","alias_value":"SRSYAZ25","created_at":"2026-07-05T09:35:02.227805+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/SRSYAZ256RDG35LRO45ZOFX64E","json":"https://pith.science/pith/SRSYAZ256RDG35LRO45ZOFX64E.json","graph_json":"https://pith.science/api/pith-number/SRSYAZ256RDG35LRO45ZOFX64E/graph.json","events_json":"https://pith.science/api/pith-number/SRSYAZ256RDG35LRO45ZOFX64E/events.json","paper":"https://pith.science/paper/SRSYAZ25"},"agent_actions":{"view_html":"https://pith.science/pith/SRSYAZ256RDG35LRO45ZOFX64E","download_json":"https://pith.science/pith/SRSYAZ256RDG35LRO45ZOFX64E.json","view_paper":"https://pith.science/paper/SRSYAZ25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.08768&json=true","fetch_graph":"https://pith.science/api/pith-number/SRSYAZ256RDG35LRO45ZOFX64E/graph.json","fetch_events":"https://pith.science/api/pith-number/SRSYAZ256RDG35LRO45ZOFX64E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SRSYAZ256RDG35LRO45ZOFX64E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SRSYAZ256RDG35LRO45ZOFX64E/action/storage_attestation","attest_author":"https://pith.science/pith/SRSYAZ256RDG35LRO45ZOFX64E/action/author_attestation","sign_citation":"https://pith.science/pith/SRSYAZ256RDG35LRO45ZOFX64E/action/citation_signature","submit_replication":"https://pith.science/pith/SRSYAZ256RDG35LRO45ZOFX64E/action/replication_record"}},"created_at":"2026-07-05T09:35:02.227805+00:00","updated_at":"2026-07-05T09:35:02.227805+00:00"}