{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YYKYJGL542IYEZRNUUWUASIN34","short_pith_number":"pith:YYKYJGL5","schema_version":"1.0","canonical_sha256":"c61584997de69182662da52d40490ddf0e306c18fcbd7b65a740155d5c76ce92","source":{"kind":"arxiv","id":"2607.29181","version":1},"attestation_state":"computed","paper":{"title":"SERUM: State Extraction and Refinement for User Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Andy J. Phu, Dongyeop Kang, James Mooney, Karin de Langis, Khanh Chi Le","submitted_at":"2026-07-31T09:02:33Z","abstract_excerpt":"Agentic assistants capable of proactive, personalized interactions require structured models of user intent and workflow. However, building these models from raw, unstructured screen activity remains an open challenge. We present SERUM, a multi-pass framework that extracts finite-state behavioral models directly from unstructured egocentric video using hierarchical VLM annotation. Processing screen recordings through a sliding window, SERUM alternates between activity-recognition and intent-inference passes, with each pass refining labels using accumulated prior context to reduce hallucination"},"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":"2607.29181","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T09:02:33Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"ac1a7e919765d67af97c7f6f913a8d8ffbf8694db4d6447e6630f2a4d6defd01","abstract_canon_sha256":"0c20cb49151900d935c480c37fcd131172e59694fdefc833a56b404e03dc0940"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:20:31.160460Z","signature_b64":"vQCAt8B39tqAw0nV7JNio5/0SNvyqo7wHBfiShaUVxO9n0W/ujPmAlNHcOADC2Xu//Y7xSuUa9+c58JTkPDYBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c61584997de69182662da52d40490ddf0e306c18fcbd7b65a740155d5c76ce92","last_reissued_at":"2026-08-03T01:20:31.158851Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:20:31.158851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SERUM: State Extraction and Refinement for User Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Andy J. Phu, Dongyeop Kang, James Mooney, Karin de Langis, Khanh Chi Le","submitted_at":"2026-07-31T09:02:33Z","abstract_excerpt":"Agentic assistants capable of proactive, personalized interactions require structured models of user intent and workflow. However, building these models from raw, unstructured screen activity remains an open challenge. We present SERUM, a multi-pass framework that extracts finite-state behavioral models directly from unstructured egocentric video using hierarchical VLM annotation. Processing screen recordings through a sliding window, SERUM alternates between activity-recognition and intent-inference passes, with each pass refining labels using accumulated prior context to reduce hallucination"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29181","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/2607.29181/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":"2607.29181","created_at":"2026-08-03T01:20:31.159894+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.29181v1","created_at":"2026-08-03T01:20:31.159894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29181","created_at":"2026-08-03T01:20:31.159894+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYKYJGL542IY","created_at":"2026-08-03T01:20:31.159894+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYKYJGL542IYEZRN","created_at":"2026-08-03T01:20:31.159894+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYKYJGL5","created_at":"2026-08-03T01:20:31.159894+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/YYKYJGL542IYEZRNUUWUASIN34","json":"https://pith.science/pith/YYKYJGL542IYEZRNUUWUASIN34.json","graph_json":"https://pith.science/api/pith-number/YYKYJGL542IYEZRNUUWUASIN34/graph.json","events_json":"https://pith.science/api/pith-number/YYKYJGL542IYEZRNUUWUASIN34/events.json","paper":"https://pith.science/paper/YYKYJGL5"},"agent_actions":{"view_html":"https://pith.science/pith/YYKYJGL542IYEZRNUUWUASIN34","download_json":"https://pith.science/pith/YYKYJGL542IYEZRNUUWUASIN34.json","view_paper":"https://pith.science/paper/YYKYJGL5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.29181&json=true","fetch_graph":"https://pith.science/api/pith-number/YYKYJGL542IYEZRNUUWUASIN34/graph.json","fetch_events":"https://pith.science/api/pith-number/YYKYJGL542IYEZRNUUWUASIN34/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYKYJGL542IYEZRNUUWUASIN34/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYKYJGL542IYEZRNUUWUASIN34/action/storage_attestation","attest_author":"https://pith.science/pith/YYKYJGL542IYEZRNUUWUASIN34/action/author_attestation","sign_citation":"https://pith.science/pith/YYKYJGL542IYEZRNUUWUASIN34/action/citation_signature","submit_replication":"https://pith.science/pith/YYKYJGL542IYEZRNUUWUASIN34/action/replication_record"}},"created_at":"2026-08-03T01:20:31.159894+00:00","updated_at":"2026-08-03T01:20:31.159894+00:00"}