{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:G5XNBDHLUFT3SODRVPLNIZP7CH","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":"0d3cf9819826b529b4cd4757e64132979ad280e9f0d00f67ccb1c11261c885a2","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-21T15:55:06Z","title_canon_sha256":"70821b0cdc0d5736d98ff49f9dd3fed4d5c6e4667647735fd887ace242d7c100"},"schema_version":"1.0","source":{"id":"2501.12231","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.12231","created_at":"2026-07-05T10:03:33Z"},{"alias_kind":"arxiv_version","alias_value":"2501.12231v1","created_at":"2026-07-05T10:03:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12231","created_at":"2026-07-05T10:03:33Z"},{"alias_kind":"pith_short_12","alias_value":"G5XNBDHLUFT3","created_at":"2026-07-05T10:03:33Z"},{"alias_kind":"pith_short_16","alias_value":"G5XNBDHLUFT3SODR","created_at":"2026-07-05T10:03:33Z"},{"alias_kind":"pith_short_8","alias_value":"G5XNBDHL","created_at":"2026-07-05T10:03:33Z"}],"graph_snapshots":[{"event_id":"sha256:de08c6493db76504808e23a6df0851ffc563ca5ac9d569703d9033e0d415238b","target":"graph","created_at":"2026-07-05T10:03:33Z","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/2501.12231/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The improved competence of generative models can help building multi-modal virtual assistants that leverage modalities beyond language. By observing humans performing multi-step tasks, one can build assistants that have situational awareness of actions and tasks being performed, enabling them to cater assistance based on this understanding. In this paper, we develop a Context-aware Instructional Task Assistant with Multi-modal Large Language Models (InsTALL) that leverages an online visual stream (e.g. a user's screen share or video recording) and responds in real-time to user queries related ","authors_text":"Arshit Gupta, Bonan Min, Girik Malik, Pha Nguyen, Sailik Sengupta","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-21T15:55:06Z","title":"InsTALL: Context-aware Instructional Task Assistance with Multi-modal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12231","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":"sha256:70cdcdb5d8bb29643e90dd511a54fc9b7dee2fe1b4ff7bbfcbe090ba936b33d6","target":"record","created_at":"2026-07-05T10:03:33Z","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":"0d3cf9819826b529b4cd4757e64132979ad280e9f0d00f67ccb1c11261c885a2","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-21T15:55:06Z","title_canon_sha256":"70821b0cdc0d5736d98ff49f9dd3fed4d5c6e4667647735fd887ace242d7c100"},"schema_version":"1.0","source":{"id":"2501.12231","kind":"arxiv","version":1}},"canonical_sha256":"376ed08ceba167b93871abd6d465ff11ccdc45f51497640ff5a65da8f2902406","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"376ed08ceba167b93871abd6d465ff11ccdc45f51497640ff5a65da8f2902406","first_computed_at":"2026-07-05T10:03:33.396558Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:03:33.396558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ElSlKiWS0rCmUt4BgOvKh5rT11XcqAKQFn0pBrXs77UJDc6/7BmhT4/UUogEUUSwntVDD9Z75ZOW2cXwjNJmBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:03:33.397063Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.12231","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70cdcdb5d8bb29643e90dd511a54fc9b7dee2fe1b4ff7bbfcbe090ba936b33d6","sha256:de08c6493db76504808e23a6df0851ffc563ca5ac9d569703d9033e0d415238b"],"state_sha256":"ca6728e09532ba177de66fd430144c812bdef42698f48ece3effaab433a7da4e"}