{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:G5XNBDHLUFT3SODRVPLNIZP7CH","short_pith_number":"pith:G5XNBDHL","canonical_record":{"source":{"id":"2501.12231","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-21T15:55:06Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"70821b0cdc0d5736d98ff49f9dd3fed4d5c6e4667647735fd887ace242d7c100","abstract_canon_sha256":"0d3cf9819826b529b4cd4757e64132979ad280e9f0d00f67ccb1c11261c885a2"},"schema_version":"1.0"},"canonical_sha256":"376ed08ceba167b93871abd6d465ff11ccdc45f51497640ff5a65da8f2902406","source":{"kind":"arxiv","id":"2501.12231","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:G5XNBDHLUFT3SODRVPLNIZP7CH","target":"record","payload":{"canonical_record":{"source":{"id":"2501.12231","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-21T15:55:06Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"70821b0cdc0d5736d98ff49f9dd3fed4d5c6e4667647735fd887ace242d7c100","abstract_canon_sha256":"0d3cf9819826b529b4cd4757e64132979ad280e9f0d00f67ccb1c11261c885a2"},"schema_version":"1.0"},"canonical_sha256":"376ed08ceba167b93871abd6d465ff11ccdc45f51497640ff5a65da8f2902406","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:33.397063Z","signature_b64":"ElSlKiWS0rCmUt4BgOvKh5rT11XcqAKQFn0pBrXs77UJDc6/7BmhT4/UUogEUUSwntVDD9Z75ZOW2cXwjNJmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"376ed08ceba167b93871abd6d465ff11ccdc45f51497640ff5a65da8f2902406","last_reissued_at":"2026-07-05T10:03:33.396558Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:33.396558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.12231","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:03:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dngSv8diuhHJ2QkLKEzP9FUt0bRBNazbZitaaIjzqVs8udsRxJ+eZdmGbnCrEkNr0qR8jhqWN7KMW/FdwhbwAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T15:40:05.159060Z"},"content_sha256":"70cdcdb5d8bb29643e90dd511a54fc9b7dee2fe1b4ff7bbfcbe090ba936b33d6","schema_version":"1.0","event_id":"sha256:70cdcdb5d8bb29643e90dd511a54fc9b7dee2fe1b4ff7bbfcbe090ba936b33d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:G5XNBDHLUFT3SODRVPLNIZP7CH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"InsTALL: Context-aware Instructional Task Assistance with Multi-modal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Arshit Gupta, Bonan Min, Girik Malik, Pha Nguyen, Sailik Sengupta","submitted_at":"2025-01-21T15:55:06Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12231","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/2501.12231/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:03:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nXWs9o76UOlEE50litz7T0ok/SKbzqYzmKGdJu01I+2lb4KOClaxx8UPSqDapm1AprGiXX2rFchS/y+WzpzrDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T15:40:05.159443Z"},"content_sha256":"de08c6493db76504808e23a6df0851ffc563ca5ac9d569703d9033e0d415238b","schema_version":"1.0","event_id":"sha256:de08c6493db76504808e23a6df0851ffc563ca5ac9d569703d9033e0d415238b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G5XNBDHLUFT3SODRVPLNIZP7CH/bundle.json","state_url":"https://pith.science/pith/G5XNBDHLUFT3SODRVPLNIZP7CH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G5XNBDHLUFT3SODRVPLNIZP7CH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-13T15:40:05Z","links":{"resolver":"https://pith.science/pith/G5XNBDHLUFT3SODRVPLNIZP7CH","bundle":"https://pith.science/pith/G5XNBDHLUFT3SODRVPLNIZP7CH/bundle.json","state":"https://pith.science/pith/G5XNBDHLUFT3SODRVPLNIZP7CH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G5XNBDHLUFT3SODRVPLNIZP7CH/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5FObjS7Qfui5OkDA5a/Oha1irTq5/6ER3dRY9xBLSys3poaCZ+nYojeOMTZJRtW38FEaNTm22GiVztYGrcApBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T15:40:05.162543Z","bundle_sha256":"6ef9dbd370b7779dbc0c636068d58e0289e5de45d1efcfd5c5538612d00ae0d2"}}