{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:74DDZGOB5DDL6IHEPZOYODGGED","short_pith_number":"pith:74DDZGOB","canonical_record":{"source":{"id":"2310.11699","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T04:15:12Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"0e17da90f4c6c46ffd716975d823451682dd015fafcd74a6740d0d6a2d2623cf","abstract_canon_sha256":"5d1e08fa1dc79ee1a8c7c66f61f939e40f346ee6943d78661eb6531dcb34b116"},"schema_version":"1.0"},"canonical_sha256":"ff063c99c1e8c6bf20e47e5d870cc620d69a58bca7684d9c2cfa85fbb4fcd8e7","source":{"kind":"arxiv","id":"2310.11699","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.11699","created_at":"2026-07-05T07:02:11Z"},{"alias_kind":"arxiv_version","alias_value":"2310.11699v1","created_at":"2026-07-05T07:02:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11699","created_at":"2026-07-05T07:02:11Z"},{"alias_kind":"pith_short_12","alias_value":"74DDZGOB5DDL","created_at":"2026-07-05T07:02:11Z"},{"alias_kind":"pith_short_16","alias_value":"74DDZGOB5DDL6IHE","created_at":"2026-07-05T07:02:11Z"},{"alias_kind":"pith_short_8","alias_value":"74DDZGOB","created_at":"2026-07-05T07:02:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:74DDZGOB5DDL6IHEPZOYODGGED","target":"record","payload":{"canonical_record":{"source":{"id":"2310.11699","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T04:15:12Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"0e17da90f4c6c46ffd716975d823451682dd015fafcd74a6740d0d6a2d2623cf","abstract_canon_sha256":"5d1e08fa1dc79ee1a8c7c66f61f939e40f346ee6943d78661eb6531dcb34b116"},"schema_version":"1.0"},"canonical_sha256":"ff063c99c1e8c6bf20e47e5d870cc620d69a58bca7684d9c2cfa85fbb4fcd8e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:11.139932Z","signature_b64":"kmCPro0MggoAnik4eIU6Y3pO70t03NxBf+N3aLY6uhTtGbXDLpIEc07jpJyZjkB8Vptl6v1FkpzviWKs/a+kDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff063c99c1e8c6bf20e47e5d870cc620d69a58bca7684d9c2cfa85fbb4fcd8e7","last_reissued_at":"2026-07-05T07:02:11.139519Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:11.139519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.11699","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":"2026-07-05T07:02:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zb069+E3TANICb65TFXK5GKdJPDUGA1IetXYIpZG3KwJ1ARD7YbwMJYdACCK/vlY37iBt2qlHaz3Nv+ddKPMBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T04:21:47.219755Z"},"content_sha256":"c568c14eed3a4ae57fa0632ed273fe380a0b9d441a03f4d5b5eb1b35b9e6d593","schema_version":"1.0","event_id":"sha256:c568c14eed3a4ae57fa0632ed273fe380a0b9d441a03f4d5b5eb1b35b9e6d593"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:74DDZGOB5DDL6IHEPZOYODGGED","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MISAR: A Multimodal Instructional System with Augmented Reality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Ali Vosoughi, Chenliang Xu, Jing Bi, Nguyen Manh Nguyen","submitted_at":"2023-10-18T04:15:12Z","abstract_excerpt":"Augmented reality (AR) requires the seamless integration of visual, auditory, and linguistic channels for optimized human-computer interaction. While auditory and visual inputs facilitate real-time and contextual user guidance, the potential of large language models (LLMs) in this landscape remains largely untapped. Our study introduces an innovative method harnessing LLMs to assimilate information from visual, auditory, and contextual modalities. Focusing on the unique challenge of task performance quantification in AR, we utilize egocentric video, speech, and context analysis. The integratio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11699","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/2310.11699/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":"2026-07-05T07:02:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uvfpvZ7E6fk4+LoZhfRYYwKOqND1GD2dnex+U/AFLlmpSPBmmoiLlcHgXHDx/ZMIRb0DDI4XbRsfBavBP9FdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T04:21:47.220141Z"},"content_sha256":"921921e9c36c0d551200790b0f883952dd3d934d4ba0784e2f23ecdf6597352d","schema_version":"1.0","event_id":"sha256:921921e9c36c0d551200790b0f883952dd3d934d4ba0784e2f23ecdf6597352d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/74DDZGOB5DDL6IHEPZOYODGGED/bundle.json","state_url":"https://pith.science/pith/74DDZGOB5DDL6IHEPZOYODGGED/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/74DDZGOB5DDL6IHEPZOYODGGED/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":"2026-07-08T04:21:47Z","links":{"resolver":"https://pith.science/pith/74DDZGOB5DDL6IHEPZOYODGGED","bundle":"https://pith.science/pith/74DDZGOB5DDL6IHEPZOYODGGED/bundle.json","state":"https://pith.science/pith/74DDZGOB5DDL6IHEPZOYODGGED/state.json","well_known_bundle":"https://pith.science/.well-known/pith/74DDZGOB5DDL6IHEPZOYODGGED/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:74DDZGOB5DDL6IHEPZOYODGGED","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":"5d1e08fa1dc79ee1a8c7c66f61f939e40f346ee6943d78661eb6531dcb34b116","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T04:15:12Z","title_canon_sha256":"0e17da90f4c6c46ffd716975d823451682dd015fafcd74a6740d0d6a2d2623cf"},"schema_version":"1.0","source":{"id":"2310.11699","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.11699","created_at":"2026-07-05T07:02:11Z"},{"alias_kind":"arxiv_version","alias_value":"2310.11699v1","created_at":"2026-07-05T07:02:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11699","created_at":"2026-07-05T07:02:11Z"},{"alias_kind":"pith_short_12","alias_value":"74DDZGOB5DDL","created_at":"2026-07-05T07:02:11Z"},{"alias_kind":"pith_short_16","alias_value":"74DDZGOB5DDL6IHE","created_at":"2026-07-05T07:02:11Z"},{"alias_kind":"pith_short_8","alias_value":"74DDZGOB","created_at":"2026-07-05T07:02:11Z"}],"graph_snapshots":[{"event_id":"sha256:921921e9c36c0d551200790b0f883952dd3d934d4ba0784e2f23ecdf6597352d","target":"graph","created_at":"2026-07-05T07:02:11Z","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/2310.11699/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Augmented reality (AR) requires the seamless integration of visual, auditory, and linguistic channels for optimized human-computer interaction. While auditory and visual inputs facilitate real-time and contextual user guidance, the potential of large language models (LLMs) in this landscape remains largely untapped. Our study introduces an innovative method harnessing LLMs to assimilate information from visual, auditory, and contextual modalities. Focusing on the unique challenge of task performance quantification in AR, we utilize egocentric video, speech, and context analysis. The integratio","authors_text":"Ali Vosoughi, Chenliang Xu, Jing Bi, Nguyen Manh Nguyen","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T04:15:12Z","title":"MISAR: A Multimodal Instructional System with Augmented Reality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11699","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:c568c14eed3a4ae57fa0632ed273fe380a0b9d441a03f4d5b5eb1b35b9e6d593","target":"record","created_at":"2026-07-05T07:02:11Z","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":"5d1e08fa1dc79ee1a8c7c66f61f939e40f346ee6943d78661eb6531dcb34b116","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T04:15:12Z","title_canon_sha256":"0e17da90f4c6c46ffd716975d823451682dd015fafcd74a6740d0d6a2d2623cf"},"schema_version":"1.0","source":{"id":"2310.11699","kind":"arxiv","version":1}},"canonical_sha256":"ff063c99c1e8c6bf20e47e5d870cc620d69a58bca7684d9c2cfa85fbb4fcd8e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff063c99c1e8c6bf20e47e5d870cc620d69a58bca7684d9c2cfa85fbb4fcd8e7","first_computed_at":"2026-07-05T07:02:11.139519Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:02:11.139519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kmCPro0MggoAnik4eIU6Y3pO70t03NxBf+N3aLY6uhTtGbXDLpIEc07jpJyZjkB8Vptl6v1FkpzviWKs/a+kDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:02:11.139932Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.11699","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c568c14eed3a4ae57fa0632ed273fe380a0b9d441a03f4d5b5eb1b35b9e6d593","sha256:921921e9c36c0d551200790b0f883952dd3d934d4ba0784e2f23ecdf6597352d"],"state_sha256":"4a9f51c9e65319f309477a588f41fdd9cf0561a272c0ee473e68d45995764a24"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c9jd+TENMBlE0pa/2Jhyur/OadsoB0bw2u0thj82kMwQebAIg2wmMpFlAIG5rZnY9pYbpljVopYy99sTgFtiCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T04:21:47.222246Z","bundle_sha256":"b55d332ef3e970a63c68c0f7f06a56aac781de635ab082e5aaf9a7f809b22d96"}}