{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LMU4XMHBW7Z4XJGZ3TZVWCCROV","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":"1ede09b60901f53fb92ffbf74aab764477df69eedf3228dd31b22024854a3098","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:05Z","title_canon_sha256":"e018ca2d6c6861b07d088f8e85a743773537ff7773e3d42fa0ca423865309158"},"schema_version":"1.0","source":{"id":"2406.09390","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09390","created_at":"2026-07-05T10:39:19Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09390v3","created_at":"2026-07-05T10:39:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09390","created_at":"2026-07-05T10:39:19Z"},{"alias_kind":"pith_short_12","alias_value":"LMU4XMHBW7Z4","created_at":"2026-07-05T10:39:19Z"},{"alias_kind":"pith_short_16","alias_value":"LMU4XMHBW7Z4XJGZ","created_at":"2026-07-05T10:39:19Z"},{"alias_kind":"pith_short_8","alias_value":"LMU4XMHB","created_at":"2026-07-05T10:39:19Z"}],"graph_snapshots":[{"event_id":"sha256:61697ef2608318dd8d00c1f148957984cd0581482a8cb29ae8a6cc4b7770ebee","target":"graph","created_at":"2026-07-05T10:39:19Z","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/2406.09390/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current Large Language Vision Models (LLVMs) trained on web videos perform well in general video understanding but struggle with fine-grained details, complex human-object interactions (HOI), and view-invariant representation learning essential for Activities of Daily Living (ADL). This limitation stems from a lack of specialized ADL video instruction-tuning datasets and insufficient modality integration to capture discriminative action representations. To address this, we propose a semi-automated framework for curating ADL datasets, creating ADL-X, a multiview, multimodal RGBS instruction-tun","authors_text":"Arkaprava Sinha, Dominick Reilly, Francois Bremond, Le Xue, Manish Kumar Govind, Pu Wang, Rajatsubhra Chakraborty, Srijan Das","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:05Z","title":"LLAVIDAL: A Large LAnguage VIsion Model for Daily Activities of Living"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09390","kind":"arxiv","version":3},"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":"sha256:5ca9fd8e6468d769464376723d8103f4226bbc9abbcd5835c38f41804516d341","target":"record","created_at":"2026-07-05T10:39:19Z","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":"1ede09b60901f53fb92ffbf74aab764477df69eedf3228dd31b22024854a3098","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:05Z","title_canon_sha256":"e018ca2d6c6861b07d088f8e85a743773537ff7773e3d42fa0ca423865309158"},"schema_version":"1.0","source":{"id":"2406.09390","kind":"arxiv","version":3}},"canonical_sha256":"5b29cbb0e1b7f3cba4d9dcf35b0851756e307c46cac053fdc54e2a30ba828e77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b29cbb0e1b7f3cba4d9dcf35b0851756e307c46cac053fdc54e2a30ba828e77","first_computed_at":"2026-07-05T10:39:19.372192Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:39:19.372192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LQbgZyPn/FGDkrSru9+9KqxIwRIktH+gxrUzXy0KbNJPBqOgjIwdAlIyoPMCRGLgJEWx4rD0WGUYCfqEZ6/hBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:39:19.372599Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09390","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ca9fd8e6468d769464376723d8103f4226bbc9abbcd5835c38f41804516d341","sha256:61697ef2608318dd8d00c1f148957984cd0581482a8cb29ae8a6cc4b7770ebee"],"state_sha256":"11f1785b849038f664f276f716722a1aaa2f4d4f7d40eac26cb31aff243a7a72"}