{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LMU4XMHBW7Z4XJGZ3TZVWCCROV","short_pith_number":"pith:LMU4XMHB","schema_version":"1.0","canonical_sha256":"5b29cbb0e1b7f3cba4d9dcf35b0851756e307c46cac053fdc54e2a30ba828e77","source":{"kind":"arxiv","id":"2406.09390","version":3},"attestation_state":"computed","paper":{"title":"LLAVIDAL: A Large LAnguage VIsion Model for Daily Activities of Living","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Arkaprava Sinha, Dominick Reilly, Francois Bremond, Le Xue, Manish Kumar Govind, Pu Wang, Rajatsubhra Chakraborty, Srijan Das","submitted_at":"2024-06-13T17:59:05Z","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"},"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":"2406.09390","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e018ca2d6c6861b07d088f8e85a743773537ff7773e3d42fa0ca423865309158","abstract_canon_sha256":"1ede09b60901f53fb92ffbf74aab764477df69eedf3228dd31b22024854a3098"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:19.372599Z","signature_b64":"LQbgZyPn/FGDkrSru9+9KqxIwRIktH+gxrUzXy0KbNJPBqOgjIwdAlIyoPMCRGLgJEWx4rD0WGUYCfqEZ6/hBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b29cbb0e1b7f3cba4d9dcf35b0851756e307c46cac053fdc54e2a30ba828e77","last_reissued_at":"2026-07-05T10:39:19.372192Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:19.372192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLAVIDAL: A Large LAnguage VIsion Model for Daily Activities of Living","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Arkaprava Sinha, Dominick Reilly, Francois Bremond, Le Xue, Manish Kumar Govind, Pu Wang, Rajatsubhra Chakraborty, Srijan Das","submitted_at":"2024-06-13T17:59:05Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09390","kind":"arxiv","version":3},"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/2406.09390/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":"2406.09390","created_at":"2026-07-05T10:39:19.372251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09390v3","created_at":"2026-07-05T10:39:19.372251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09390","created_at":"2026-07-05T10:39:19.372251+00:00"},{"alias_kind":"pith_short_12","alias_value":"LMU4XMHBW7Z4","created_at":"2026-07-05T10:39:19.372251+00:00"},{"alias_kind":"pith_short_16","alias_value":"LMU4XMHBW7Z4XJGZ","created_at":"2026-07-05T10:39:19.372251+00:00"},{"alias_kind":"pith_short_8","alias_value":"LMU4XMHB","created_at":"2026-07-05T10:39:19.372251+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.03459","citing_title":"SKI Models: Skeleton Induced Vision-Language Embeddings for Understanding Activities of Daily Living","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LMU4XMHBW7Z4XJGZ3TZVWCCROV","json":"https://pith.science/pith/LMU4XMHBW7Z4XJGZ3TZVWCCROV.json","graph_json":"https://pith.science/api/pith-number/LMU4XMHBW7Z4XJGZ3TZVWCCROV/graph.json","events_json":"https://pith.science/api/pith-number/LMU4XMHBW7Z4XJGZ3TZVWCCROV/events.json","paper":"https://pith.science/paper/LMU4XMHB"},"agent_actions":{"view_html":"https://pith.science/pith/LMU4XMHBW7Z4XJGZ3TZVWCCROV","download_json":"https://pith.science/pith/LMU4XMHBW7Z4XJGZ3TZVWCCROV.json","view_paper":"https://pith.science/paper/LMU4XMHB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09390&json=true","fetch_graph":"https://pith.science/api/pith-number/LMU4XMHBW7Z4XJGZ3TZVWCCROV/graph.json","fetch_events":"https://pith.science/api/pith-number/LMU4XMHBW7Z4XJGZ3TZVWCCROV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LMU4XMHBW7Z4XJGZ3TZVWCCROV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LMU4XMHBW7Z4XJGZ3TZVWCCROV/action/storage_attestation","attest_author":"https://pith.science/pith/LMU4XMHBW7Z4XJGZ3TZVWCCROV/action/author_attestation","sign_citation":"https://pith.science/pith/LMU4XMHBW7Z4XJGZ3TZVWCCROV/action/citation_signature","submit_replication":"https://pith.science/pith/LMU4XMHBW7Z4XJGZ3TZVWCCROV/action/replication_record"}},"created_at":"2026-07-05T10:39:19.372251+00:00","updated_at":"2026-07-05T10:39:19.372251+00:00"}