{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QSRJ3KTVEYHGNLRJXZK7MFICNK","short_pith_number":"pith:QSRJ3KTV","schema_version":"1.0","canonical_sha256":"84a29daa75260e66ae29be55f615026a9f227e2c65bf4bf234c1064ddbcc8ff2","source":{"kind":"arxiv","id":"2406.09400","version":2},"attestation_state":"computed","paper":{"title":"Yo'LLaVA: Your Personalized Language and Vision Assistant","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Haotian Liu, Mu Cai, Thao Nguyen, Utkarsh Ojha, Yong Jae Lee, Yuheng Li","submitted_at":"2024-06-13T17:59:29Z","abstract_excerpt":"Large Multimodal Models (LMMs) have shown remarkable capabilities across a variety of tasks (e.g., image captioning, visual question answering). While broad, their knowledge remains generic (e.g., recognizing a dog), and they are unable to handle personalized subjects (e.g., recognizing a user's pet dog). Human reasoning, in contrast, typically operates within the context of specific subjects in our surroundings. For example, one might ask, \"What should I buy for my dog's birthday?\"; as opposed to a generic inquiry about \"What should I buy for a dog's birthday?\". Similarly, when looking at a f"},"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":"2406.09400","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"027202da9551c3d60f2c166b56d406c906dc4712740796ed9c96d4c6a9db06ca","abstract_canon_sha256":"35628e7d9f3c0208e1586942c654bbcad4ce66867d87ca723f4d1a853ea76434"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:10.190652Z","signature_b64":"Pp9JxdVMohBNwpkrTWOxuUY8Zo6Zcfn7yXxHoyD5HfuPwOKNHnyPGpVCqg31hwU8Jnihr/nGHJGtiz1KkcBfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84a29daa75260e66ae29be55f615026a9f227e2c65bf4bf234c1064ddbcc8ff2","last_reissued_at":"2026-07-05T09:44:10.190164Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:10.190164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Yo'LLaVA: Your Personalized Language and Vision Assistant","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Haotian Liu, Mu Cai, Thao Nguyen, Utkarsh Ojha, Yong Jae Lee, Yuheng Li","submitted_at":"2024-06-13T17:59:29Z","abstract_excerpt":"Large Multimodal Models (LMMs) have shown remarkable capabilities across a variety of tasks (e.g., image captioning, visual question answering). While broad, their knowledge remains generic (e.g., recognizing a dog), and they are unable to handle personalized subjects (e.g., recognizing a user's pet dog). Human reasoning, in contrast, typically operates within the context of specific subjects in our surroundings. For example, one might ask, \"What should I buy for my dog's birthday?\"; as opposed to a generic inquiry about \"What should I buy for a dog's birthday?\". Similarly, when looking at a f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09400","kind":"arxiv","version":2},"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/2406.09400/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":"2406.09400","created_at":"2026-07-05T09:44:10.190213+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09400v2","created_at":"2026-07-05T09:44:10.190213+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09400","created_at":"2026-07-05T09:44:10.190213+00:00"},{"alias_kind":"pith_short_12","alias_value":"QSRJ3KTVEYHG","created_at":"2026-07-05T09:44:10.190213+00:00"},{"alias_kind":"pith_short_16","alias_value":"QSRJ3KTVEYHGNLRJ","created_at":"2026-07-05T09:44:10.190213+00:00"},{"alias_kind":"pith_short_8","alias_value":"QSRJ3KTV","created_at":"2026-07-05T09:44:10.190213+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.02452","citing_title":"Personalization Toolkit: Training Free Personalization of Large Vision Language Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09996","citing_title":"Omni-Persona: Systematic Benchmarking and Improving Omnimodal Personalization","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QSRJ3KTVEYHGNLRJXZK7MFICNK","json":"https://pith.science/pith/QSRJ3KTVEYHGNLRJXZK7MFICNK.json","graph_json":"https://pith.science/api/pith-number/QSRJ3KTVEYHGNLRJXZK7MFICNK/graph.json","events_json":"https://pith.science/api/pith-number/QSRJ3KTVEYHGNLRJXZK7MFICNK/events.json","paper":"https://pith.science/paper/QSRJ3KTV"},"agent_actions":{"view_html":"https://pith.science/pith/QSRJ3KTVEYHGNLRJXZK7MFICNK","download_json":"https://pith.science/pith/QSRJ3KTVEYHGNLRJXZK7MFICNK.json","view_paper":"https://pith.science/paper/QSRJ3KTV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09400&json=true","fetch_graph":"https://pith.science/api/pith-number/QSRJ3KTVEYHGNLRJXZK7MFICNK/graph.json","fetch_events":"https://pith.science/api/pith-number/QSRJ3KTVEYHGNLRJXZK7MFICNK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QSRJ3KTVEYHGNLRJXZK7MFICNK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QSRJ3KTVEYHGNLRJXZK7MFICNK/action/storage_attestation","attest_author":"https://pith.science/pith/QSRJ3KTVEYHGNLRJXZK7MFICNK/action/author_attestation","sign_citation":"https://pith.science/pith/QSRJ3KTVEYHGNLRJXZK7MFICNK/action/citation_signature","submit_replication":"https://pith.science/pith/QSRJ3KTVEYHGNLRJXZK7MFICNK/action/replication_record"}},"created_at":"2026-07-05T09:44:10.190213+00:00","updated_at":"2026-07-05T09:44:10.190213+00:00"}