{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QSRJ3KTVEYHGNLRJXZK7MFICNK","short_pith_number":"pith:QSRJ3KTV","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"},"canonical_sha256":"84a29daa75260e66ae29be55f615026a9f227e2c65bf4bf234c1064ddbcc8ff2","source":{"kind":"arxiv","id":"2406.09400","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09400","created_at":"2026-07-05T09:44:10Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09400v2","created_at":"2026-07-05T09:44:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09400","created_at":"2026-07-05T09:44:10Z"},{"alias_kind":"pith_short_12","alias_value":"QSRJ3KTVEYHG","created_at":"2026-07-05T09:44:10Z"},{"alias_kind":"pith_short_16","alias_value":"QSRJ3KTVEYHGNLRJ","created_at":"2026-07-05T09:44:10Z"},{"alias_kind":"pith_short_8","alias_value":"QSRJ3KTV","created_at":"2026-07-05T09:44:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QSRJ3KTVEYHGNLRJXZK7MFICNK","target":"record","payload":{"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"},"canonical_sha256":"84a29daa75260e66ae29be55f615026a9f227e2c65bf4bf234c1064ddbcc8ff2","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"},"source_kind":"arxiv","source_id":"2406.09400","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:44:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d1NDBHd2XiSa36OssDkBjAxiD6/v2ZaLSUCJMu8G9TbdgxLHy5auM6CcEvTVfhSR/9DthmWqlPayxrmCgdhDCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:42:26.805563Z"},"content_sha256":"0b2e16af90b053586336a84c29f2c14e5532fb7c24cdcd60902792316bf4fe79","schema_version":"1.0","event_id":"sha256:0b2e16af90b053586336a84c29f2c14e5532fb7c24cdcd60902792316bf4fe79"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QSRJ3KTVEYHGNLRJXZK7MFICNK","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:44:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LaUOjEVYheuXFDAKjnnmMEm8wvLR0q61s8+aYhaIYm8GMcSyzviAnmnu9sKmQ2vgOb/+ORiK3kw1udXOpZnRCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:42:26.806093Z"},"content_sha256":"217382d88443ebd50bd9ce5fe4fe660e2fd1cd2b9cf592178368cf97f3ad72ce","schema_version":"1.0","event_id":"sha256:217382d88443ebd50bd9ce5fe4fe660e2fd1cd2b9cf592178368cf97f3ad72ce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QSRJ3KTVEYHGNLRJXZK7MFICNK/bundle.json","state_url":"https://pith.science/pith/QSRJ3KTVEYHGNLRJXZK7MFICNK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QSRJ3KTVEYHGNLRJXZK7MFICNK/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":"2026-08-09T15:42:26Z","links":{"resolver":"https://pith.science/pith/QSRJ3KTVEYHGNLRJXZK7MFICNK","bundle":"https://pith.science/pith/QSRJ3KTVEYHGNLRJXZK7MFICNK/bundle.json","state":"https://pith.science/pith/QSRJ3KTVEYHGNLRJXZK7MFICNK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QSRJ3KTVEYHGNLRJXZK7MFICNK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QSRJ3KTVEYHGNLRJXZK7MFICNK","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":"35628e7d9f3c0208e1586942c654bbcad4ce66867d87ca723f4d1a853ea76434","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:29Z","title_canon_sha256":"027202da9551c3d60f2c166b56d406c906dc4712740796ed9c96d4c6a9db06ca"},"schema_version":"1.0","source":{"id":"2406.09400","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09400","created_at":"2026-07-05T09:44:10Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09400v2","created_at":"2026-07-05T09:44:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09400","created_at":"2026-07-05T09:44:10Z"},{"alias_kind":"pith_short_12","alias_value":"QSRJ3KTVEYHG","created_at":"2026-07-05T09:44:10Z"},{"alias_kind":"pith_short_16","alias_value":"QSRJ3KTVEYHGNLRJ","created_at":"2026-07-05T09:44:10Z"},{"alias_kind":"pith_short_8","alias_value":"QSRJ3KTV","created_at":"2026-07-05T09:44:10Z"}],"graph_snapshots":[{"event_id":"sha256:217382d88443ebd50bd9ce5fe4fe660e2fd1cd2b9cf592178368cf97f3ad72ce","target":"graph","created_at":"2026-07-05T09:44:10Z","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/2406.09400/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Haotian Liu, Mu Cai, Thao Nguyen, Utkarsh Ojha, Yong Jae Lee, Yuheng Li","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:29Z","title":"Yo'LLaVA: Your Personalized Language and Vision Assistant"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09400","kind":"arxiv","version":2},"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":"sha256:0b2e16af90b053586336a84c29f2c14e5532fb7c24cdcd60902792316bf4fe79","target":"record","created_at":"2026-07-05T09:44:10Z","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":"35628e7d9f3c0208e1586942c654bbcad4ce66867d87ca723f4d1a853ea76434","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:29Z","title_canon_sha256":"027202da9551c3d60f2c166b56d406c906dc4712740796ed9c96d4c6a9db06ca"},"schema_version":"1.0","source":{"id":"2406.09400","kind":"arxiv","version":2}},"canonical_sha256":"84a29daa75260e66ae29be55f615026a9f227e2c65bf4bf234c1064ddbcc8ff2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84a29daa75260e66ae29be55f615026a9f227e2c65bf4bf234c1064ddbcc8ff2","first_computed_at":"2026-07-05T09:44:10.190164Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:10.190164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Pp9JxdVMohBNwpkrTWOxuUY8Zo6Zcfn7yXxHoyD5HfuPwOKNHnyPGpVCqg31hwU8Jnihr/nGHJGtiz1KkcBfBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:10.190652Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09400","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b2e16af90b053586336a84c29f2c14e5532fb7c24cdcd60902792316bf4fe79","sha256:217382d88443ebd50bd9ce5fe4fe660e2fd1cd2b9cf592178368cf97f3ad72ce"],"state_sha256":"af12ae1049e19ca4e68dc49655547cdb797e73dbff021daea55f214b61e11d06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V5LhaD3+xZ+iNWq5Tv+gKlRA7zMMa2dl1FnXELJ2wq/hEfY7QWu9dzyPM08UAuUMVyUcsc7jT9tM/+2vRnFVCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T15:42:26.812316Z","bundle_sha256":"4e7a4fc370190a343882d57c0cc5dc7e9513d10f3d0139b10f74c092d1578083"}}