{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RYCLFXDFXTDKJ3RX7GU2YYWLL4","short_pith_number":"pith:RYCLFXDF","schema_version":"1.0","canonical_sha256":"8e04b2dc65bcc6a4ee37f9a9ac62cb5f24efd051ee5b598e5aaa163feef801d9","source":{"kind":"arxiv","id":"2606.05275","version":1},"attestation_state":"computed","paper":{"title":"Personal AI Agent for Camera Roll VQA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Donghyun Kim, Krishna Kumar Singh, Thao Nguyen, Yong Jae Lee, Yuheng Li","submitted_at":"2026-06-03T17:59:30Z","abstract_excerpt":"We study the personal camera roll visual question answering setting. In this setting, a conversational AI assistant can access a user's personal camera roll and retrieve relevant photos to answer queries, ranging from simple factual questions (e.g., ``Name of the food I tried yesterday?'') to more open-ended ones (e.g., ``Recommend some dishes I have never eaten before''). Given the vast nature of the personal camera roll (i.e., multiple years, hundreds to thousands of photos), a successful AI assistant needs to understand a long-horizon, highly personalized visual content stream in order to n"},"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":"2606.05275","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T17:59:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9b43d08f2befdce56900add0369e847cc7b9c8a8f864299441f427892ef9e132","abstract_canon_sha256":"4c866178caa35c322e9fcd75c7c241068030f8e1c2d60808bd0847e6395600a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T00:13:51.411330Z","signature_b64":"YisBg6CR74a+Eddga/lulHwBzVyq76khnhjyoe+wvhJK3oyib8b/J2h3zwklD9p/Wroy6bKM2i+KA9VhHaMFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e04b2dc65bcc6a4ee37f9a9ac62cb5f24efd051ee5b598e5aaa163feef801d9","last_reissued_at":"2026-06-05T00:13:51.410863Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T00:13:51.410863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Personal AI Agent for Camera Roll VQA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Donghyun Kim, Krishna Kumar Singh, Thao Nguyen, Yong Jae Lee, Yuheng Li","submitted_at":"2026-06-03T17:59:30Z","abstract_excerpt":"We study the personal camera roll visual question answering setting. In this setting, a conversational AI assistant can access a user's personal camera roll and retrieve relevant photos to answer queries, ranging from simple factual questions (e.g., ``Name of the food I tried yesterday?'') to more open-ended ones (e.g., ``Recommend some dishes I have never eaten before''). Given the vast nature of the personal camera roll (i.e., multiple years, hundreds to thousands of photos), a successful AI assistant needs to understand a long-horizon, highly personalized visual content stream in order to n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05275","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/2606.05275/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":"2606.05275","created_at":"2026-06-05T00:13:51.410945+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05275v1","created_at":"2026-06-05T00:13:51.410945+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05275","created_at":"2026-06-05T00:13:51.410945+00:00"},{"alias_kind":"pith_short_12","alias_value":"RYCLFXDFXTDK","created_at":"2026-06-05T00:13:51.410945+00:00"},{"alias_kind":"pith_short_16","alias_value":"RYCLFXDFXTDKJ3RX","created_at":"2026-06-05T00:13:51.410945+00:00"},{"alias_kind":"pith_short_8","alias_value":"RYCLFXDF","created_at":"2026-06-05T00:13:51.410945+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RYCLFXDFXTDKJ3RX7GU2YYWLL4","json":"https://pith.science/pith/RYCLFXDFXTDKJ3RX7GU2YYWLL4.json","graph_json":"https://pith.science/api/pith-number/RYCLFXDFXTDKJ3RX7GU2YYWLL4/graph.json","events_json":"https://pith.science/api/pith-number/RYCLFXDFXTDKJ3RX7GU2YYWLL4/events.json","paper":"https://pith.science/paper/RYCLFXDF"},"agent_actions":{"view_html":"https://pith.science/pith/RYCLFXDFXTDKJ3RX7GU2YYWLL4","download_json":"https://pith.science/pith/RYCLFXDFXTDKJ3RX7GU2YYWLL4.json","view_paper":"https://pith.science/paper/RYCLFXDF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05275&json=true","fetch_graph":"https://pith.science/api/pith-number/RYCLFXDFXTDKJ3RX7GU2YYWLL4/graph.json","fetch_events":"https://pith.science/api/pith-number/RYCLFXDFXTDKJ3RX7GU2YYWLL4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RYCLFXDFXTDKJ3RX7GU2YYWLL4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RYCLFXDFXTDKJ3RX7GU2YYWLL4/action/storage_attestation","attest_author":"https://pith.science/pith/RYCLFXDFXTDKJ3RX7GU2YYWLL4/action/author_attestation","sign_citation":"https://pith.science/pith/RYCLFXDFXTDKJ3RX7GU2YYWLL4/action/citation_signature","submit_replication":"https://pith.science/pith/RYCLFXDFXTDKJ3RX7GU2YYWLL4/action/replication_record"}},"created_at":"2026-06-05T00:13:51.410945+00:00","updated_at":"2026-06-05T00:13:51.410945+00:00"}