{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MF56J2GK6GG7HLWEKBMDCQIZNR","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":"07cf2330a3cd026091aa9a1c9844e6c8e319bf3e17c71c1d4d5d882af73728e0","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-19T23:34:48Z","title_canon_sha256":"15a23a1fcd96ce09ddeabe4b23f3901544699ba0020df964f2fb36fbbbd09c97"},"schema_version":"1.0","source":{"id":"2401.11061","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.11061","created_at":"2026-07-05T09:54:00Z"},{"alias_kind":"arxiv_version","alias_value":"2401.11061v4","created_at":"2026-07-05T09:54:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11061","created_at":"2026-07-05T09:54:00Z"},{"alias_kind":"pith_short_12","alias_value":"MF56J2GK6GG7","created_at":"2026-07-05T09:54:00Z"},{"alias_kind":"pith_short_16","alias_value":"MF56J2GK6GG7HLWE","created_at":"2026-07-05T09:54:00Z"},{"alias_kind":"pith_short_8","alias_value":"MF56J2GK","created_at":"2026-07-05T09:54:00Z"}],"graph_snapshots":[{"event_id":"sha256:f9cb2d61b2d530cc99a20ab9590024049624cf2c0c74e5b9738b92f084fe4f3f","target":"graph","created_at":"2026-07-05T09:54:00Z","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/2401.11061/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce PhotoBot, a framework for fully automated photo acquisition based on an interplay between high-level human language guidance and a robot photographer. We propose to communicate photography suggestions to the user via reference images that are selected from a curated gallery. We leverage a visual language model (VLM) and an object detector to characterize the reference images via textual descriptions and then use a large language model (LLM) to retrieve relevant reference images based on a user's language query through text-based reasoning. To correspond the reference image and the","authors_text":"Dmitriy Rivkin, Gregory Dudek, Jimmy Li, Jonathan Kelly, Oliver Limoyo","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-19T23:34:48Z","title":"PhotoBot: Reference-Guided Interactive Photography via Natural Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11061","kind":"arxiv","version":4},"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":"sha256:2e6d9f29c0ab45d5cbb4e27814aa933666359c46af8713479e9515a36f139060","target":"record","created_at":"2026-07-05T09:54:00Z","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":"07cf2330a3cd026091aa9a1c9844e6c8e319bf3e17c71c1d4d5d882af73728e0","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-19T23:34:48Z","title_canon_sha256":"15a23a1fcd96ce09ddeabe4b23f3901544699ba0020df964f2fb36fbbbd09c97"},"schema_version":"1.0","source":{"id":"2401.11061","kind":"arxiv","version":4}},"canonical_sha256":"617be4e8caf18df3aec450583141196c66bda77ca5abaeffefa6ed84a5866ea1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"617be4e8caf18df3aec450583141196c66bda77ca5abaeffefa6ed84a5866ea1","first_computed_at":"2026-07-05T09:54:00.853076Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:00.853076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WCmCNLvvfjBwc2G4x6Z9vdrD+e6D8nsITNjLf8g0WwbqFcG6Eic98TeCZxp88yttw36Chr8qSMK0Yl/kWq5SAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:00.853591Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.11061","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e6d9f29c0ab45d5cbb4e27814aa933666359c46af8713479e9515a36f139060","sha256:f9cb2d61b2d530cc99a20ab9590024049624cf2c0c74e5b9738b92f084fe4f3f"],"state_sha256":"ce7c7e32de7ab902d2e4fe212da2f24c0b88d4ce7061b580c196ec8f19d335a8"}