{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TZKTIPLZNCUYMQPCII75JJQ2NF","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":"aad1bfaf28050be5507530d31508042a2ad4c3f2f8edca8728b7b9047c267aad","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-11-15T13:47:00Z","title_canon_sha256":"dd3d9e7bbaeb6b467bf43e245f559b5cd78df366a3a7c9bf58c5b7e55a5df341"},"schema_version":"1.0","source":{"id":"2311.08957","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.08957","created_at":"2026-06-09T02:08:25Z"},{"alias_kind":"arxiv_version","alias_value":"2311.08957v1","created_at":"2026-06-09T02:08:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08957","created_at":"2026-06-09T02:08:25Z"},{"alias_kind":"pith_short_12","alias_value":"TZKTIPLZNCUY","created_at":"2026-06-09T02:08:25Z"},{"alias_kind":"pith_short_16","alias_value":"TZKTIPLZNCUYMQPC","created_at":"2026-06-09T02:08:25Z"},{"alias_kind":"pith_short_8","alias_value":"TZKTIPLZ","created_at":"2026-06-09T02:08:25Z"}],"graph_snapshots":[{"event_id":"sha256:66c3162437c8a5c7ad77b27c1c46c25cb98d84268a43427b2fc290900b5883de","target":"graph","created_at":"2026-06-09T02:08:25Z","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/2311.08957/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the rapidly evolving landscape of human-computer interaction, the integration of vision capabilities into conversational agents stands as a crucial advancement. This paper presents an initial implementation of a dialogue manager that leverages the latest progress in Large Language Models (e.g., GPT-4, IDEFICS) to enhance the traditional text-based prompts with real-time visual input. LLMs are used to interpret both textual prompts and visual stimuli, creating a more contextually aware conversational agent. The system's prompt engineering, incorporating dialogue with summarisation of the ima","authors_text":"Giulio Antonio Abbo, Tony Belpaeme","cross_cats":["cs.AI","cs.HC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-11-15T13:47:00Z","title":"I Was Blind but Now I See: Implementing Vision-Enabled Dialogue in Social Robots"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08957","kind":"arxiv","version":1},"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:dfe59d2703dd74249c183ea913811b26cf12f52037669e60e5292d9bf12adc47","target":"record","created_at":"2026-06-09T02:08:25Z","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":"aad1bfaf28050be5507530d31508042a2ad4c3f2f8edca8728b7b9047c267aad","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-11-15T13:47:00Z","title_canon_sha256":"dd3d9e7bbaeb6b467bf43e245f559b5cd78df366a3a7c9bf58c5b7e55a5df341"},"schema_version":"1.0","source":{"id":"2311.08957","kind":"arxiv","version":1}},"canonical_sha256":"9e55343d7968a98641e2423fd4a61a69758342d2a038bdfe616a478ed7a1620f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e55343d7968a98641e2423fd4a61a69758342d2a038bdfe616a478ed7a1620f","first_computed_at":"2026-06-09T02:08:25.429103Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:08:25.429103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yHTfz+r2K3C0BXte++oqw9Uqq8t6yTEWTpjz4uYg0oRLQmtcj2KMwrPQyoiKMmA32bkZCZTi4kK0u49hCKOTDA==","signature_status":"signed_v1","signed_at":"2026-06-09T02:08:25.432688Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.08957","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfe59d2703dd74249c183ea913811b26cf12f52037669e60e5292d9bf12adc47","sha256:66c3162437c8a5c7ad77b27c1c46c25cb98d84268a43427b2fc290900b5883de"],"state_sha256":"6715cc289b7e563939965e8e3f30f0864e7b8a1050d79674d9ca6304243520fc"}