{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:R3N5CU5BH6GEUNGXVPGF57K7JK","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":"33ff0f00d8ed05dcb529ced906cb441037e00eb007cc976dbbd57c6a685061bb","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-21T23:31:57Z","title_canon_sha256":"e974f56565979abb913bd5875fd995fc796f604f8916a8d2dd9480b3b8341c11"},"schema_version":"1.0","source":{"id":"2407.15295","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.15295","created_at":"2026-07-05T08:46:41Z"},{"alias_kind":"arxiv_version","alias_value":"2407.15295v1","created_at":"2026-07-05T08:46:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15295","created_at":"2026-07-05T08:46:41Z"},{"alias_kind":"pith_short_12","alias_value":"R3N5CU5BH6GE","created_at":"2026-07-05T08:46:41Z"},{"alias_kind":"pith_short_16","alias_value":"R3N5CU5BH6GEUNGX","created_at":"2026-07-05T08:46:41Z"},{"alias_kind":"pith_short_8","alias_value":"R3N5CU5B","created_at":"2026-07-05T08:46:41Z"}],"graph_snapshots":[{"event_id":"sha256:d0768f8be74a61669e6f35d5ecc9dcf6847e6947c73c6265afde15665815e2e7","target":"graph","created_at":"2026-07-05T08:46:41Z","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/2407.15295/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large multimodal models (LMMs) hold substantial promise across various domains, from personal assistance in daily tasks to sophisticated applications like medical diagnostics. However, their capabilities have limitations in the video game domain, such as challenges with scene understanding, hallucinations, and inaccurate descriptions of video game content, especially in open-source models. This paper describes the development of VideoGameBunny, a LLaVA-style model based on Bunny, specifically tailored for understanding images from video games. We release intermediate checkpoints, training logs","authors_text":"Cor-Paul Bezemer, Mohammad Reza Taesiri","cross_cats":["cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-21T23:31:57Z","title":"VideoGameBunny: Towards vision assistants for video games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15295","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":"sha256:7e6d9b50274074d751ade331b14287860430f329d7adbd50081f25c30d51ba60","target":"record","created_at":"2026-07-05T08:46:41Z","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":"33ff0f00d8ed05dcb529ced906cb441037e00eb007cc976dbbd57c6a685061bb","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-21T23:31:57Z","title_canon_sha256":"e974f56565979abb913bd5875fd995fc796f604f8916a8d2dd9480b3b8341c11"},"schema_version":"1.0","source":{"id":"2407.15295","kind":"arxiv","version":1}},"canonical_sha256":"8edbd153a13f8c4a34d7abcc5efd5f4ab515171df8cefe1e3a11d552f39aed3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8edbd153a13f8c4a34d7abcc5efd5f4ab515171df8cefe1e3a11d552f39aed3c","first_computed_at":"2026-07-05T08:46:41.549435Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:41.549435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dg2EUdJRLtoT2ZBAp5VhkfrKoVIImvif4JgWw92ymWukZhkJ84z8zG9+sEQGi31StTXLWcGOmDXbCPzUQniPAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:41.549910Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.15295","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e6d9b50274074d751ade331b14287860430f329d7adbd50081f25c30d51ba60","sha256:d0768f8be74a61669e6f35d5ecc9dcf6847e6947c73c6265afde15665815e2e7"],"state_sha256":"4c42507e31a1360e473339e2c0f542fb9a5e09d342a787fd5d78c0caa0ce1b17"}