{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:E67EHFZFJEJS5NMMTDGCPL3GTH","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":"3dd5bc0080765fdc084d8461da364538c83910186b4eddbf7e9809ff350f0383","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-10-16T09:30:45Z","title_canon_sha256":"2cfcfaa602ddb266fa84417f3a0bf4a9c037bc7153edd7c19efd0c15c0abbe31"},"schema_version":"1.0","source":{"id":"2310.10221","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10221","created_at":"2026-07-05T07:48:32Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10221v2","created_at":"2026-07-05T07:48:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10221","created_at":"2026-07-05T07:48:32Z"},{"alias_kind":"pith_short_12","alias_value":"E67EHFZFJEJS","created_at":"2026-07-05T07:48:32Z"},{"alias_kind":"pith_short_16","alias_value":"E67EHFZFJEJS5NMM","created_at":"2026-07-05T07:48:32Z"},{"alias_kind":"pith_short_8","alias_value":"E67EHFZF","created_at":"2026-07-05T07:48:32Z"}],"graph_snapshots":[{"event_id":"sha256:e317209eff7fa200ea61fa45a68be8ef3d4de0a6b50ce896c8db5bb0a1262513","target":"graph","created_at":"2026-07-05T07:48:32Z","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/2310.10221/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robotic vision applications often necessitate a wide range of visual perception tasks, such as object detection, segmentation, and identification. While there have been substantial advances in these individual tasks, integrating specialized models into a unified vision pipeline presents significant engineering challenges and costs. Recently, Multimodal Large Language Models (MLLMs) have emerged as novel backbones for various downstream tasks. We argue that leveraging the pre-training capabilities of MLLMs enables the creation of a simplified framework, thus mitigating the need for task-specifi","authors_text":"George Killick, Gerardo Aragon Camarasa, Richard McCreadie, Zijun Long","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-10-16T09:30:45Z","title":"RoboLLM: Robotic Vision Tasks Grounded on Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10221","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":"sha256:7688dd56f01df920e25bd4851d23f340c461470f1a0e84aa23ebbe99144d8d10","target":"record","created_at":"2026-07-05T07:48:32Z","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":"3dd5bc0080765fdc084d8461da364538c83910186b4eddbf7e9809ff350f0383","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-10-16T09:30:45Z","title_canon_sha256":"2cfcfaa602ddb266fa84417f3a0bf4a9c037bc7153edd7c19efd0c15c0abbe31"},"schema_version":"1.0","source":{"id":"2310.10221","kind":"arxiv","version":2}},"canonical_sha256":"27be43972549132eb58c98cc27af6699eb91d5e14f789d5b2a24d455a314d90d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27be43972549132eb58c98cc27af6699eb91d5e14f789d5b2a24d455a314d90d","first_computed_at":"2026-07-05T07:48:32.105890Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:32.105890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ze3ZQdi4/6/I17SH/NAMvdkNycTjzrmaIsmj+fpBjQavAXfsPgAs7Xwk4QQNf2cN2//kIEplqXhuVFh6a/btDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:32.106396Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.10221","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7688dd56f01df920e25bd4851d23f340c461470f1a0e84aa23ebbe99144d8d10","sha256:e317209eff7fa200ea61fa45a68be8ef3d4de0a6b50ce896c8db5bb0a1262513"],"state_sha256":"6dee4eebd3b8196308e8689ed6808e8023f08aaa3d0d04209d8a01ae2b86918c"}