{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:E67EHFZFJEJS5NMMTDGCPL3GTH","short_pith_number":"pith:E67EHFZF","canonical_record":{"source":{"id":"2310.10221","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-10-16T09:30:45Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2cfcfaa602ddb266fa84417f3a0bf4a9c037bc7153edd7c19efd0c15c0abbe31","abstract_canon_sha256":"3dd5bc0080765fdc084d8461da364538c83910186b4eddbf7e9809ff350f0383"},"schema_version":"1.0"},"canonical_sha256":"27be43972549132eb58c98cc27af6699eb91d5e14f789d5b2a24d455a314d90d","source":{"kind":"arxiv","id":"2310.10221","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:E67EHFZFJEJS5NMMTDGCPL3GTH","target":"record","payload":{"canonical_record":{"source":{"id":"2310.10221","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-10-16T09:30:45Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2cfcfaa602ddb266fa84417f3a0bf4a9c037bc7153edd7c19efd0c15c0abbe31","abstract_canon_sha256":"3dd5bc0080765fdc084d8461da364538c83910186b4eddbf7e9809ff350f0383"},"schema_version":"1.0"},"canonical_sha256":"27be43972549132eb58c98cc27af6699eb91d5e14f789d5b2a24d455a314d90d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:32.106396Z","signature_b64":"ze3ZQdi4/6/I17SH/NAMvdkNycTjzrmaIsmj+fpBjQavAXfsPgAs7Xwk4QQNf2cN2//kIEplqXhuVFh6a/btDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27be43972549132eb58c98cc27af6699eb91d5e14f789d5b2a24d455a314d90d","last_reissued_at":"2026-07-05T07:48:32.105890Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:32.105890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.10221","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:48:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hUN06HdHUBTWpccV7JILBtTMWNEX2TErOPsk5iqZKPjjt3xiwk3AQFs/Q3Lg1oALTk6Y5GjCQkx1Vuw91QJLBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:09:04.173378Z"},"content_sha256":"7688dd56f01df920e25bd4851d23f340c461470f1a0e84aa23ebbe99144d8d10","schema_version":"1.0","event_id":"sha256:7688dd56f01df920e25bd4851d23f340c461470f1a0e84aa23ebbe99144d8d10"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:E67EHFZFJEJS5NMMTDGCPL3GTH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RoboLLM: Robotic Vision Tasks Grounded on Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"George Killick, Gerardo Aragon Camarasa, Richard McCreadie, Zijun Long","submitted_at":"2023-10-16T09:30:45Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10221","kind":"arxiv","version":2},"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/2310.10221/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:48:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6a0vN6WZ3z8RF05Vixx1OG0G+edTzb6aEyeQfwGZ9NURjYFjgq1s58EiYz0DIAkaazaeDYxe2S539aZpzH/QCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:09:04.173758Z"},"content_sha256":"e317209eff7fa200ea61fa45a68be8ef3d4de0a6b50ce896c8db5bb0a1262513","schema_version":"1.0","event_id":"sha256:e317209eff7fa200ea61fa45a68be8ef3d4de0a6b50ce896c8db5bb0a1262513"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E67EHFZFJEJS5NMMTDGCPL3GTH/bundle.json","state_url":"https://pith.science/pith/E67EHFZFJEJS5NMMTDGCPL3GTH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E67EHFZFJEJS5NMMTDGCPL3GTH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T15:09:04Z","links":{"resolver":"https://pith.science/pith/E67EHFZFJEJS5NMMTDGCPL3GTH","bundle":"https://pith.science/pith/E67EHFZFJEJS5NMMTDGCPL3GTH/bundle.json","state":"https://pith.science/pith/E67EHFZFJEJS5NMMTDGCPL3GTH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E67EHFZFJEJS5NMMTDGCPL3GTH/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s2SemSnkLwo7aRltNyuTJfledTib5xIkVWpOh0C31VW8lnkTap40sok2HDasjbIbQ9j+e/yg8I6sH4kExdd0Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T15:09:04.175727Z","bundle_sha256":"122f573bd7ddaf6514704661b9f2601704a4a2a1fcb6e4034382be684a2854b3"}}