{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IWBYRN2ASLXKP6H7V375PJ5X4V","short_pith_number":"pith:IWBYRN2A","canonical_record":{"source":{"id":"2311.01378","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2023-11-02T16:34:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a46623a0809364e13041acd5187a238e16b787a3e7101eff9db09d46cb95d7f9","abstract_canon_sha256":"acf5b854e35077856f99fbbcc551f23d4efec5c2d3f5deccf242275df7a9dba8"},"schema_version":"1.0"},"canonical_sha256":"458388b74092eea7f8ffaeffd7a7b7e55266a2aeb2963d1e0f1e15ceefe3d1fc","source":{"kind":"arxiv","id":"2311.01378","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.01378","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2311.01378v3","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01378","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"IWBYRN2ASLXK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"IWBYRN2ASLXKP6H7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"IWBYRN2A","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IWBYRN2ASLXKP6H7V375PJ5X4V","target":"record","payload":{"canonical_record":{"source":{"id":"2311.01378","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2023-11-02T16:34:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a46623a0809364e13041acd5187a238e16b787a3e7101eff9db09d46cb95d7f9","abstract_canon_sha256":"acf5b854e35077856f99fbbcc551f23d4efec5c2d3f5deccf242275df7a9dba8"},"schema_version":"1.0"},"canonical_sha256":"458388b74092eea7f8ffaeffd7a7b7e55266a2aeb2963d1e0f1e15ceefe3d1fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:46.480027Z","signature_b64":"L9D4mjIB4siw7jWpM7R+Xd/KqkL3HDE5QJanziZc92qcLaS2grXF6HQQ/EGWMMlmlXiEKy98Ezz4ftEjus8FDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"458388b74092eea7f8ffaeffd7a7b7e55266a2aeb2963d1e0f1e15ceefe3d1fc","last_reissued_at":"2026-05-17T23:38:46.479380Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:46.479380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.01378","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"drG5jpipFbrd3CESTXwwrlGlerE/bb721dgAXYO3Hqc3aLEnSZUmmxkO9vCII7D2rDq4AOGy7ZZiajrXMKf+DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T01:12:12.522714Z"},"content_sha256":"7439e2974d1ced98920fcc14003f2043943ddd2b9c079b21c21293d75cd70db9","schema_version":"1.0","event_id":"sha256:7439e2974d1ced98920fcc14003f2043943ddd2b9c079b21c21293d75cd70db9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IWBYRN2ASLXKP6H7V375PJ5X4V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vision-Language Foundation Models as Effective Robot Imitators","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Simple fine-tuning adapts pre-trained vision-language models into robot policies that beat prior methods.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Chilam Cheang, Cunjun Yu, Hanbo Zhang, Hang Li, Hongtao Wu, Huaping Liu, Jie Xu, Minghuan Liu, Tao Kong, Weinan Zhang, Xinghang Li, Ya Jing","submitted_at":"2023-11-02T16:34:33Z","abstract_excerpt":"Recent progress in vision language foundation models has shown their ability to understand multimodal data and resolve complicated vision language tasks, including robotics manipulation. We seek a straightforward way of making use of existing vision-language models (VLMs) with simple fine-tuning on robotics data. To this end, we derive a simple and novel vision-language manipulation framework, dubbed RoboFlamingo, built upon the open-source VLMs, OpenFlamingo. Unlike prior works, RoboFlamingo utilizes pre-trained VLMs for single-step vision-language comprehension, models sequential history inf"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"By exceeding the state-of-the-art performance with a large margin on the tested benchmark, we show RoboFlamingo can be an effective and competitive alternative to adapt VLMs to robot control.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That modest fine-tuning on existing language-conditioned manipulation datasets is sufficient to transfer the general vision-language understanding of pre-trained VLMs into reliable sequential robot policies without catastrophic forgetting or domain shift.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"RoboFlamingo adapts open-source vision-language models for robot manipulation tasks via single-step comprehension plus an explicit policy head, outperforming prior methods on benchmarks with only light fine-tuning.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Simple fine-tuning adapts pre-trained vision-language models into robot policies that beat prior methods.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"91a85c646de6f8822037a18cc2a3b4a068bb69e07509d595515f345f2f48dba5"},"source":{"id":"2311.01378","kind":"arxiv","version":3},"verdict":{"id":"164d1108-8125-4063-9f30-d765cb47c30c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T21:40:52.339632Z","strongest_claim":"By exceeding the state-of-the-art performance with a large margin on the tested benchmark, we show RoboFlamingo can be an effective and competitive alternative to adapt VLMs to robot control.","one_line_summary":"RoboFlamingo adapts open-source vision-language models for robot manipulation tasks via single-step comprehension plus an explicit policy head, outperforming prior methods on benchmarks with only light fine-tuning.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That modest fine-tuning on existing language-conditioned manipulation datasets is sufficient to transfer the general vision-language understanding of pre-trained VLMs into reliable sequential robot policies without catastrophic forgetting or domain shift.","pith_extraction_headline":"Simple fine-tuning adapts pre-trained vision-language models into robot policies that beat prior methods."},"references":{"count":25,"sample":[{"doi":"","year":null,"title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","work_id":"037320f1-b0a9-4cbe-a639-bfb25409ce71","ref_index":1,"cited_arxiv_id":"2204.01691","is_internal_anchor":true},{"doi":"","year":null,"title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","work_id":"87bfa84a-e663-4165-806f-93ef439d88d0","ref_index":2,"cited_arxiv_id":"2308.01390","is_internal_anchor":true},{"doi":"","year":null,"title":"S., Purohit, S., Reynolds, L., Tow, J., Wang, B., and Weinbach, S","work_id":"168a55d5-675d-49cf-be47-a17ee8cd742e","ref_index":3,"cited_arxiv_id":"2204.06745","is_internal_anchor":true},{"doi":"","year":null,"title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","work_id":"ff438a8a-8003-4fae-9131-acd418b3597b","ref_index":4,"cited_arxiv_id":"2307.15818","is_internal_anchor":true},{"doi":"","year":1901,"title":"Language models are few-shot learners","work_id":"677093e0-2019-45af-8c52-d9b33dec7e3d","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":25,"snapshot_sha256":"176287bd0ea2afcf183ff6e753d1f38baffb67f66ee0f0a9630a812af836f494","internal_anchors":13},"formal_canon":{"evidence_count":2,"snapshot_sha256":"b2d9565cc7de3aef309fec141a2ba2e069e8709d5cb7b522e9343be85d23e6d7"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"164d1108-8125-4063-9f30-d765cb47c30c"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OqDpu4uLpgid95gLeSYKfGeReLaWStS/bhchpCve+f9hcQvEIn1SvDlvJ9JFnOAj1K5cReZ7jgdDJBAqR4M1Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T01:12:12.523297Z"},"content_sha256":"c45b66d844da92e76ec17d984e042c16a5b5436ee28d87e174efa2362a9ce908","schema_version":"1.0","event_id":"sha256:c45b66d844da92e76ec17d984e042c16a5b5436ee28d87e174efa2362a9ce908"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IWBYRN2ASLXKP6H7V375PJ5X4V/bundle.json","state_url":"https://pith.science/pith/IWBYRN2ASLXKP6H7V375PJ5X4V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IWBYRN2ASLXKP6H7V375PJ5X4V/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":"2026-05-27T01:12:12Z","links":{"resolver":"https://pith.science/pith/IWBYRN2ASLXKP6H7V375PJ5X4V","bundle":"https://pith.science/pith/IWBYRN2ASLXKP6H7V375PJ5X4V/bundle.json","state":"https://pith.science/pith/IWBYRN2ASLXKP6H7V375PJ5X4V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IWBYRN2ASLXKP6H7V375PJ5X4V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IWBYRN2ASLXKP6H7V375PJ5X4V","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":"acf5b854e35077856f99fbbcc551f23d4efec5c2d3f5deccf242275df7a9dba8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2023-11-02T16:34:33Z","title_canon_sha256":"a46623a0809364e13041acd5187a238e16b787a3e7101eff9db09d46cb95d7f9"},"schema_version":"1.0","source":{"id":"2311.01378","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.01378","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2311.01378v3","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01378","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"IWBYRN2ASLXK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"IWBYRN2ASLXKP6H7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"IWBYRN2A","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:c45b66d844da92e76ec17d984e042c16a5b5436ee28d87e174efa2362a9ce908","target":"graph","created_at":"2026-05-17T23:38:46Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"By exceeding the state-of-the-art performance with a large margin on the tested benchmark, we show RoboFlamingo can be an effective and competitive alternative to adapt VLMs to robot control."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That modest fine-tuning on existing language-conditioned manipulation datasets is sufficient to transfer the general vision-language understanding of pre-trained VLMs into reliable sequential robot policies without catastrophic forgetting or domain shift."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"RoboFlamingo adapts open-source vision-language models for robot manipulation tasks via single-step comprehension plus an explicit policy head, outperforming prior methods on benchmarks with only light fine-tuning."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Simple fine-tuning adapts pre-trained vision-language models into robot policies that beat prior methods."}],"snapshot_sha256":"91a85c646de6f8822037a18cc2a3b4a068bb69e07509d595515f345f2f48dba5"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"b2d9565cc7de3aef309fec141a2ba2e069e8709d5cb7b522e9343be85d23e6d7"},"paper":{"abstract_excerpt":"Recent progress in vision language foundation models has shown their ability to understand multimodal data and resolve complicated vision language tasks, including robotics manipulation. We seek a straightforward way of making use of existing vision-language models (VLMs) with simple fine-tuning on robotics data. To this end, we derive a simple and novel vision-language manipulation framework, dubbed RoboFlamingo, built upon the open-source VLMs, OpenFlamingo. Unlike prior works, RoboFlamingo utilizes pre-trained VLMs for single-step vision-language comprehension, models sequential history inf","authors_text":"Chilam Cheang, Cunjun Yu, Hanbo Zhang, Hang Li, Hongtao Wu, Huaping Liu, Jie Xu, Minghuan Liu, Tao Kong, Weinan Zhang, Xinghang Li, Ya Jing","cross_cats":["cs.AI","cs.LG"],"headline":"Simple fine-tuning adapts pre-trained vision-language models into robot policies that beat prior methods.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2023-11-02T16:34:33Z","title":"Vision-Language Foundation Models as Effective Robot Imitators"},"references":{"count":25,"internal_anchors":13,"resolved_work":25,"sample":[{"cited_arxiv_id":"2204.01691","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","work_id":"037320f1-b0a9-4cbe-a639-bfb25409ce71","year":null},{"cited_arxiv_id":"2308.01390","doi":"","is_internal_anchor":true,"ref_index":2,"title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","work_id":"87bfa84a-e663-4165-806f-93ef439d88d0","year":null},{"cited_arxiv_id":"2204.06745","doi":"","is_internal_anchor":true,"ref_index":3,"title":"S., Purohit, S., Reynolds, L., Tow, J., Wang, B., and Weinbach, S","work_id":"168a55d5-675d-49cf-be47-a17ee8cd742e","year":null},{"cited_arxiv_id":"2307.15818","doi":"","is_internal_anchor":true,"ref_index":4,"title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","work_id":"ff438a8a-8003-4fae-9131-acd418b3597b","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Language models are few-shot learners","work_id":"677093e0-2019-45af-8c52-d9b33dec7e3d","year":1901}],"snapshot_sha256":"176287bd0ea2afcf183ff6e753d1f38baffb67f66ee0f0a9630a812af836f494"},"source":{"id":"2311.01378","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T21:40:52.339632Z","id":"164d1108-8125-4063-9f30-d765cb47c30c","model_set":{"reader":"grok-4.3"},"one_line_summary":"RoboFlamingo adapts open-source vision-language models for robot manipulation tasks via single-step comprehension plus an explicit policy head, outperforming prior methods on benchmarks with only light fine-tuning.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Simple fine-tuning adapts pre-trained vision-language models into robot policies that beat prior methods.","strongest_claim":"By exceeding the state-of-the-art performance with a large margin on the tested benchmark, we show RoboFlamingo can be an effective and competitive alternative to adapt VLMs to robot control.","weakest_assumption":"That modest fine-tuning on existing language-conditioned manipulation datasets is sufficient to transfer the general vision-language understanding of pre-trained VLMs into reliable sequential robot policies without catastrophic forgetting or domain shift."}},"verdict_id":"164d1108-8125-4063-9f30-d765cb47c30c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7439e2974d1ced98920fcc14003f2043943ddd2b9c079b21c21293d75cd70db9","target":"record","created_at":"2026-05-17T23:38:46Z","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":"acf5b854e35077856f99fbbcc551f23d4efec5c2d3f5deccf242275df7a9dba8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2023-11-02T16:34:33Z","title_canon_sha256":"a46623a0809364e13041acd5187a238e16b787a3e7101eff9db09d46cb95d7f9"},"schema_version":"1.0","source":{"id":"2311.01378","kind":"arxiv","version":3}},"canonical_sha256":"458388b74092eea7f8ffaeffd7a7b7e55266a2aeb2963d1e0f1e15ceefe3d1fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"458388b74092eea7f8ffaeffd7a7b7e55266a2aeb2963d1e0f1e15ceefe3d1fc","first_computed_at":"2026-05-17T23:38:46.479380Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:46.479380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L9D4mjIB4siw7jWpM7R+Xd/KqkL3HDE5QJanziZc92qcLaS2grXF6HQQ/EGWMMlmlXiEKy98Ezz4ftEjus8FDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:46.480027Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.01378","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7439e2974d1ced98920fcc14003f2043943ddd2b9c079b21c21293d75cd70db9","sha256:c45b66d844da92e76ec17d984e042c16a5b5436ee28d87e174efa2362a9ce908"],"state_sha256":"e8e248b9721ee7d043e5c1df204c574e0453d5ffe9076c58dc1f70ebf0f24989"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XiHjr9CMROp+FxZzWS3Z4V2HuLqWJqGFH+g2SXi8K38VCWrIgTW/QxicMFDAw2Lneaojp8DMSry0GHwUmYTdDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T01:12:12.527529Z","bundle_sha256":"e7825ebc36d16fa1594a894c5cc62ab9aeb621175e5f40a7a9a71977574e7b62"}}