{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:E3T33REDAUK72EVJZT4BVCFQGB","short_pith_number":"pith:E3T33RED","canonical_record":{"source":{"id":"2412.14058","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-18T17:07:20Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"68aff8c3e3373b6aae6aedffb5e6c987e6510dab548baddf2b11e15244a28776","abstract_canon_sha256":"334f8ebbf897361337c756e401d8bad05d9afe3016185d1262c03aca70045cd6"},"schema_version":"1.0"},"canonical_sha256":"26e7bdc4830515fd12a9ccf81a88b0304845d02a7ee8022d7163fbd4f8dbd609","source":{"kind":"arxiv","id":"2412.14058","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14058","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14058v4","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14058","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"E3T33REDAUK7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"E3T33REDAUK72EVJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"E3T33RED","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:E3T33REDAUK72EVJZT4BVCFQGB","target":"record","payload":{"canonical_record":{"source":{"id":"2412.14058","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-18T17:07:20Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"68aff8c3e3373b6aae6aedffb5e6c987e6510dab548baddf2b11e15244a28776","abstract_canon_sha256":"334f8ebbf897361337c756e401d8bad05d9afe3016185d1262c03aca70045cd6"},"schema_version":"1.0"},"canonical_sha256":"26e7bdc4830515fd12a9ccf81a88b0304845d02a7ee8022d7163fbd4f8dbd609","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:13.007578Z","signature_b64":"u7E0Ynleg5WCOorRf+OVtExejtEqvST/Q+IRlKCL7t+Ru3aj9mn15qdVAl80zfURZ5r4e645ahwLEMHQQfk/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26e7bdc4830515fd12a9ccf81a88b0304845d02a7ee8022d7163fbd4f8dbd609","last_reissued_at":"2026-05-17T23:38:13.006948Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:13.006948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.14058","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O43mFyxFBRwGFdsFCwsuw0Ox4XIrdoOidJNuj5ro1ASNArokl6Ia2hYt4ypCdvut5rx8P/KMYwdV5WWmPbVOCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:23:21.544820Z"},"content_sha256":"b8172326c0d39ee0871ad207c94b39b1b97246ddf8f6dd40fef3452c1a247b2a","schema_version":"1.0","event_id":"sha256:b8172326c0d39ee0871ad207c94b39b1b97246ddf8f6dd40fef3452c1a247b2a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:E3T33REDAUK72EVJZT4BVCFQGB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What Matters in Building Vision-Language-Action Models for Generalist Robots","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Specific choices in backbones, architectures, and data timing let simple Vision-Language-Action models set new robot manipulation records.","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Bingyi Kang, Di Guo, Dong Wang, Hanbo Zhang, Huaping Liu, Jirong Liu, Long Qian, Minghuan Liu, Peiyan Li, Tao Kong, Xiao Ma, Xinghang Li, Xinlong Wang","submitted_at":"2024-12-18T17:07:20Z","abstract_excerpt":"To utilize Foundation Vision Language Models (VLMs) for robotic tasks and motion planning, the community has proposed different methods for injecting action components into VLMs and building the Vision-Language-Action models (VLAs). In this work, we disclose the key factors that significantly influence the performance of VLA on robot manipulation problems and focus on answering three essential design choices: which backbone to select, how to formulate the VLA architectures, and when to add cross-embodiment data. The obtained results convince us firmly to explain why we prefer VLA and develop a"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Through extensive experiments which include over 8 VLM backbones, 4 policy architectures, and over 600 distinct designed experiments, we provide a detailed guidebook for the future design of VLAs... RoboVLMs... achieve a new state-of-the-art performance in three simulation tasks and real-world experiments.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the chosen simulation tasks and real-world experiments are representative enough of generalist robot manipulation that the observed ranking of design choices will transfer to new tasks, embodiments, and environments not tested in the 600+ runs.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Systematic tests of VLM backbones, policy architectures, and cross-embodiment data yield RoboVLMs that set new SOTA on robot manipulation benchmarks while requiring few manual designs.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Specific choices in backbones, architectures, and data timing let simple Vision-Language-Action models set new robot manipulation records.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"233bf637abbb829875db7cf18e555ed55f389674e64b32d2597d2ef338c8487f"},"source":{"id":"2412.14058","kind":"arxiv","version":4},"verdict":{"id":"5de490e9-804b-4794-af7a-10c5bab1f587","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T21:33:48.446845Z","strongest_claim":"Through extensive experiments which include over 8 VLM backbones, 4 policy architectures, and over 600 distinct designed experiments, we provide a detailed guidebook for the future design of VLAs... RoboVLMs... achieve a new state-of-the-art performance in three simulation tasks and real-world experiments.","one_line_summary":"Systematic tests of VLM backbones, policy architectures, and cross-embodiment data yield RoboVLMs that set new SOTA on robot manipulation benchmarks while requiring few manual designs.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the chosen simulation tasks and real-world experiments are representative enough of generalist robot manipulation that the observed ranking of design choices will transfer to new tasks, embodiments, and environments not tested in the 600+ runs.","pith_extraction_headline":"Specific choices in backbones, architectures, and data timing let simple Vision-Language-Action models set new robot manipulation records."},"references":{"count":54,"sample":[{"doi":"","year":2022,"title":"Flamingo: a visual language model for few-shot learning","work_id":"abe0dc9d-38b0-4f78-87e4-1f56476c29c8","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","work_id":"cbc2bb21-b6bb-46c0-80bf-107e195ffe10","ref_index":2,"cited_arxiv_id":"2308.12966","is_internal_anchor":true},{"doi":"","year":2024,"title":"PaliGemma: A versatile 3B VLM for transfer","work_id":"df6f48b3-5792-47c7-9614-cb856ea31ad9","ref_index":3,"cited_arxiv_id":"2407.07726","is_internal_anchor":true},{"doi":"","year":2024,"title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","work_id":"f790abdc-a796-482f-a40d-f8ee035ecfc2","ref_index":4,"cited_arxiv_id":"2410.24164","is_internal_anchor":true},{"doi":"","year":2023,"title":"RoboCat : A self-improving foundation agent for robotic manipulation","work_id":"143e7731-0488-4088-8e23-63f9d4140118","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":54,"snapshot_sha256":"068783adc0418b56d569a8d0f13ce528ebe66b651ad9e79116787bc514b71dec","internal_anchors":25},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8df15057d85122e96a54c885c04271576961ff57df3c998dfacce45ccdae174c"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"5de490e9-804b-4794-af7a-10c5bab1f587"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c/l9nk6eMZ1N6VfyjmnE3aC8z1YRzCn+tg4iNlZvzHmzevynvrk1HpcfCX+SMi0W6x408+AbsAnlit6ewttmCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:23:21.545856Z"},"content_sha256":"e2a260c128369a5e7f927d6a68fab19f1e1c1e7a43c6e055f6f12feec82ad6b9","schema_version":"1.0","event_id":"sha256:e2a260c128369a5e7f927d6a68fab19f1e1c1e7a43c6e055f6f12feec82ad6b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E3T33REDAUK72EVJZT4BVCFQGB/bundle.json","state_url":"https://pith.science/pith/E3T33REDAUK72EVJZT4BVCFQGB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E3T33REDAUK72EVJZT4BVCFQGB/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":"2026-05-25T19:23:21Z","links":{"resolver":"https://pith.science/pith/E3T33REDAUK72EVJZT4BVCFQGB","bundle":"https://pith.science/pith/E3T33REDAUK72EVJZT4BVCFQGB/bundle.json","state":"https://pith.science/pith/E3T33REDAUK72EVJZT4BVCFQGB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E3T33REDAUK72EVJZT4BVCFQGB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:E3T33REDAUK72EVJZT4BVCFQGB","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":"334f8ebbf897361337c756e401d8bad05d9afe3016185d1262c03aca70045cd6","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-18T17:07:20Z","title_canon_sha256":"68aff8c3e3373b6aae6aedffb5e6c987e6510dab548baddf2b11e15244a28776"},"schema_version":"1.0","source":{"id":"2412.14058","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14058","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14058v4","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14058","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"E3T33REDAUK7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"E3T33REDAUK72EVJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"E3T33RED","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:e2a260c128369a5e7f927d6a68fab19f1e1c1e7a43c6e055f6f12feec82ad6b9","target":"graph","created_at":"2026-05-17T23:38:13Z","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":"Through extensive experiments which include over 8 VLM backbones, 4 policy architectures, and over 600 distinct designed experiments, we provide a detailed guidebook for the future design of VLAs... RoboVLMs... achieve a new state-of-the-art performance in three simulation tasks and real-world experiments."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the chosen simulation tasks and real-world experiments are representative enough of generalist robot manipulation that the observed ranking of design choices will transfer to new tasks, embodiments, and environments not tested in the 600+ runs."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Systematic tests of VLM backbones, policy architectures, and cross-embodiment data yield RoboVLMs that set new SOTA on robot manipulation benchmarks while requiring few manual designs."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Specific choices in backbones, architectures, and data timing let simple Vision-Language-Action models set new robot manipulation records."}],"snapshot_sha256":"233bf637abbb829875db7cf18e555ed55f389674e64b32d2597d2ef338c8487f"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8df15057d85122e96a54c885c04271576961ff57df3c998dfacce45ccdae174c"},"paper":{"abstract_excerpt":"To utilize Foundation Vision Language Models (VLMs) for robotic tasks and motion planning, the community has proposed different methods for injecting action components into VLMs and building the Vision-Language-Action models (VLAs). In this work, we disclose the key factors that significantly influence the performance of VLA on robot manipulation problems and focus on answering three essential design choices: which backbone to select, how to formulate the VLA architectures, and when to add cross-embodiment data. The obtained results convince us firmly to explain why we prefer VLA and develop a","authors_text":"Bingyi Kang, Di Guo, Dong Wang, Hanbo Zhang, Huaping Liu, Jirong Liu, Long Qian, Minghuan Liu, Peiyan Li, Tao Kong, Xiao Ma, Xinghang Li, Xinlong Wang","cross_cats":["cs.CV"],"headline":"Specific choices in backbones, architectures, and data timing let simple Vision-Language-Action models set new robot manipulation records.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-18T17:07:20Z","title":"What Matters in Building Vision-Language-Action Models for Generalist Robots"},"references":{"count":54,"internal_anchors":25,"resolved_work":54,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Flamingo: a visual language model for few-shot learning","work_id":"abe0dc9d-38b0-4f78-87e4-1f56476c29c8","year":2022},{"cited_arxiv_id":"2308.12966","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","work_id":"cbc2bb21-b6bb-46c0-80bf-107e195ffe10","year":2023},{"cited_arxiv_id":"2407.07726","doi":"","is_internal_anchor":true,"ref_index":3,"title":"PaliGemma: A versatile 3B VLM for transfer","work_id":"df6f48b3-5792-47c7-9614-cb856ea31ad9","year":2024},{"cited_arxiv_id":"2410.24164","doi":"","is_internal_anchor":true,"ref_index":4,"title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","work_id":"f790abdc-a796-482f-a40d-f8ee035ecfc2","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"RoboCat : A self-improving foundation agent for robotic manipulation","work_id":"143e7731-0488-4088-8e23-63f9d4140118","year":2023}],"snapshot_sha256":"068783adc0418b56d569a8d0f13ce528ebe66b651ad9e79116787bc514b71dec"},"source":{"id":"2412.14058","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-17T21:33:48.446845Z","id":"5de490e9-804b-4794-af7a-10c5bab1f587","model_set":{"reader":"grok-4.3"},"one_line_summary":"Systematic tests of VLM backbones, policy architectures, and cross-embodiment data yield RoboVLMs that set new SOTA on robot manipulation benchmarks while requiring few manual designs.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Specific choices in backbones, architectures, and data timing let simple Vision-Language-Action models set new robot manipulation records.","strongest_claim":"Through extensive experiments which include over 8 VLM backbones, 4 policy architectures, and over 600 distinct designed experiments, we provide a detailed guidebook for the future design of VLAs... RoboVLMs... achieve a new state-of-the-art performance in three simulation tasks and real-world experiments.","weakest_assumption":"That the chosen simulation tasks and real-world experiments are representative enough of generalist robot manipulation that the observed ranking of design choices will transfer to new tasks, embodiments, and environments not tested in the 600+ runs."}},"verdict_id":"5de490e9-804b-4794-af7a-10c5bab1f587"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b8172326c0d39ee0871ad207c94b39b1b97246ddf8f6dd40fef3452c1a247b2a","target":"record","created_at":"2026-05-17T23:38:13Z","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":"334f8ebbf897361337c756e401d8bad05d9afe3016185d1262c03aca70045cd6","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-18T17:07:20Z","title_canon_sha256":"68aff8c3e3373b6aae6aedffb5e6c987e6510dab548baddf2b11e15244a28776"},"schema_version":"1.0","source":{"id":"2412.14058","kind":"arxiv","version":4}},"canonical_sha256":"26e7bdc4830515fd12a9ccf81a88b0304845d02a7ee8022d7163fbd4f8dbd609","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26e7bdc4830515fd12a9ccf81a88b0304845d02a7ee8022d7163fbd4f8dbd609","first_computed_at":"2026-05-17T23:38:13.006948Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:13.006948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u7E0Ynleg5WCOorRf+OVtExejtEqvST/Q+IRlKCL7t+Ru3aj9mn15qdVAl80zfURZ5r4e645ahwLEMHQQfk/AQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:13.007578Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.14058","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8172326c0d39ee0871ad207c94b39b1b97246ddf8f6dd40fef3452c1a247b2a","sha256:e2a260c128369a5e7f927d6a68fab19f1e1c1e7a43c6e055f6f12feec82ad6b9"],"state_sha256":"b3ae79ddd217402e9b350883cc48b10ff86b2f4c2e3395791e3e65ea8908b946"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FagAjDK9DHZplAMaegBeWIaM4j9AG499iriInVPyykppkd94l5oUDdRcCLB3zbQSV1ZKci+kt0p0G+3AzdbpCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:23:21.550402Z","bundle_sha256":"f6a8b1caba221972f48924bb01b20c65eb42477523cb6fdacdedabe37d3e5099"}}