{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KJDRCWTRHYDFH6Y6X67JCM2MFN","short_pith_number":"pith:KJDRCWTR","canonical_record":{"source":{"id":"2508.13073","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-08-18T16:45:48Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5c704c940d76581b6834b4f713d011330cc8435255f2c993a4f040337734f580","abstract_canon_sha256":"ca67b0f9cf1a480f3dad4c5e03c723c6e779cd4fad89a3bf2e5d3abbaf71aebb"},"schema_version":"1.0"},"canonical_sha256":"5247115a713e0653fb1ebfbe91334c2b53750093a87c76fe467a5744a7e3bb46","source":{"kind":"arxiv","id":"2508.13073","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.13073","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"2508.13073v2","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13073","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"KJDRCWTRHYDF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"KJDRCWTRHYDFH6Y6","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"KJDRCWTR","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KJDRCWTRHYDFH6Y6X67JCM2MFN","target":"record","payload":{"canonical_record":{"source":{"id":"2508.13073","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-08-18T16:45:48Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5c704c940d76581b6834b4f713d011330cc8435255f2c993a4f040337734f580","abstract_canon_sha256":"ca67b0f9cf1a480f3dad4c5e03c723c6e779cd4fad89a3bf2e5d3abbaf71aebb"},"schema_version":"1.0"},"canonical_sha256":"5247115a713e0653fb1ebfbe91334c2b53750093a87c76fe467a5744a7e3bb46","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:13.174286Z","signature_b64":"MbMpCJdZoU4gDn6AjPyHrB5P+vagvM5UA0STWTM6vQpIsiLIZkMxIRPYLVu5uCOamVF9Y/Tplqdinav5cilYAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5247115a713e0653fb1ebfbe91334c2b53750093a87c76fe467a5744a7e3bb46","last_reissued_at":"2026-05-17T23:38:13.173723Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:13.173723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.13073","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":"2026-05-17T23:38:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t7DB7b+KEVwf7VX2r3WL9eyWX1tyAG72BH3OQLT0GdFKtsuRODHY+8nHg6D9sfAcpe4zKI0mXNTa54bOSqujDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T20:37:50.401927Z"},"content_sha256":"95b1e646cbdc05213ed45a8ce839871cc9814b4fe2e19fd5f5c945be57fc465c","schema_version":"1.0","event_id":"sha256:95b1e646cbdc05213ed45a8ce839871cc9814b4fe2e19fd5f5c945be57fc465c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KJDRCWTRHYDFH6Y6X67JCM2MFN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Large VLM-based VLA models for robotic manipulation can be systematically classified into monolithic and hierarchical architectures.","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Lingsen Zhang, Liqiang Nie, Ran Chen, Renshan Zhang, Rui Shao, Wei Li, Zhiyang Liu","submitted_at":"2025-08-18T16:45:48Z","abstract_excerpt":"Robotic manipulation, a key frontier in robotics and embodied AI, requires precise motor control and multimodal understanding, yet traditional rule-based methods fail to scale or generalize in unstructured, novel environments. In recent years, Vision-Language-Action (VLA) models, built upon Large Vision-Language Models (VLMs) pretrained on vast image-text datasets, have emerged as a transformative paradigm. This survey provides the first systematic, taxonomy-oriented review of large VLM-based VLA models for robotic manipulation. We begin by clearly defining large VLM-based VLA models and delin"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"This survey provides the first systematic, taxonomy-oriented review of large VLM-based VLA models for robotic manipulation, resolving inconsistencies in existing taxonomies and filling a critical gap.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the proposed split into monolithic (single/dual-system) and hierarchical models, along with the listed integration domains, comprehensively captures the field without significant omissions or overlaps that would undermine the taxonomy's utility.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"This survey organizes large VLM-based VLA models for robotic manipulation into monolithic and hierarchical paradigms, reviews their integrations and datasets, and outlines future directions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Large VLM-based VLA models for robotic manipulation can be systematically classified into monolithic and hierarchical architectures.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"fc66631ce0b964cbb57721970264499a773be95e5a38efcc2c61773771a66a60"},"source":{"id":"2508.13073","kind":"arxiv","version":2},"verdict":{"id":"3fa5fe66-7bb3-4295-9706-b07fc0eb4a08","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T20:24:02.001566Z","strongest_claim":"This survey provides the first systematic, taxonomy-oriented review of large VLM-based VLA models for robotic manipulation, resolving inconsistencies in existing taxonomies and filling a critical gap.","one_line_summary":"This survey organizes large VLM-based VLA models for robotic manipulation into monolithic and hierarchical paradigms, reviews their integrations and datasets, and outlines future directions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the proposed split into monolithic (single/dual-system) and hierarchical models, along with the listed integration domains, comprehensively captures the field without significant omissions or overlaps that would undermine the taxonomy's utility.","pith_extraction_headline":"Large VLM-based VLA models for robotic manipulation can be systematically classified into monolithic and hierarchical architectures."},"references":{"count":243,"sample":[{"doi":"","year":2024,"title":"//arxiv.org/abs/2402.02385","work_id":"6ae9f09f-8664-4f8e-835f-07d5a9665e6c","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"A Survey on Vision-Language-Action Models for Embodied AI","work_id":"9492fb3d-d667-4892-81bb-b2878f12ff0c","ref_index":2,"cited_arxiv_id":"2405.14093","is_internal_anchor":true},{"doi":"","year":2025,"title":"Metaurban: a simulation platform for embodied ai in urban spaces,","work_id":"c19134ea-10c9-4a07-bc0f-46756c4e9aa0","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Generative artificial intelligence in robotic manipulation: A survey","work_id":"a71401c0-7d08-4253-9d71-0cb28f5db313","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Aligning cyber space with physical world: A comprehensive survey on embodied AI","work_id":"6546762e-7a35-47a7-8489-4ef27dc923a6","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":243,"snapshot_sha256":"9893ec419f70645d4cfbbb3b72b29a947bfb5ff2e6af35b6a3d1bffb4c0947ca","internal_anchors":28},"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":"3fa5fe66-7bb3-4295-9706-b07fc0eb4a08"},"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":"sjM5oDqe8mSuPhQ2vFB1x8/UTueHFjCx4mn+DPcVJRUERstxjXrx+scJselb4DveAnlTz3/FWkM8j1xxVMIKBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T20:37:50.402930Z"},"content_sha256":"d79b03e09fc347e279117f146faae770af26e98084c45a0ee3a06198a3316a5d","schema_version":"1.0","event_id":"sha256:d79b03e09fc347e279117f146faae770af26e98084c45a0ee3a06198a3316a5d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KJDRCWTRHYDFH6Y6X67JCM2MFN/bundle.json","state_url":"https://pith.science/pith/KJDRCWTRHYDFH6Y6X67JCM2MFN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KJDRCWTRHYDFH6Y6X67JCM2MFN/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":"2026-05-18T20:37:50Z","links":{"resolver":"https://pith.science/pith/KJDRCWTRHYDFH6Y6X67JCM2MFN","bundle":"https://pith.science/pith/KJDRCWTRHYDFH6Y6X67JCM2MFN/bundle.json","state":"https://pith.science/pith/KJDRCWTRHYDFH6Y6X67JCM2MFN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KJDRCWTRHYDFH6Y6X67JCM2MFN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KJDRCWTRHYDFH6Y6X67JCM2MFN","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":"ca67b0f9cf1a480f3dad4c5e03c723c6e779cd4fad89a3bf2e5d3abbaf71aebb","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-08-18T16:45:48Z","title_canon_sha256":"5c704c940d76581b6834b4f713d011330cc8435255f2c993a4f040337734f580"},"schema_version":"1.0","source":{"id":"2508.13073","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.13073","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"2508.13073v2","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13073","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"KJDRCWTRHYDF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"KJDRCWTRHYDFH6Y6","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"KJDRCWTR","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:d79b03e09fc347e279117f146faae770af26e98084c45a0ee3a06198a3316a5d","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":"This survey provides the first systematic, taxonomy-oriented review of large VLM-based VLA models for robotic manipulation, resolving inconsistencies in existing taxonomies and filling a critical gap."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the proposed split into monolithic (single/dual-system) and hierarchical models, along with the listed integration domains, comprehensively captures the field without significant omissions or overlaps that would undermine the taxonomy's utility."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"This survey organizes large VLM-based VLA models for robotic manipulation into monolithic and hierarchical paradigms, reviews their integrations and datasets, and outlines future directions."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Large VLM-based VLA models for robotic manipulation can be systematically classified into monolithic and hierarchical architectures."}],"snapshot_sha256":"fc66631ce0b964cbb57721970264499a773be95e5a38efcc2c61773771a66a60"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Robotic manipulation, a key frontier in robotics and embodied AI, requires precise motor control and multimodal understanding, yet traditional rule-based methods fail to scale or generalize in unstructured, novel environments. In recent years, Vision-Language-Action (VLA) models, built upon Large Vision-Language Models (VLMs) pretrained on vast image-text datasets, have emerged as a transformative paradigm. This survey provides the first systematic, taxonomy-oriented review of large VLM-based VLA models for robotic manipulation. We begin by clearly defining large VLM-based VLA models and delin","authors_text":"Lingsen Zhang, Liqiang Nie, Ran Chen, Renshan Zhang, Rui Shao, Wei Li, Zhiyang Liu","cross_cats":["cs.CV"],"headline":"Large VLM-based VLA models for robotic manipulation can be systematically classified into monolithic and hierarchical architectures.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-08-18T16:45:48Z","title":"Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey"},"references":{"count":243,"internal_anchors":28,"resolved_work":243,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"//arxiv.org/abs/2402.02385","work_id":"6ae9f09f-8664-4f8e-835f-07d5a9665e6c","year":2024},{"cited_arxiv_id":"2405.14093","doi":"","is_internal_anchor":true,"ref_index":2,"title":"A Survey on Vision-Language-Action Models for Embodied AI","work_id":"9492fb3d-d667-4892-81bb-b2878f12ff0c","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Metaurban: a simulation platform for embodied ai in urban spaces,","work_id":"c19134ea-10c9-4a07-bc0f-46756c4e9aa0","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Generative artificial intelligence in robotic manipulation: A survey","work_id":"a71401c0-7d08-4253-9d71-0cb28f5db313","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Aligning cyber space with physical world: A comprehensive survey on embodied AI","work_id":"6546762e-7a35-47a7-8489-4ef27dc923a6","year":2024}],"snapshot_sha256":"9893ec419f70645d4cfbbb3b72b29a947bfb5ff2e6af35b6a3d1bffb4c0947ca"},"source":{"id":"2508.13073","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-17T20:24:02.001566Z","id":"3fa5fe66-7bb3-4295-9706-b07fc0eb4a08","model_set":{"reader":"grok-4.3"},"one_line_summary":"This survey organizes large VLM-based VLA models for robotic manipulation into monolithic and hierarchical paradigms, reviews their integrations and datasets, and outlines future directions.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Large VLM-based VLA models for robotic manipulation can be systematically classified into monolithic and hierarchical architectures.","strongest_claim":"This survey provides the first systematic, taxonomy-oriented review of large VLM-based VLA models for robotic manipulation, resolving inconsistencies in existing taxonomies and filling a critical gap.","weakest_assumption":"That the proposed split into monolithic (single/dual-system) and hierarchical models, along with the listed integration domains, comprehensively captures the field without significant omissions or overlaps that would undermine the taxonomy's utility."}},"verdict_id":"3fa5fe66-7bb3-4295-9706-b07fc0eb4a08"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:95b1e646cbdc05213ed45a8ce839871cc9814b4fe2e19fd5f5c945be57fc465c","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":"ca67b0f9cf1a480f3dad4c5e03c723c6e779cd4fad89a3bf2e5d3abbaf71aebb","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-08-18T16:45:48Z","title_canon_sha256":"5c704c940d76581b6834b4f713d011330cc8435255f2c993a4f040337734f580"},"schema_version":"1.0","source":{"id":"2508.13073","kind":"arxiv","version":2}},"canonical_sha256":"5247115a713e0653fb1ebfbe91334c2b53750093a87c76fe467a5744a7e3bb46","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5247115a713e0653fb1ebfbe91334c2b53750093a87c76fe467a5744a7e3bb46","first_computed_at":"2026-05-17T23:38:13.173723Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:13.173723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MbMpCJdZoU4gDn6AjPyHrB5P+vagvM5UA0STWTM6vQpIsiLIZkMxIRPYLVu5uCOamVF9Y/Tplqdinav5cilYAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:13.174286Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.13073","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95b1e646cbdc05213ed45a8ce839871cc9814b4fe2e19fd5f5c945be57fc465c","sha256:d79b03e09fc347e279117f146faae770af26e98084c45a0ee3a06198a3316a5d"],"state_sha256":"2d3993a9b1491b484b5f1277e9c99adbad94420da43edb0c6c89937ca8fb5e7f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"csPhDDFRnViLaMagQTthMu2g58pEcKmYT8oDQhdPIRBfG5QYyMGhxt0Kc/daCHt4Qx2sXGM+W8EpGcjxSFoeDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-18T20:37:50.405842Z","bundle_sha256":"54e4208492d6bf6f35f5edc6e769333c21e1d636934f9ff1924161f1488c5282"}}