{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4QLZCZFJDGEUGHHFNBK4VLUKJW","short_pith_number":"pith:4QLZCZFJ","schema_version":"1.0","canonical_sha256":"e4179164a91989431ce56855caae8a4d8d488edbd8521d250bf18a2343301179","source":{"kind":"arxiv","id":"2502.16707","version":1},"attestation_state":"computed","paper":{"title":"Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jiaming Han, Jianlan Luo, Sergey Levine, Xiangyu Yue, Yunhai Feng, Zhuoran Yang","submitted_at":"2025-02-23T20:42:15Z","abstract_excerpt":"Solving complex long-horizon robotic manipulation problems requires sophisticated high-level planning capabilities, the ability to reason about the physical world, and reactively choose appropriate motor skills. Vision-language models (VLMs) pretrained on Internet data could in principle offer a framework for tackling such problems. However, in their current form, VLMs lack both the nuanced understanding of intricate physics required for robotic manipulation and the ability to reason over long horizons to address error compounding issues. In this paper, we introduce a novel test-time computati"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.16707","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-02-23T20:42:15Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"640f3dffbec8ebfd93fbaef095f8a79b102ec4cee5bb298b071c8ad84077e831","abstract_canon_sha256":"06dade9471122364adcc6c92b8170ac43d7c9e3b01e7c6ce6bc5d3f9f31ef942"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:58.037761Z","signature_b64":"kMbLQ4CnwikUzKKnCr7O2940QD5fVYiBkXc+4GMqt/70yJu/9Myze2MNfkXDgZ/VvC8MqESJgMykyBUhHyK5Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4179164a91989431ce56855caae8a4d8d488edbd8521d250bf18a2343301179","last_reissued_at":"2026-07-05T10:18:58.037262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:58.037262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jiaming Han, Jianlan Luo, Sergey Levine, Xiangyu Yue, Yunhai Feng, Zhuoran Yang","submitted_at":"2025-02-23T20:42:15Z","abstract_excerpt":"Solving complex long-horizon robotic manipulation problems requires sophisticated high-level planning capabilities, the ability to reason about the physical world, and reactively choose appropriate motor skills. Vision-language models (VLMs) pretrained on Internet data could in principle offer a framework for tackling such problems. However, in their current form, VLMs lack both the nuanced understanding of intricate physics required for robotic manipulation and the ability to reason over long horizons to address error compounding issues. In this paper, we introduce a novel test-time computati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16707","kind":"arxiv","version":1},"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/2502.16707/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.16707","created_at":"2026-07-05T10:18:58.037323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.16707v1","created_at":"2026-07-05T10:18:58.037323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16707","created_at":"2026-07-05T10:18:58.037323+00:00"},{"alias_kind":"pith_short_12","alias_value":"4QLZCZFJDGEU","created_at":"2026-07-05T10:18:58.037323+00:00"},{"alias_kind":"pith_short_16","alias_value":"4QLZCZFJDGEUGHHF","created_at":"2026-07-05T10:18:58.037323+00:00"},{"alias_kind":"pith_short_8","alias_value":"4QLZCZFJ","created_at":"2026-07-05T10:18:58.037323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08024","citing_title":"APIVOT: Adaptive Planning with Interleaved Vision-Language Thoughts","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27146","citing_title":"PhysReflect-VLA: Physical Feasibility and Self-Reflective Regulation for Reliable Vision-Language-Action Policies","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07723","citing_title":"VoLo: A Physical Orchestrator for Open-Vocabulary Long-Horizon Manipulation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21723","citing_title":"VLBiMan: Vision-Language Anchored One-Shot Demonstration Enables Generalizable Bimanual Robotic Manipulation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2511.14148","citing_title":"AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2507.01925","citing_title":"A Survey on Vision-Language-Action Models: An Action Tokenization Perspective","ref_index":152,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20323","citing_title":"PhysMem: Scaling Test-Time Memory for Embodied Physical Reasoning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12167","citing_title":"From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03909","citing_title":"Task-Aware Scanning Parameter Configuration for Robotic Inspection Using Vision Language Embeddings and Hyperdimensional Computing","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21138","citing_title":"Navigating the Clutter: Waypoint-Based Bi-Level Planning for Multi-Robot Systems","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16886","citing_title":"Chain Of Interaction Benchmark (COIN): When Reasoning meets Embodied Interaction","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4QLZCZFJDGEUGHHFNBK4VLUKJW","json":"https://pith.science/pith/4QLZCZFJDGEUGHHFNBK4VLUKJW.json","graph_json":"https://pith.science/api/pith-number/4QLZCZFJDGEUGHHFNBK4VLUKJW/graph.json","events_json":"https://pith.science/api/pith-number/4QLZCZFJDGEUGHHFNBK4VLUKJW/events.json","paper":"https://pith.science/paper/4QLZCZFJ"},"agent_actions":{"view_html":"https://pith.science/pith/4QLZCZFJDGEUGHHFNBK4VLUKJW","download_json":"https://pith.science/pith/4QLZCZFJDGEUGHHFNBK4VLUKJW.json","view_paper":"https://pith.science/paper/4QLZCZFJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.16707&json=true","fetch_graph":"https://pith.science/api/pith-number/4QLZCZFJDGEUGHHFNBK4VLUKJW/graph.json","fetch_events":"https://pith.science/api/pith-number/4QLZCZFJDGEUGHHFNBK4VLUKJW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4QLZCZFJDGEUGHHFNBK4VLUKJW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4QLZCZFJDGEUGHHFNBK4VLUKJW/action/storage_attestation","attest_author":"https://pith.science/pith/4QLZCZFJDGEUGHHFNBK4VLUKJW/action/author_attestation","sign_citation":"https://pith.science/pith/4QLZCZFJDGEUGHHFNBK4VLUKJW/action/citation_signature","submit_replication":"https://pith.science/pith/4QLZCZFJDGEUGHHFNBK4VLUKJW/action/replication_record"}},"created_at":"2026-07-05T10:18:58.037323+00:00","updated_at":"2026-07-05T10:18:58.037323+00:00"}