{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QCMC7KQCKF7EQYKKI7LZJ73Z5X","short_pith_number":"pith:QCMC7KQC","schema_version":"1.0","canonical_sha256":"80982faa02517e48614a47d794ff79edfc41b428837f971e46dd23d3cb3282ac","source":{"kind":"arxiv","id":"2505.15517","version":2},"attestation_state":"computed","paper":{"title":"Robo2VLM: Visual Question Answering from Large-Scale In-the-Wild Robot Manipulation Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.RO","authors_text":"Kaiyuan Chen, Ken Goldberg, Pannag R Sanketi, Shuangyu Xie, Zehan Ma","submitted_at":"2025-05-21T13:42:52Z","abstract_excerpt":"Vision-Language Models (VLMs) acquire real-world knowledge and general reasoning ability through Internet-scale image-text corpora. They can augment robotic systems with scene understanding and task planning, and assist visuomotor policies that are trained on robot trajectory data. We explore the reverse paradigm - using rich, real, multi-modal robot trajectory data to enhance and evaluate VLMs. In this paper, we present Robo2VLM, a Visual Question Answering (VQA) dataset generation framework for VLMs. Given a human tele-operated robot trajectory, Robo2VLM derives ground-truth from non-visual "},"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":"2505.15517","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-21T13:42:52Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"743c6efb68b68e9d189ddac0b96d62b5b1639e1d6e52b96aa59f8a577333adbc","abstract_canon_sha256":"fb4b61bbbbe9a9523a2944ff1fd0f1fbeae73d83517e5016965262fce0e8428c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:20.504137Z","signature_b64":"HhgfGu9Uz2t5FWlvCHo9AZ7vugMN5MifhlJ4BfnF1AZUyvJ92USxHtn8jPZlIEPxM12JM70WXfuVsh93j6fwDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80982faa02517e48614a47d794ff79edfc41b428837f971e46dd23d3cb3282ac","last_reissued_at":"2026-07-05T11:24:20.503592Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:20.503592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robo2VLM: Visual Question Answering from Large-Scale In-the-Wild Robot Manipulation Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.RO","authors_text":"Kaiyuan Chen, Ken Goldberg, Pannag R Sanketi, Shuangyu Xie, Zehan Ma","submitted_at":"2025-05-21T13:42:52Z","abstract_excerpt":"Vision-Language Models (VLMs) acquire real-world knowledge and general reasoning ability through Internet-scale image-text corpora. They can augment robotic systems with scene understanding and task planning, and assist visuomotor policies that are trained on robot trajectory data. We explore the reverse paradigm - using rich, real, multi-modal robot trajectory data to enhance and evaluate VLMs. In this paper, we present Robo2VLM, a Visual Question Answering (VQA) dataset generation framework for VLMs. Given a human tele-operated robot trajectory, Robo2VLM derives ground-truth from non-visual "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15517","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/2505.15517/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":"2505.15517","created_at":"2026-07-05T11:24:20.503656+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.15517v2","created_at":"2026-07-05T11:24:20.503656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15517","created_at":"2026-07-05T11:24:20.503656+00:00"},{"alias_kind":"pith_short_12","alias_value":"QCMC7KQCKF7E","created_at":"2026-07-05T11:24:20.503656+00:00"},{"alias_kind":"pith_short_16","alias_value":"QCMC7KQCKF7EQYKK","created_at":"2026-07-05T11:24:20.503656+00:00"},{"alias_kind":"pith_short_8","alias_value":"QCMC7KQC","created_at":"2026-07-05T11:24:20.503656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23881","citing_title":"Ground Then Rank: Revisiting Knowledge-Based VQA with Training-Free Entity Identification","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20905","citing_title":"Vesta: A Generalist Embodied Reasoning Model","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13040","citing_title":"RoboProcessBench: Benchmarking Process-Aware Understanding in Vision-Language Robotic Manipulation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08520","citing_title":"Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30877","citing_title":"Wall-OSS-0.5 Technical Report","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25802","citing_title":"Rethinking VLM Representation for VLA Initialization","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25813","citing_title":"Extending Embodied Question Answering from Perception to Decision","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28548","citing_title":"GEM: Generative Supervision Helps Embodied Intelligence","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19328","citing_title":"RoboJailBench: Benchmarking Adversarial Attacks and Defenses in Embodied Robotic Agents","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13119","citing_title":"Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20012","citing_title":"EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QCMC7KQCKF7EQYKKI7LZJ73Z5X","json":"https://pith.science/pith/QCMC7KQCKF7EQYKKI7LZJ73Z5X.json","graph_json":"https://pith.science/api/pith-number/QCMC7KQCKF7EQYKKI7LZJ73Z5X/graph.json","events_json":"https://pith.science/api/pith-number/QCMC7KQCKF7EQYKKI7LZJ73Z5X/events.json","paper":"https://pith.science/paper/QCMC7KQC"},"agent_actions":{"view_html":"https://pith.science/pith/QCMC7KQCKF7EQYKKI7LZJ73Z5X","download_json":"https://pith.science/pith/QCMC7KQCKF7EQYKKI7LZJ73Z5X.json","view_paper":"https://pith.science/paper/QCMC7KQC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.15517&json=true","fetch_graph":"https://pith.science/api/pith-number/QCMC7KQCKF7EQYKKI7LZJ73Z5X/graph.json","fetch_events":"https://pith.science/api/pith-number/QCMC7KQCKF7EQYKKI7LZJ73Z5X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QCMC7KQCKF7EQYKKI7LZJ73Z5X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QCMC7KQCKF7EQYKKI7LZJ73Z5X/action/storage_attestation","attest_author":"https://pith.science/pith/QCMC7KQCKF7EQYKKI7LZJ73Z5X/action/author_attestation","sign_citation":"https://pith.science/pith/QCMC7KQCKF7EQYKKI7LZJ73Z5X/action/citation_signature","submit_replication":"https://pith.science/pith/QCMC7KQCKF7EQYKKI7LZJ73Z5X/action/replication_record"}},"created_at":"2026-07-05T11:24:20.503656+00:00","updated_at":"2026-07-05T11:24:20.503656+00:00"}