{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QCMC7KQCKF7EQYKKI7LZJ73Z5X","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":"fb4b61bbbbe9a9523a2944ff1fd0f1fbeae73d83517e5016965262fce0e8428c","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-21T13:42:52Z","title_canon_sha256":"743c6efb68b68e9d189ddac0b96d62b5b1639e1d6e52b96aa59f8a577333adbc"},"schema_version":"1.0","source":{"id":"2505.15517","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15517","created_at":"2026-07-05T11:24:20Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15517v2","created_at":"2026-07-05T11:24:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15517","created_at":"2026-07-05T11:24:20Z"},{"alias_kind":"pith_short_12","alias_value":"QCMC7KQCKF7E","created_at":"2026-07-05T11:24:20Z"},{"alias_kind":"pith_short_16","alias_value":"QCMC7KQCKF7EQYKK","created_at":"2026-07-05T11:24:20Z"},{"alias_kind":"pith_short_8","alias_value":"QCMC7KQC","created_at":"2026-07-05T11:24:20Z"}],"graph_snapshots":[{"event_id":"sha256:ebdacc428c7d0acdcf7ef2939b25de30ee9d26be4be455129ff9d50fa7671e91","target":"graph","created_at":"2026-07-05T11:24:20Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.15517/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Kaiyuan Chen, Ken Goldberg, Pannag R Sanketi, Shuangyu Xie, Zehan Ma","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-21T13:42:52Z","title":"Robo2VLM: Visual Question Answering from Large-Scale In-the-Wild Robot Manipulation Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15517","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fc2ef7f5df89a0d3ec0b3b20f8cbd4921bccfee5732372383d5968078f3364df","target":"record","created_at":"2026-07-05T11:24:20Z","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":"fb4b61bbbbe9a9523a2944ff1fd0f1fbeae73d83517e5016965262fce0e8428c","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-21T13:42:52Z","title_canon_sha256":"743c6efb68b68e9d189ddac0b96d62b5b1639e1d6e52b96aa59f8a577333adbc"},"schema_version":"1.0","source":{"id":"2505.15517","kind":"arxiv","version":2}},"canonical_sha256":"80982faa02517e48614a47d794ff79edfc41b428837f971e46dd23d3cb3282ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80982faa02517e48614a47d794ff79edfc41b428837f971e46dd23d3cb3282ac","first_computed_at":"2026-07-05T11:24:20.503592Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:20.503592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HhgfGu9Uz2t5FWlvCHo9AZ7vugMN5MifhlJ4BfnF1AZUyvJ92USxHtn8jPZlIEPxM12JM70WXfuVsh93j6fwDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:20.504137Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.15517","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc2ef7f5df89a0d3ec0b3b20f8cbd4921bccfee5732372383d5968078f3364df","sha256:ebdacc428c7d0acdcf7ef2939b25de30ee9d26be4be455129ff9d50fa7671e91"],"state_sha256":"08daa85200b5026fa7efbe8f658ca81ef35d6fb0c7ffa1cd5bf56c6e979c4c9e"}