{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:I66ZQJNT2LX4IR5VI6NMCI4UUQ","short_pith_number":"pith:I66ZQJNT","schema_version":"1.0","canonical_sha256":"47bd9825b3d2efc447b5479ac12394a43636e73aedc5ca0a9d866cd3a3185d5d","source":{"kind":"arxiv","id":"2506.13679","version":1},"attestation_state":"computed","paper":{"title":"ROSA: Harnessing Robot States for Vision-Language and Action Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Haoqiang Fan, Haoxuan Liu, Kefan Gu, Tiancai Wang, Xiaoyan Sun, Yucheng Zhao, Yuqing Wen","submitted_at":"2025-06-16T16:34:20Z","abstract_excerpt":"Vision-Language-Action (VLA) models have recently made significant advance in multi-task, end-to-end robotic control, due to the strong generalization capabilities of Vision-Language Models (VLMs). A fundamental challenge in developing such models is effectively aligning the vision-language space with the robotic action space. Existing approaches typically rely on directly fine-tuning VLMs using expert demonstrations. However, this strategy suffers from a spatio-temporal gap, resulting in considerable data inefficiency and heavy reliance on human labor. Spatially, VLMs operate within a high-le"},"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":"2506.13679","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-16T16:34:20Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"84026ffbdcfa40a3bf9a1834ad7848b51122d0b665aed07773462dcbddf9d20f","abstract_canon_sha256":"784ad93b1f6d3bbe5dc0a9146decec370b7c4f83d3f674d8e8dc308679406971"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:24.781766Z","signature_b64":"vZpTF5WO/AGgHguYy4ujmEzWcSB0xTwzdsuEKNxMJemwUc8K8fHFS/vkTVO8vEsqYuiYRVq+5cOoDWK6KWk2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47bd9825b3d2efc447b5479ac12394a43636e73aedc5ca0a9d866cd3a3185d5d","last_reissued_at":"2026-07-05T11:22:24.781216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:24.781216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ROSA: Harnessing Robot States for Vision-Language and Action Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Haoqiang Fan, Haoxuan Liu, Kefan Gu, Tiancai Wang, Xiaoyan Sun, Yucheng Zhao, Yuqing Wen","submitted_at":"2025-06-16T16:34:20Z","abstract_excerpt":"Vision-Language-Action (VLA) models have recently made significant advance in multi-task, end-to-end robotic control, due to the strong generalization capabilities of Vision-Language Models (VLMs). A fundamental challenge in developing such models is effectively aligning the vision-language space with the robotic action space. Existing approaches typically rely on directly fine-tuning VLMs using expert demonstrations. However, this strategy suffers from a spatio-temporal gap, resulting in considerable data inefficiency and heavy reliance on human labor. Spatially, VLMs operate within a high-le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13679","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/2506.13679/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":"2506.13679","created_at":"2026-07-05T11:22:24.781276+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13679v1","created_at":"2026-07-05T11:22:24.781276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13679","created_at":"2026-07-05T11:22:24.781276+00:00"},{"alias_kind":"pith_short_12","alias_value":"I66ZQJNT2LX4","created_at":"2026-07-05T11:22:24.781276+00:00"},{"alias_kind":"pith_short_16","alias_value":"I66ZQJNT2LX4IR5V","created_at":"2026-07-05T11:22:24.781276+00:00"},{"alias_kind":"pith_short_8","alias_value":"I66ZQJNT","created_at":"2026-07-05T11:22:24.781276+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I66ZQJNT2LX4IR5VI6NMCI4UUQ","json":"https://pith.science/pith/I66ZQJNT2LX4IR5VI6NMCI4UUQ.json","graph_json":"https://pith.science/api/pith-number/I66ZQJNT2LX4IR5VI6NMCI4UUQ/graph.json","events_json":"https://pith.science/api/pith-number/I66ZQJNT2LX4IR5VI6NMCI4UUQ/events.json","paper":"https://pith.science/paper/I66ZQJNT"},"agent_actions":{"view_html":"https://pith.science/pith/I66ZQJNT2LX4IR5VI6NMCI4UUQ","download_json":"https://pith.science/pith/I66ZQJNT2LX4IR5VI6NMCI4UUQ.json","view_paper":"https://pith.science/paper/I66ZQJNT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13679&json=true","fetch_graph":"https://pith.science/api/pith-number/I66ZQJNT2LX4IR5VI6NMCI4UUQ/graph.json","fetch_events":"https://pith.science/api/pith-number/I66ZQJNT2LX4IR5VI6NMCI4UUQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I66ZQJNT2LX4IR5VI6NMCI4UUQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I66ZQJNT2LX4IR5VI6NMCI4UUQ/action/storage_attestation","attest_author":"https://pith.science/pith/I66ZQJNT2LX4IR5VI6NMCI4UUQ/action/author_attestation","sign_citation":"https://pith.science/pith/I66ZQJNT2LX4IR5VI6NMCI4UUQ/action/citation_signature","submit_replication":"https://pith.science/pith/I66ZQJNT2LX4IR5VI6NMCI4UUQ/action/replication_record"}},"created_at":"2026-07-05T11:22:24.781276+00:00","updated_at":"2026-07-05T11:22:24.781276+00:00"}