{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:766G5U5HJYKBP64P565OWGTWJZ","short_pith_number":"pith:766G5U5H","schema_version":"1.0","canonical_sha256":"ffbc6ed3a74e1417fb8fefbaeb1a764e4ec9f8be3fb1f8e36c478a17457f0f01","source":{"kind":"arxiv","id":"2510.01711","version":3},"attestation_state":"computed","paper":{"title":"Contrastive Representation Regularization for Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Changyeon Kim, Dongyoung Kim, Jimin Lee, Jinwoo Shin, Kyungmin Lee, Myungkyu Koo, Taeyoung Kim, Younggyo Seo","submitted_at":"2025-10-02T06:41:22Z","abstract_excerpt":"Vision-Language-Action (VLA) models have shown strong capabilities in robot manipulation by leveraging rich representations from pre-trained Vision-Language Models (VLMs). However, their representations arguably remain suboptimal, lacking sensitivity to robotic signals such as control actions and proprioceptive information. To address the issue, we introduce Robot State-aware Contrastive Loss (RS-CL), a simple and effective representation regularization for VLA models, designed to bridge the gap between VLM representations and robotic signals. In particular, RS-CL aligns the representations mo"},"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":"2510.01711","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-10-02T06:41:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1fc800e2eee78737a154f24769e1a7f2272bbe481a5adf1cf76dc4f87d9b38ff","abstract_canon_sha256":"167dbb3cc40272613197a37a79325faf17fa69accc1126c5e2e82b6b3a9a5b7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:04:56.240230Z","signature_b64":"sDYCb6t4NjIAeSOiFpqB1tcM97vW1go/QU5ndlMrTKZyVixw5xX9374v5Cvse43BmjV4TQgeBM0xbIX2v02TCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffbc6ed3a74e1417fb8fefbaeb1a764e4ec9f8be3fb1f8e36c478a17457f0f01","last_reissued_at":"2026-05-29T01:04:56.239737Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:04:56.239737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Representation Regularization for Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Changyeon Kim, Dongyoung Kim, Jimin Lee, Jinwoo Shin, Kyungmin Lee, Myungkyu Koo, Taeyoung Kim, Younggyo Seo","submitted_at":"2025-10-02T06:41:22Z","abstract_excerpt":"Vision-Language-Action (VLA) models have shown strong capabilities in robot manipulation by leveraging rich representations from pre-trained Vision-Language Models (VLMs). However, their representations arguably remain suboptimal, lacking sensitivity to robotic signals such as control actions and proprioceptive information. To address the issue, we introduce Robot State-aware Contrastive Loss (RS-CL), a simple and effective representation regularization for VLA models, designed to bridge the gap between VLM representations and robotic signals. In particular, RS-CL aligns the representations mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.01711","kind":"arxiv","version":3},"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/2510.01711/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":"2510.01711","created_at":"2026-05-29T01:04:56.239798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.01711v3","created_at":"2026-05-29T01:04:56.239798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.01711","created_at":"2026-05-29T01:04:56.239798+00:00"},{"alias_kind":"pith_short_12","alias_value":"766G5U5HJYKB","created_at":"2026-05-29T01:04:56.239798+00:00"},{"alias_kind":"pith_short_16","alias_value":"766G5U5HJYKBP64P","created_at":"2026-05-29T01:04:56.239798+00:00"},{"alias_kind":"pith_short_8","alias_value":"766G5U5H","created_at":"2026-05-29T01:04:56.239798+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/766G5U5HJYKBP64P565OWGTWJZ","json":"https://pith.science/pith/766G5U5HJYKBP64P565OWGTWJZ.json","graph_json":"https://pith.science/api/pith-number/766G5U5HJYKBP64P565OWGTWJZ/graph.json","events_json":"https://pith.science/api/pith-number/766G5U5HJYKBP64P565OWGTWJZ/events.json","paper":"https://pith.science/paper/766G5U5H"},"agent_actions":{"view_html":"https://pith.science/pith/766G5U5HJYKBP64P565OWGTWJZ","download_json":"https://pith.science/pith/766G5U5HJYKBP64P565OWGTWJZ.json","view_paper":"https://pith.science/paper/766G5U5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.01711&json=true","fetch_graph":"https://pith.science/api/pith-number/766G5U5HJYKBP64P565OWGTWJZ/graph.json","fetch_events":"https://pith.science/api/pith-number/766G5U5HJYKBP64P565OWGTWJZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/766G5U5HJYKBP64P565OWGTWJZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/766G5U5HJYKBP64P565OWGTWJZ/action/storage_attestation","attest_author":"https://pith.science/pith/766G5U5HJYKBP64P565OWGTWJZ/action/author_attestation","sign_citation":"https://pith.science/pith/766G5U5HJYKBP64P565OWGTWJZ/action/citation_signature","submit_replication":"https://pith.science/pith/766G5U5HJYKBP64P565OWGTWJZ/action/replication_record"}},"created_at":"2026-05-29T01:04:56.239798+00:00","updated_at":"2026-05-29T01:04:56.239798+00:00"}