{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FEAOCOWRECFLUVR7VM2XC54PJ4","short_pith_number":"pith:FEAOCOWR","schema_version":"1.0","canonical_sha256":"2900e13ad1208aba563fab3571778f4f29ec409d32930ed38ee05895153f7597","source":{"kind":"arxiv","id":"2505.09577","version":1},"attestation_state":"computed","paper":{"title":"VTLA: Vision-Tactile-Language-Action Model with Preference Learning for Insertion Manipulation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chaofan Zhang, Peng Hao, Shaowei Cui, Shuo Wang, Xiaoge Cao, Xiaoshuai Hao","submitted_at":"2025-05-14T17:29:35Z","abstract_excerpt":"While vision-language models have advanced significantly, their application in language-conditioned robotic manipulation is still underexplored, especially for contact-rich tasks that extend beyond visually dominant pick-and-place scenarios. To bridge this gap, we introduce Vision-Tactile-Language-Action model, a novel framework that enables robust policy generation in contact-intensive scenarios by effectively integrating visual and tactile inputs through cross-modal language grounding. A low-cost, multi-modal dataset has been constructed in a simulation environment, containing vision-tactile"},"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":"2505.09577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-14T17:29:35Z","cross_cats_sorted":[],"title_canon_sha256":"4c82b137251e5e6ef7b706f89d86c5086eb8adaf68aef3cd23e986ef7437e2de","abstract_canon_sha256":"0ba518deef6f094e18ac2c62c4ca9bc6cec1dc6abe495fd66d6cd4602192a55b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:10.772628Z","signature_b64":"qYUTeE5nLpBjcS8eMSIK1Hl14Z/sl3rqdqRRAjG8Uw2MjAc6BigL0aAP798CEquaz++ykKzIeQv5Q9jZDQKBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2900e13ad1208aba563fab3571778f4f29ec409d32930ed38ee05895153f7597","last_reissued_at":"2026-07-05T11:03:10.772091Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:10.772091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VTLA: Vision-Tactile-Language-Action Model with Preference Learning for Insertion Manipulation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chaofan Zhang, Peng Hao, Shaowei Cui, Shuo Wang, Xiaoge Cao, Xiaoshuai Hao","submitted_at":"2025-05-14T17:29:35Z","abstract_excerpt":"While vision-language models have advanced significantly, their application in language-conditioned robotic manipulation is still underexplored, especially for contact-rich tasks that extend beyond visually dominant pick-and-place scenarios. To bridge this gap, we introduce Vision-Tactile-Language-Action model, a novel framework that enables robust policy generation in contact-intensive scenarios by effectively integrating visual and tactile inputs through cross-modal language grounding. A low-cost, multi-modal dataset has been constructed in a simulation environment, containing vision-tactile"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09577","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/2505.09577/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":"2505.09577","created_at":"2026-07-05T11:03:10.772157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.09577v1","created_at":"2026-07-05T11:03:10.772157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09577","created_at":"2026-07-05T11:03:10.772157+00:00"},{"alias_kind":"pith_short_12","alias_value":"FEAOCOWRECFL","created_at":"2026-07-05T11:03:10.772157+00:00"},{"alias_kind":"pith_short_16","alias_value":"FEAOCOWRECFLUVR7","created_at":"2026-07-05T11:03:10.772157+00:00"},{"alias_kind":"pith_short_8","alias_value":"FEAOCOWR","created_at":"2026-07-05T11:03:10.772157+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17055","citing_title":"T-Rex: Tactile-Reactive Dexterous Manipulation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02503","citing_title":"VT-WAM: Visual-Tactile World Action Model for Contact-Rich Manipulation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09777","citing_title":"AetheRock: An Arm-Worn Robot Teaching System for Force-Guided Vision-Tactile Learning","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09337","citing_title":"TORL-VLA: Tactile Guided Online Reinforcement Learning for Contact-Rich Manipulation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08737","citing_title":"Dream-Tac: A Unified Tactile World Action Model for Contact-Rich Robot Manipulation","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06281","citing_title":"Multi-Resolution Tactile Imitation Learning for Contact-Rich Robotic Manipulation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01241","citing_title":"OneVLA: A Unified Framework for Embodied Tasks","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31451","citing_title":"UniTac: A Unified Multimodal Model for Cross-Sensor Tactile Understanding and Generation","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29941","citing_title":"Seeing Touch from Motion: A Unified Modality-Aware Visuo-Tactile Policy with Tactile Motion Correlation","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29089","citing_title":"TAP-VLA: Tactile Annotation Prompting for Vision Language Action Models","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2502.13451","citing_title":"MapNav: A Novel Memory Representation via Annotated Semantic Maps for Vision-and-Language Navigation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22812","citing_title":"GesVLA: Gesture-Aware Vision-Language-Action Model Embedded Representations","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07308","citing_title":"AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Models","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17336","citing_title":"Tactile-based Multimodal Fusion in Embodied Intelligence: A Survey of Vision, Language, and Contact-Driven Paradigms","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20082","citing_title":"VL-DPO: Vision-Language-Guided Finetuning for Preference-Aligned Autonomous Driving","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2508.13073","citing_title":"Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2601.20239","citing_title":"TouchGuide: Inference-Time Steering of Visuomotor Policies via Touch Guidance","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2603.04038","citing_title":"Force-Aware Residual DAgger via Trajectory Editing for Precision Insertion with Impedance Control","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2603.25044","citing_title":"ThermoAct:Thermal-Aware Vision-Language-Action Models for Robotic Perception and Decision-Making","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03269","citing_title":"RLDX-1 Technical Report","ref_index":118,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23272","citing_title":"Modular Sensory Stream for Integrating Physical Feedback in Vision-Language-Action Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13015","citing_title":"Learning Versatile Humanoid Manipulation with Touch Dreaming","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07308","citing_title":"AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Models","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03269","citing_title":"RLDX-1 Technical Report","ref_index":118,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FEAOCOWRECFLUVR7VM2XC54PJ4","json":"https://pith.science/pith/FEAOCOWRECFLUVR7VM2XC54PJ4.json","graph_json":"https://pith.science/api/pith-number/FEAOCOWRECFLUVR7VM2XC54PJ4/graph.json","events_json":"https://pith.science/api/pith-number/FEAOCOWRECFLUVR7VM2XC54PJ4/events.json","paper":"https://pith.science/paper/FEAOCOWR"},"agent_actions":{"view_html":"https://pith.science/pith/FEAOCOWRECFLUVR7VM2XC54PJ4","download_json":"https://pith.science/pith/FEAOCOWRECFLUVR7VM2XC54PJ4.json","view_paper":"https://pith.science/paper/FEAOCOWR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.09577&json=true","fetch_graph":"https://pith.science/api/pith-number/FEAOCOWRECFLUVR7VM2XC54PJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/FEAOCOWRECFLUVR7VM2XC54PJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FEAOCOWRECFLUVR7VM2XC54PJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FEAOCOWRECFLUVR7VM2XC54PJ4/action/storage_attestation","attest_author":"https://pith.science/pith/FEAOCOWRECFLUVR7VM2XC54PJ4/action/author_attestation","sign_citation":"https://pith.science/pith/FEAOCOWRECFLUVR7VM2XC54PJ4/action/citation_signature","submit_replication":"https://pith.science/pith/FEAOCOWRECFLUVR7VM2XC54PJ4/action/replication_record"}},"created_at":"2026-07-05T11:03:10.772157+00:00","updated_at":"2026-07-05T11:03:10.772157+00:00"}