{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WY6ZE7WINZMAANT2C7OVVWJEW4","short_pith_number":"pith:WY6ZE7WI","schema_version":"1.0","canonical_sha256":"b63d927ec86e5800367a17dd5ad924b72b2e42dbcac712397d29c58fe01e0600","source":{"kind":"arxiv","id":"2501.04693","version":3},"attestation_state":"computed","paper":{"title":"Beyond Sight: Finetuning Generalist Robot Policies with Heterogeneous Sensors via Language Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Carmelo Sferrazza, Joshua Jones, Kyle Stachowicz, Oier Mees, Pieter Abbeel, Sergey Levine","submitted_at":"2025-01-08T18:57:33Z","abstract_excerpt":"Interacting with the world is a multi-sensory experience: achieving effective general-purpose interaction requires making use of all available modalities -- including vision, touch, and audio -- to fill in gaps from partial observation. For example, when vision is occluded reaching into a bag, a robot should rely on its senses of touch and sound. However, state-of-the-art generalist robot policies are typically trained on large datasets to predict robot actions solely from visual and proprioceptive observations. In this work, we propose FuSe, a novel approach that enables finetuning visuomotor"},"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":"2501.04693","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-01-08T18:57:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c701ecbef816329e0c547fc410fd298420bb828e1888a16252b393c9045b38ae","abstract_canon_sha256":"974459fa5d6157d2bd240536d50fedd6a827e0ea19803ec48f368e5f2986c87a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:01.168094Z","signature_b64":"ynDqpNDVvT/X+WRK9eCF3nIgQ077Z7G47oucDM0Ve7qDafdekQl+P9yUl0w40wm+QtmNJp6A4tpLxcuo2gHQBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b63d927ec86e5800367a17dd5ad924b72b2e42dbcac712397d29c58fe01e0600","last_reissued_at":"2026-07-05T10:01:01.167683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:01.167683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Sight: Finetuning Generalist Robot Policies with Heterogeneous Sensors via Language Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Carmelo Sferrazza, Joshua Jones, Kyle Stachowicz, Oier Mees, Pieter Abbeel, Sergey Levine","submitted_at":"2025-01-08T18:57:33Z","abstract_excerpt":"Interacting with the world is a multi-sensory experience: achieving effective general-purpose interaction requires making use of all available modalities -- including vision, touch, and audio -- to fill in gaps from partial observation. For example, when vision is occluded reaching into a bag, a robot should rely on its senses of touch and sound. However, state-of-the-art generalist robot policies are typically trained on large datasets to predict robot actions solely from visual and proprioceptive observations. In this work, we propose FuSe, a novel approach that enables finetuning visuomotor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04693","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/2501.04693/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":"2501.04693","created_at":"2026-07-05T10:01:01.167738+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.04693v3","created_at":"2026-07-05T10:01:01.167738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04693","created_at":"2026-07-05T10:01:01.167738+00:00"},{"alias_kind":"pith_short_12","alias_value":"WY6ZE7WINZMA","created_at":"2026-07-05T10:01:01.167738+00:00"},{"alias_kind":"pith_short_16","alias_value":"WY6ZE7WINZMAANT2","created_at":"2026-07-05T10:01:01.167738+00:00"},{"alias_kind":"pith_short_8","alias_value":"WY6ZE7WI","created_at":"2026-07-05T10:01:01.167738+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29948","citing_title":"Heterogeneous Tactile Transformer","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28476","citing_title":"FADA: Few-Shot Domain Adaptation via Dynamics Alignment for Humanoid Control","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23864","citing_title":"Learning to Feel the Future: DreamTacVLA for Contact-Rich Manipulation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2603.22003","citing_title":"VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models","ref_index":13,"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":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":141,"is_internal_anchor":false},{"citing_arxiv_id":"2501.09747","citing_title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08971","citing_title":"Modality-Aware Zero-Shot Pruning and Sparse Attention for Efficient Multimodal Edge Inference","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WY6ZE7WINZMAANT2C7OVVWJEW4","json":"https://pith.science/pith/WY6ZE7WINZMAANT2C7OVVWJEW4.json","graph_json":"https://pith.science/api/pith-number/WY6ZE7WINZMAANT2C7OVVWJEW4/graph.json","events_json":"https://pith.science/api/pith-number/WY6ZE7WINZMAANT2C7OVVWJEW4/events.json","paper":"https://pith.science/paper/WY6ZE7WI"},"agent_actions":{"view_html":"https://pith.science/pith/WY6ZE7WINZMAANT2C7OVVWJEW4","download_json":"https://pith.science/pith/WY6ZE7WINZMAANT2C7OVVWJEW4.json","view_paper":"https://pith.science/paper/WY6ZE7WI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.04693&json=true","fetch_graph":"https://pith.science/api/pith-number/WY6ZE7WINZMAANT2C7OVVWJEW4/graph.json","fetch_events":"https://pith.science/api/pith-number/WY6ZE7WINZMAANT2C7OVVWJEW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WY6ZE7WINZMAANT2C7OVVWJEW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WY6ZE7WINZMAANT2C7OVVWJEW4/action/storage_attestation","attest_author":"https://pith.science/pith/WY6ZE7WINZMAANT2C7OVVWJEW4/action/author_attestation","sign_citation":"https://pith.science/pith/WY6ZE7WINZMAANT2C7OVVWJEW4/action/citation_signature","submit_replication":"https://pith.science/pith/WY6ZE7WINZMAANT2C7OVVWJEW4/action/replication_record"}},"created_at":"2026-07-05T10:01:01.167738+00:00","updated_at":"2026-07-05T10:01:01.167738+00:00"}