{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4P76NSJQVPJX4PEOAJV644W32S","short_pith_number":"pith:4P76NSJQ","schema_version":"1.0","canonical_sha256":"e3ffe6c930abd37e3c8e026bee72dbd4a06a6cc22963121070ae5825145e0a97","source":{"kind":"arxiv","id":"2212.03858","version":2},"attestation_state":"computed","paper":{"title":"See, Hear, and Feel: Smart Sensory Fusion for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Edward Adelson, Hao Li, Huazhe Xu, Jiajun Wu, Junzhe Zhu, Li Fei-Fei, Michelle A Lee, Ruohan Gao, Shaoxiong Wang, Yizhi Zhang","submitted_at":"2022-12-07T18:55:53Z","abstract_excerpt":"Humans use all of their senses to accomplish different tasks in everyday activities. In contrast, existing work on robotic manipulation mostly relies on one, or occasionally two modalities, such as vision and touch. In this work, we systematically study how visual, auditory, and tactile perception can jointly help robots to solve complex manipulation tasks. We build a robot system that can see with a camera, hear with a contact microphone, and feel with a vision-based tactile sensor, with all three sensory modalities fused with a self-attention model. Results on two challenging tasks, dense pa"},"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":"2212.03858","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-12-07T18:55:53Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"926481bcfd1cca94ebe53e0ab328d9fa384db992c5f38ac0eb437fbe5cf1c438","abstract_canon_sha256":"01e36e9569dbe8ba80ca19e20520924741f250d52fc9ee5c93f679955955d3e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:23:35.194142Z","signature_b64":"b966UPLVAntgZgmmnaxhJBPm7Qoy+XKXwilOHOvor/3EEps3w23fPIxHBLjYOX0Snc1iiG02fQ2V5uiBWhSpBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3ffe6c930abd37e3c8e026bee72dbd4a06a6cc22963121070ae5825145e0a97","last_reissued_at":"2026-07-05T05:23:35.193715Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:23:35.193715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"See, Hear, and Feel: Smart Sensory Fusion for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Edward Adelson, Hao Li, Huazhe Xu, Jiajun Wu, Junzhe Zhu, Li Fei-Fei, Michelle A Lee, Ruohan Gao, Shaoxiong Wang, Yizhi Zhang","submitted_at":"2022-12-07T18:55:53Z","abstract_excerpt":"Humans use all of their senses to accomplish different tasks in everyday activities. In contrast, existing work on robotic manipulation mostly relies on one, or occasionally two modalities, such as vision and touch. In this work, we systematically study how visual, auditory, and tactile perception can jointly help robots to solve complex manipulation tasks. We build a robot system that can see with a camera, hear with a contact microphone, and feel with a vision-based tactile sensor, with all three sensory modalities fused with a self-attention model. Results on two challenging tasks, dense pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.03858","kind":"arxiv","version":2},"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/2212.03858/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":"2212.03858","created_at":"2026-07-05T05:23:35.193772+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.03858v2","created_at":"2026-07-05T05:23:35.193772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.03858","created_at":"2026-07-05T05:23:35.193772+00:00"},{"alias_kind":"pith_short_12","alias_value":"4P76NSJQVPJX","created_at":"2026-07-05T05:23:35.193772+00:00"},{"alias_kind":"pith_short_16","alias_value":"4P76NSJQVPJX4PEO","created_at":"2026-07-05T05:23:35.193772+00:00"},{"alias_kind":"pith_short_8","alias_value":"4P76NSJQ","created_at":"2026-07-05T05:23:35.193772+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06281","citing_title":"Multi-Resolution Tactile Imitation Learning for Contact-Rich Robotic Manipulation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31723","citing_title":"UniTacVLA: Unified Tactile Understanding and Prediction in Vision Language Action Models","ref_index":1,"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":38,"is_internal_anchor":false},{"citing_arxiv_id":"2504.18662","citing_title":"M2R2: MultiModal Robotic Representation for Temporal Action Segmentation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2511.14427","citing_title":"Self-Supervised Multisensory Pretraining for Contact-Rich Robot Reinforcement Learning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23864","citing_title":"Learning to Feel the Future: DreamTacVLA for Contact-Rich Manipulation","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4P76NSJQVPJX4PEOAJV644W32S","json":"https://pith.science/pith/4P76NSJQVPJX4PEOAJV644W32S.json","graph_json":"https://pith.science/api/pith-number/4P76NSJQVPJX4PEOAJV644W32S/graph.json","events_json":"https://pith.science/api/pith-number/4P76NSJQVPJX4PEOAJV644W32S/events.json","paper":"https://pith.science/paper/4P76NSJQ"},"agent_actions":{"view_html":"https://pith.science/pith/4P76NSJQVPJX4PEOAJV644W32S","download_json":"https://pith.science/pith/4P76NSJQVPJX4PEOAJV644W32S.json","view_paper":"https://pith.science/paper/4P76NSJQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.03858&json=true","fetch_graph":"https://pith.science/api/pith-number/4P76NSJQVPJX4PEOAJV644W32S/graph.json","fetch_events":"https://pith.science/api/pith-number/4P76NSJQVPJX4PEOAJV644W32S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4P76NSJQVPJX4PEOAJV644W32S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4P76NSJQVPJX4PEOAJV644W32S/action/storage_attestation","attest_author":"https://pith.science/pith/4P76NSJQVPJX4PEOAJV644W32S/action/author_attestation","sign_citation":"https://pith.science/pith/4P76NSJQVPJX4PEOAJV644W32S/action/citation_signature","submit_replication":"https://pith.science/pith/4P76NSJQVPJX4PEOAJV644W32S/action/replication_record"}},"created_at":"2026-07-05T05:23:35.193772+00:00","updated_at":"2026-07-05T05:23:35.193772+00:00"}