{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Y7A353KSDBYSEFHXFKX6P624KI","short_pith_number":"pith:Y7A353KS","schema_version":"1.0","canonical_sha256":"c7c1beed5218712214f72aafe7fb5c521c24a29d989dc75647eb5166bd7f9700","source":{"kind":"arxiv","id":"1810.10191","version":2},"attestation_state":"computed","paper":{"title":"Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Animesh Garg, Jeannette Bohg, Krishnan Srinivasan, Li Fei-Fei, Michelle A. Lee, Parth Shah, Silvio Savarese, Yuke Zhu","submitted_at":"2018-10-24T05:21:22Z","abstract_excerpt":"Contact-rich manipulation tasks in unstructured environments often require both haptic and visual feedback. However, it is non-trivial to manually design a robot controller that combines modalities with very different characteristics. While deep reinforcement learning has shown success in learning control policies for high-dimensional inputs, these algorithms are generally intractable to deploy on real robots due to sample complexity. We use self-supervision to learn a compact and multimodal representation of our sensory inputs, which can then be used to improve the sample efficiency of our po"},"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":"1810.10191","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-10-24T05:21:22Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c691e4e06933ed25c315745de43515aa10188fb3e135da99f92e9a84f6f7fbe4","abstract_canon_sha256":"45a77576cb911f909263c169f850de2abb32fd2b4fb70e5aa2d5433d15bae9a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:48.992664Z","signature_b64":"elgDWhAgS/qCBfotR0vsv3+aGQ72ugP3V7qpIa0QaMOaB/uCdNS4NT91QQBno+5tMA5LT945TgXLAxTPu37rBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7c1beed5218712214f72aafe7fb5c521c24a29d989dc75647eb5166bd7f9700","last_reissued_at":"2026-05-17T23:51:48.991941Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:48.991941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Animesh Garg, Jeannette Bohg, Krishnan Srinivasan, Li Fei-Fei, Michelle A. Lee, Parth Shah, Silvio Savarese, Yuke Zhu","submitted_at":"2018-10-24T05:21:22Z","abstract_excerpt":"Contact-rich manipulation tasks in unstructured environments often require both haptic and visual feedback. However, it is non-trivial to manually design a robot controller that combines modalities with very different characteristics. While deep reinforcement learning has shown success in learning control policies for high-dimensional inputs, these algorithms are generally intractable to deploy on real robots due to sample complexity. We use self-supervision to learn a compact and multimodal representation of our sensory inputs, which can then be used to improve the sample efficiency of our po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.10191","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":""},"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":"1810.10191","created_at":"2026-05-17T23:51:48.992053+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.10191v2","created_at":"2026-05-17T23:51:48.992053+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.10191","created_at":"2026-05-17T23:51:48.992053+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y7A353KSDBYS","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y7A353KSDBYSEFHX","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y7A353KS","created_at":"2026-05-18T12:33:04.347982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.09656","citing_title":"Grasping Using Tactile Sensing and Deep Calibration","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2511.14427","citing_title":"Self-Supervised Multisensory Pretraining for Contact-Rich Robot Reinforcement Learning","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y7A353KSDBYSEFHXFKX6P624KI","json":"https://pith.science/pith/Y7A353KSDBYSEFHXFKX6P624KI.json","graph_json":"https://pith.science/api/pith-number/Y7A353KSDBYSEFHXFKX6P624KI/graph.json","events_json":"https://pith.science/api/pith-number/Y7A353KSDBYSEFHXFKX6P624KI/events.json","paper":"https://pith.science/paper/Y7A353KS"},"agent_actions":{"view_html":"https://pith.science/pith/Y7A353KSDBYSEFHXFKX6P624KI","download_json":"https://pith.science/pith/Y7A353KSDBYSEFHXFKX6P624KI.json","view_paper":"https://pith.science/paper/Y7A353KS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.10191&json=true","fetch_graph":"https://pith.science/api/pith-number/Y7A353KSDBYSEFHXFKX6P624KI/graph.json","fetch_events":"https://pith.science/api/pith-number/Y7A353KSDBYSEFHXFKX6P624KI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y7A353KSDBYSEFHXFKX6P624KI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y7A353KSDBYSEFHXFKX6P624KI/action/storage_attestation","attest_author":"https://pith.science/pith/Y7A353KSDBYSEFHXFKX6P624KI/action/author_attestation","sign_citation":"https://pith.science/pith/Y7A353KSDBYSEFHXFKX6P624KI/action/citation_signature","submit_replication":"https://pith.science/pith/Y7A353KSDBYSEFHXFKX6P624KI/action/replication_record"}},"created_at":"2026-05-17T23:51:48.992053+00:00","updated_at":"2026-05-17T23:51:48.992053+00:00"}