{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OSEF2B337KI7FCGF6QGVSYAO3G","short_pith_number":"pith:OSEF2B33","schema_version":"1.0","canonical_sha256":"74885d077bfa91f288c5f40d59600ed998a198bae928ed6f21a81e8c6e642fee","source":{"kind":"arxiv","id":"2401.12024","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Visual-Tactile Representation Learning through Self-Supervised Contrastive Pre-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Elmar Rueckert, Fotios Lygerakis, Vedant Dave","submitted_at":"2024-01-22T15:11:57Z","abstract_excerpt":"The rapidly evolving field of robotics necessitates methods that can facilitate the fusion of multiple modalities. Specifically, when it comes to interacting with tangible objects, effectively combining visual and tactile sensory data is key to understanding and navigating the complex dynamics of the physical world, enabling a more nuanced and adaptable response to changing environments. Nevertheless, much of the earlier work in merging these two sensory modalities has relied on supervised methods utilizing datasets labeled by humans.This paper introduces MViTac, a novel methodology that lever"},"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":"2401.12024","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-01-22T15:11:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4963da37f063522acf5218295f7f1048c11ec659ffbaccae164ce98803f4fa32","abstract_canon_sha256":"3af828435dae60271ca37696201ad0ad4f4effb08b5bb56b7cefff9570b7f239"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:13.710132Z","signature_b64":"Zzvjs30EzbguOvJdfegUHd4u6rxjXO4Uvc00nl50YsJ6q+NdFlbIllUPdP+WqIXDgcf7HDDNxWu1qogux3VHCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74885d077bfa91f288c5f40d59600ed998a198bae928ed6f21a81e8c6e642fee","last_reissued_at":"2026-07-05T07:36:13.709642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:13.709642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Visual-Tactile Representation Learning through Self-Supervised Contrastive Pre-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Elmar Rueckert, Fotios Lygerakis, Vedant Dave","submitted_at":"2024-01-22T15:11:57Z","abstract_excerpt":"The rapidly evolving field of robotics necessitates methods that can facilitate the fusion of multiple modalities. Specifically, when it comes to interacting with tangible objects, effectively combining visual and tactile sensory data is key to understanding and navigating the complex dynamics of the physical world, enabling a more nuanced and adaptable response to changing environments. Nevertheless, much of the earlier work in merging these two sensory modalities has relied on supervised methods utilizing datasets labeled by humans.This paper introduces MViTac, a novel methodology that lever"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12024","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/2401.12024/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":"2401.12024","created_at":"2026-07-05T07:36:13.709701+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.12024v1","created_at":"2026-07-05T07:36:13.709701+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12024","created_at":"2026-07-05T07:36:13.709701+00:00"},{"alias_kind":"pith_short_12","alias_value":"OSEF2B337KI7","created_at":"2026-07-05T07:36:13.709701+00:00"},{"alias_kind":"pith_short_16","alias_value":"OSEF2B337KI7FCGF","created_at":"2026-07-05T07:36:13.709701+00:00"},{"alias_kind":"pith_short_8","alias_value":"OSEF2B33","created_at":"2026-07-05T07:36:13.709701+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06281","citing_title":"Multi-Resolution Tactile Imitation Learning for Contact-Rich Robotic Manipulation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23468","citing_title":"Multi-Modal Manipulation via Multi-Modal Policy Consensus","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2511.14427","citing_title":"Self-Supervised Multisensory Pretraining for Contact-Rich Robot Reinforcement Learning","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28156","citing_title":"FlexiTac: A Low-Cost, Open-Source, Scalable Tactile Sensing Solution for Robotic Systems","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OSEF2B337KI7FCGF6QGVSYAO3G","json":"https://pith.science/pith/OSEF2B337KI7FCGF6QGVSYAO3G.json","graph_json":"https://pith.science/api/pith-number/OSEF2B337KI7FCGF6QGVSYAO3G/graph.json","events_json":"https://pith.science/api/pith-number/OSEF2B337KI7FCGF6QGVSYAO3G/events.json","paper":"https://pith.science/paper/OSEF2B33"},"agent_actions":{"view_html":"https://pith.science/pith/OSEF2B337KI7FCGF6QGVSYAO3G","download_json":"https://pith.science/pith/OSEF2B337KI7FCGF6QGVSYAO3G.json","view_paper":"https://pith.science/paper/OSEF2B33","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.12024&json=true","fetch_graph":"https://pith.science/api/pith-number/OSEF2B337KI7FCGF6QGVSYAO3G/graph.json","fetch_events":"https://pith.science/api/pith-number/OSEF2B337KI7FCGF6QGVSYAO3G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OSEF2B337KI7FCGF6QGVSYAO3G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OSEF2B337KI7FCGF6QGVSYAO3G/action/storage_attestation","attest_author":"https://pith.science/pith/OSEF2B337KI7FCGF6QGVSYAO3G/action/author_attestation","sign_citation":"https://pith.science/pith/OSEF2B337KI7FCGF6QGVSYAO3G/action/citation_signature","submit_replication":"https://pith.science/pith/OSEF2B337KI7FCGF6QGVSYAO3G/action/replication_record"}},"created_at":"2026-07-05T07:36:13.709701+00:00","updated_at":"2026-07-05T07:36:13.709701+00:00"}