{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:A3HJGGMV4VSJBCDLWFOP7SLV45","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c3477e2c1833f426114f4a3fe7e2d6b5894a75c233d767e77345ba14b14957a5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-11-18T12:32:23Z","title_canon_sha256":"20c20ad424df6c7dad37ba2e44711c0f607ef77018f9cabda1b5c620afc23513"},"schema_version":"1.0","source":{"id":"2511.14427","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.14427","created_at":"2026-06-11T01:09:22Z"},{"alias_kind":"arxiv_version","alias_value":"2511.14427v4","created_at":"2026-06-11T01:09:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.14427","created_at":"2026-06-11T01:09:22Z"},{"alias_kind":"pith_short_12","alias_value":"A3HJGGMV4VSJ","created_at":"2026-06-11T01:09:22Z"},{"alias_kind":"pith_short_16","alias_value":"A3HJGGMV4VSJBCDL","created_at":"2026-06-11T01:09:22Z"},{"alias_kind":"pith_short_8","alias_value":"A3HJGGMV","created_at":"2026-06-11T01:09:22Z"}],"graph_snapshots":[{"event_id":"sha256:2acf9866fce9d1222e48e8961408b72e969bda878783c4894f03565a1fa635f4","target":"graph","created_at":"2026-06-11T01:09:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our approach exhibits strong robustness to perturbations and achieves high success rates on the real robot with as few as 6,000 online interactions, offering a simple yet powerful solution for complex multisensory robotic control."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the representations learned by masked autoencoding on multisensory observations will contain the dynamic, task-relevant features needed by the critic without requiring additional fine-tuning or task-specific adaptation during pretraining."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MSDP pretrains a transformer encoder via masked multisensory reconstruction and feeds the embeddings into an asymmetric actor-critic RL setup, yielding faster learning and high real-robot success rates with only 6,000 interactions."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Self-supervised multisensory pretraining allows robots to learn contact-rich manipulation with few real-world trials."}],"snapshot_sha256":"f08dd8b40c5136c83c278349c46bfdba0a91c695ed17b8210c99b275539cadcd"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"09e41fd4c864b92575d936d436d7f1432ac3ae7132c041de69425565a05b8945"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2511.14427/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Effective contact-rich manipulation requires robots to synergistically leverage vision, force, and proprioception. However, Reinforcement Learning agents struggle to learn in such multisensory settings, especially amidst sensory noise and dynamic changes. We propose MultiSensory Dynamic Pretraining (MSDP), a novel framework for learning expressive multisensory representations tailored for task-oriented policy learning. MSDP is based on masked autoencoding and trains a transformer-based encoder by reconstructing multisensory observations from only a subset of sensor embeddings, leading to cross","authors_text":"Gabriele Tiboni, Georgia Chalvatzaki, Rickmer Krohn, Vignesh Prasad","cross_cats":["cs.LG"],"headline":"Self-supervised multisensory pretraining allows robots to learn contact-rich manipulation with few real-world trials.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-11-18T12:32:23Z","title":"Self-Supervised Multisensory Pretraining for Contact-Rich Robot Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.14427","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-17T21:01:17.451795Z","id":"61e9d419-62d2-4767-b718-f5eef2410828","model_set":{"reader":"grok-4.3"},"one_line_summary":"MSDP pretrains a transformer encoder via masked multisensory reconstruction and feeds the embeddings into an asymmetric actor-critic RL setup, yielding faster learning and high real-robot success rates with only 6,000 interactions.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Self-supervised multisensory pretraining allows robots to learn contact-rich manipulation with few real-world trials.","strongest_claim":"Our approach exhibits strong robustness to perturbations and achieves high success rates on the real robot with as few as 6,000 online interactions, offering a simple yet powerful solution for complex multisensory robotic control.","weakest_assumption":"That the representations learned by masked autoencoding on multisensory observations will contain the dynamic, task-relevant features needed by the critic without requiring additional fine-tuning or task-specific adaptation during pretraining."}},"verdict_id":"61e9d419-62d2-4767-b718-f5eef2410828"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7ee1762378a35e0a6ae03ac38832516a58a9e5c98cf270226e406b8a9a605852","target":"record","created_at":"2026-06-11T01:09:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c3477e2c1833f426114f4a3fe7e2d6b5894a75c233d767e77345ba14b14957a5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-11-18T12:32:23Z","title_canon_sha256":"20c20ad424df6c7dad37ba2e44711c0f607ef77018f9cabda1b5c620afc23513"},"schema_version":"1.0","source":{"id":"2511.14427","kind":"arxiv","version":4}},"canonical_sha256":"06ce931995e56490886bb15cffc975e75af518af2d1a8565542febba39471d14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06ce931995e56490886bb15cffc975e75af518af2d1a8565542febba39471d14","first_computed_at":"2026-06-11T01:09:22.060932Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:09:22.060932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8b+lpAqmI84LGPMUoWACb8eEw34HZF0vsfqu8R5CVu4TLoJfsrK7jzlpQCyUWM1DhVYHBYj/vv4qo75YpR/sDA==","signature_status":"signed_v1","signed_at":"2026-06-11T01:09:22.062052Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.14427","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ee1762378a35e0a6ae03ac38832516a58a9e5c98cf270226e406b8a9a605852","sha256:2acf9866fce9d1222e48e8961408b72e969bda878783c4894f03565a1fa635f4"],"state_sha256":"6033240ffb07f92c2224aa9c2d09e9c8fc2b5037466d8775f81320cd93fca69a"}