{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WARKTWYB34DPD4BFVI337OABNG","short_pith_number":"pith:WARKTWYB","schema_version":"1.0","canonical_sha256":"b022a9db01df06f1f025aa37bfb80169a7ec0a7601f062e6e08658f91d4f60d1","source":{"kind":"arxiv","id":"2402.18002","version":2},"attestation_state":"computed","paper":{"title":"Symmetry-aware Reinforcement Learning for Robotic Assembly under Partial Observability with a Soft Wrist","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Cristian C. Beltran-Hernandez, Hai Nguyen, Masashi Hamaya, Tadashi Kozuno","submitted_at":"2024-02-28T02:30:59Z","abstract_excerpt":"This study tackles the representative yet challenging contact-rich peg-in-hole task of robotic assembly, using a soft wrist that can operate more safely and tolerate lower-frequency control signals than a rigid one. Previous studies often use a fully observable formulation, requiring external setups or estimators for the peg-to-hole pose. In contrast, we use a partially observable formulation and deep reinforcement learning from demonstrations to learn a memory-based agent that acts purely on haptic and proprioceptive signals. Moreover, previous works do not incorporate potential domain symmet"},"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":"2402.18002","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-02-28T02:30:59Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"383ecc84ef2d04ef89d22cf9da172e600ce16a23886b1f0ecbfc58d148f5de68","abstract_canon_sha256":"75522b8f2f68e6dd032942afeeb5e3cdcbd2bf9f17607d7893e22e8561e6c06d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:30.571365Z","signature_b64":"YWSsmcCkWsNoorpgqClSdHz2Ud5/eOjRuZWDhgXlGQfI8AdEdgQ7iFt3cvmCKmbMoAKOQgkpRmUc9iXHkJY8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b022a9db01df06f1f025aa37bfb80169a7ec0a7601f062e6e08658f91d4f60d1","last_reissued_at":"2026-07-05T08:13:30.570950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:30.570950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Symmetry-aware Reinforcement Learning for Robotic Assembly under Partial Observability with a Soft Wrist","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Cristian C. Beltran-Hernandez, Hai Nguyen, Masashi Hamaya, Tadashi Kozuno","submitted_at":"2024-02-28T02:30:59Z","abstract_excerpt":"This study tackles the representative yet challenging contact-rich peg-in-hole task of robotic assembly, using a soft wrist that can operate more safely and tolerate lower-frequency control signals than a rigid one. Previous studies often use a fully observable formulation, requiring external setups or estimators for the peg-to-hole pose. In contrast, we use a partially observable formulation and deep reinforcement learning from demonstrations to learn a memory-based agent that acts purely on haptic and proprioceptive signals. Moreover, previous works do not incorporate potential domain symmet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18002","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/2402.18002/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":"2402.18002","created_at":"2026-07-05T08:13:30.571007+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.18002v2","created_at":"2026-07-05T08:13:30.571007+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18002","created_at":"2026-07-05T08:13:30.571007+00:00"},{"alias_kind":"pith_short_12","alias_value":"WARKTWYB34DP","created_at":"2026-07-05T08:13:30.571007+00:00"},{"alias_kind":"pith_short_16","alias_value":"WARKTWYB34DPD4BF","created_at":"2026-07-05T08:13:30.571007+00:00"},{"alias_kind":"pith_short_8","alias_value":"WARKTWYB","created_at":"2026-07-05T08:13:30.571007+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WARKTWYB34DPD4BFVI337OABNG","json":"https://pith.science/pith/WARKTWYB34DPD4BFVI337OABNG.json","graph_json":"https://pith.science/api/pith-number/WARKTWYB34DPD4BFVI337OABNG/graph.json","events_json":"https://pith.science/api/pith-number/WARKTWYB34DPD4BFVI337OABNG/events.json","paper":"https://pith.science/paper/WARKTWYB"},"agent_actions":{"view_html":"https://pith.science/pith/WARKTWYB34DPD4BFVI337OABNG","download_json":"https://pith.science/pith/WARKTWYB34DPD4BFVI337OABNG.json","view_paper":"https://pith.science/paper/WARKTWYB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.18002&json=true","fetch_graph":"https://pith.science/api/pith-number/WARKTWYB34DPD4BFVI337OABNG/graph.json","fetch_events":"https://pith.science/api/pith-number/WARKTWYB34DPD4BFVI337OABNG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WARKTWYB34DPD4BFVI337OABNG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WARKTWYB34DPD4BFVI337OABNG/action/storage_attestation","attest_author":"https://pith.science/pith/WARKTWYB34DPD4BFVI337OABNG/action/author_attestation","sign_citation":"https://pith.science/pith/WARKTWYB34DPD4BFVI337OABNG/action/citation_signature","submit_replication":"https://pith.science/pith/WARKTWYB34DPD4BFVI337OABNG/action/replication_record"}},"created_at":"2026-07-05T08:13:30.571007+00:00","updated_at":"2026-07-05T08:13:30.571007+00:00"}