{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:A5CUGUDOT3ULB4LXO3QBOOK4UA","short_pith_number":"pith:A5CUGUDO","schema_version":"1.0","canonical_sha256":"074543506e9ee8b0f17776e017395ca0088c91d1b5330b25032862b30ac38cf9","source":{"kind":"arxiv","id":"2604.25897","version":2},"attestation_state":"computed","paper":{"title":"Variational Neural Belief Parameterizations for Robust Dexterous Grasping under Multimodal Uncertainty","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A variational Gaussian-mixture belief enables faster, more robust dexterous grasping by optimizing risk-sensitive objectives directly.","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Calin Belta, Clinton Enwerem, John S. Baras, Shreya Kalyanaraman","submitted_at":"2026-04-28T17:40:49Z","abstract_excerpt":"Contact variability, sensing uncertainty, and external disturbances make grasp execution stochastic. Expected-quality objectives ignore tail outcomes and often select grasps that fail under adverse contact realizations. Risk-sensitive POMDPs address this failure mode, but many use particle-filter beliefs that scale poorly, obstruct gradient-based optimization, and estimate Conditional Value-at-Risk (CVaR) with high-variance approximations. We instead formulate grasp acquisition as variational inference over latent contact parameters and object pose, representing the belief with a differentiabl"},"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":"2604.25897","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-04-28T17:40:49Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"4d016aa5960fe168986b689f09a8464edfe82731b9f05a300d7942ce577e7350","abstract_canon_sha256":"f13ffe2590a7a9783c5e5ff0f658cc5c3be370eeb200c2bbeb646254de33c94c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:21:36.141292Z","signature_b64":"3Pmiq8OCX0WAucMfTbLU/FGVVhBSql1a7Yh4PkLH+NLUBzMkVmpHbKiVgxmBZ8UhaQxSbIdFNMT4/NlcX3FXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"074543506e9ee8b0f17776e017395ca0088c91d1b5330b25032862b30ac38cf9","last_reissued_at":"2026-07-28T00:21:36.140301Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:21:36.140301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Neural Belief Parameterizations for Robust Dexterous Grasping under Multimodal Uncertainty","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A variational Gaussian-mixture belief enables faster, more robust dexterous grasping by optimizing risk-sensitive objectives directly.","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Calin Belta, Clinton Enwerem, John S. Baras, Shreya Kalyanaraman","submitted_at":"2026-04-28T17:40:49Z","abstract_excerpt":"Contact variability, sensing uncertainty, and external disturbances make grasp execution stochastic. Expected-quality objectives ignore tail outcomes and often select grasps that fail under adverse contact realizations. Risk-sensitive POMDPs address this failure mode, but many use particle-filter beliefs that scale poorly, obstruct gradient-based optimization, and estimate Conditional Value-at-Risk (CVaR) with high-variance approximations. We instead formulate grasp acquisition as variational inference over latent contact parameters and object pose, representing the belief with a differentiabl"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"In simulation, our variational neural belief improves robust grasp success under contact-parameter uncertainty and exogenous force perturbations while reducing planning time by roughly an order of magnitude relative to particle-filter model-predictive control. On a serial-chain robot arm with a multifingered hand, we validate grasp-and-lift success under object-pose uncertainty against a Gaussian baseline. Both methods succeed on the tested perturbations, but our controller terminates in fewer steps and less wall-clock time while achieving a higher tactile grasp-quality proxy.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a finite Gaussian mixture plus variational inference yields a sufficiently accurate and differentiable approximation to the true multimodal posterior over latent contact parameters and object pose for the CVaR objective to produce reliable robustness gains.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A variational Gaussian-mixture belief with Gumbel-Softmax and reparameterized sampling enables direct gradient optimization of tail-risk grasping objectives, improving success rates and cutting planning time versus particle-filter baselines.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A variational Gaussian-mixture belief enables faster, more robust dexterous grasping by optimizing risk-sensitive objectives directly.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"85f12411fb4a840852a38c053ad63195540917f4ad3bcfd6b15c30b909424bcb"},"source":{"id":"2604.25897","kind":"arxiv","version":2},"verdict":{"id":"75d13e9f-a54c-43f3-90ba-f6c3d76ed19e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T15:32:37.419169Z","strongest_claim":"In simulation, our variational neural belief improves robust grasp success under contact-parameter uncertainty and exogenous force perturbations while reducing planning time by roughly an order of magnitude relative to particle-filter model-predictive control. On a serial-chain robot arm with a multifingered hand, we validate grasp-and-lift success under object-pose uncertainty against a Gaussian baseline. Both methods succeed on the tested perturbations, but our controller terminates in fewer steps and less wall-clock time while achieving a higher tactile grasp-quality proxy.","one_line_summary":"A variational Gaussian-mixture belief with Gumbel-Softmax and reparameterized sampling enables direct gradient optimization of tail-risk grasping objectives, improving success rates and cutting planning time versus particle-filter baselines.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a finite Gaussian mixture plus variational inference yields a sufficiently accurate and differentiable approximation to the true multimodal posterior over latent contact parameters and object pose for the CVaR objective to produce reliable robustness gains.","pith_extraction_headline":"A variational Gaussian-mixture belief enables faster, more robust dexterous grasping by optimizing risk-sensitive objectives directly."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.25897/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T03:39:01.010326Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T20:37:00.423443Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"3c9d211476a74d878e6b77b762f9031e0c9cc45f9067e386e7cb4b1938807b2a"},"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":"2604.25897","created_at":"2026-07-28T00:21:36.140727+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.25897v2","created_at":"2026-07-28T00:21:36.140727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.25897","created_at":"2026-07-28T00:21:36.140727+00:00"},{"alias_kind":"pith_short_12","alias_value":"A5CUGUDOT3UL","created_at":"2026-07-28T00:21:36.140727+00:00"},{"alias_kind":"pith_short_16","alias_value":"A5CUGUDOT3ULB4LX","created_at":"2026-07-28T00:21:36.140727+00:00"},{"alias_kind":"pith_short_8","alias_value":"A5CUGUDO","created_at":"2026-07-28T00:21:36.140727+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.12728","citing_title":"EquiDexFlow: Contact-Grounded SE(3)-Equivariant Dexterous Grasp Generative Flows","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A5CUGUDOT3ULB4LXO3QBOOK4UA","json":"https://pith.science/pith/A5CUGUDOT3ULB4LXO3QBOOK4UA.json","graph_json":"https://pith.science/api/pith-number/A5CUGUDOT3ULB4LXO3QBOOK4UA/graph.json","events_json":"https://pith.science/api/pith-number/A5CUGUDOT3ULB4LXO3QBOOK4UA/events.json","paper":"https://pith.science/paper/A5CUGUDO"},"agent_actions":{"view_html":"https://pith.science/pith/A5CUGUDOT3ULB4LXO3QBOOK4UA","download_json":"https://pith.science/pith/A5CUGUDOT3ULB4LXO3QBOOK4UA.json","view_paper":"https://pith.science/paper/A5CUGUDO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.25897&json=true","fetch_graph":"https://pith.science/api/pith-number/A5CUGUDOT3ULB4LXO3QBOOK4UA/graph.json","fetch_events":"https://pith.science/api/pith-number/A5CUGUDOT3ULB4LXO3QBOOK4UA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A5CUGUDOT3ULB4LXO3QBOOK4UA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A5CUGUDOT3ULB4LXO3QBOOK4UA/action/storage_attestation","attest_author":"https://pith.science/pith/A5CUGUDOT3ULB4LXO3QBOOK4UA/action/author_attestation","sign_citation":"https://pith.science/pith/A5CUGUDOT3ULB4LXO3QBOOK4UA/action/citation_signature","submit_replication":"https://pith.science/pith/A5CUGUDOT3ULB4LXO3QBOOK4UA/action/replication_record"}},"created_at":"2026-07-28T00:21:36.140727+00:00","updated_at":"2026-07-28T00:21:36.140727+00:00"}