{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YWLO2JJRFPYP7VP437CQSD2SRY","short_pith_number":"pith:YWLO2JJR","canonical_record":{"source":{"id":"2605.21414","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-20T17:10:31Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"35da05681e127de13b6c5df231c2e9d0295e74d06f995e23418a3d46bf27126a","abstract_canon_sha256":"cb54c10436ecc43b838e6d0ebd78a5631aa001ae1cb257ed60c87c0996f2aadb"},"schema_version":"1.0"},"canonical_sha256":"c596ed25312bf0ffd5fcdfc5090f528e2b0ae4ccec16be6ac682884ae3bf5b97","source":{"kind":"arxiv","id":"2605.21414","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21414","created_at":"2026-05-21T02:05:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21414v1","created_at":"2026-05-21T02:05:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21414","created_at":"2026-05-21T02:05:33Z"},{"alias_kind":"pith_short_12","alias_value":"YWLO2JJRFPYP","created_at":"2026-05-21T02:05:33Z"},{"alias_kind":"pith_short_16","alias_value":"YWLO2JJRFPYP7VP4","created_at":"2026-05-21T02:05:33Z"},{"alias_kind":"pith_short_8","alias_value":"YWLO2JJR","created_at":"2026-05-21T02:05:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YWLO2JJRFPYP7VP437CQSD2SRY","target":"record","payload":{"canonical_record":{"source":{"id":"2605.21414","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-20T17:10:31Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"35da05681e127de13b6c5df231c2e9d0295e74d06f995e23418a3d46bf27126a","abstract_canon_sha256":"cb54c10436ecc43b838e6d0ebd78a5631aa001ae1cb257ed60c87c0996f2aadb"},"schema_version":"1.0"},"canonical_sha256":"c596ed25312bf0ffd5fcdfc5090f528e2b0ae4ccec16be6ac682884ae3bf5b97","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:05:33.604987Z","signature_b64":"hZ2Y6yUsIpLMa5h278AULCgt57imL/a4RziG5dy28bl1KQzAcRp+tFla3iEcxi/XnMHRFkbi0CcOeLxNnh0yCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c596ed25312bf0ffd5fcdfc5090f528e2b0ae4ccec16be6ac682884ae3bf5b97","last_reissued_at":"2026-05-21T02:05:33.604150Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:05:33.604150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.21414","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T02:05:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AjIN9GOBLOKireG8w7W6XwSIj5f/v3qU/T7YkiFNnAeKpb81dwyjFdDbHg2gWu9nnPby3QXjJI985JQhxSfKBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T14:09:58.064755Z"},"content_sha256":"3ac812c6b688f91cf424db0f9e0a68a50331f48cb9f77d6f33ab6e45188b7c15","schema_version":"1.0","event_id":"sha256:3ac812c6b688f91cf424db0f9e0a68a50331f48cb9f77d6f33ab6e45188b7c15"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YWLO2JJRFPYP7VP437CQSD2SRY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Cordelia Schmid, Paul Pacaud, Shizhe Chen","submitted_at":"2026-05-20T17:10:31Z","abstract_excerpt":"Vision-Language-Action (VLA) models have shown strong potential for general-purpose robotic manipulation by leveraging large pretrained vision-language backbones. However, most existing VLAs rely primarily on 2D visual representations, which limit their ability to reason about fine-grained geometry and spatial grounding - capabilities that are essential for precise and robust manipulation in 3D environments. In this paper, we propose PointACT, a dual-system 3D-aware VLA policy that integrates hierarchical 3D point cloud representations directly into the action decoding process. PointACT employ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21414","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/2605.21414/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T02:05:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XNH62Ckxc9qcDmXev9k2bvBNT+AfD4q8kkiGJDRJbNgwz/13Y/nXo67IUGeUIMh8Efw4ce9+ydql/Ub7B26JCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T14:09:58.065521Z"},"content_sha256":"938b7ee64c0e4725524e572992e7716d4bf79206f51679bebd038a882fc2b549","schema_version":"1.0","event_id":"sha256:938b7ee64c0e4725524e572992e7716d4bf79206f51679bebd038a882fc2b549"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YWLO2JJRFPYP7VP437CQSD2SRY/bundle.json","state_url":"https://pith.science/pith/YWLO2JJRFPYP7VP437CQSD2SRY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YWLO2JJRFPYP7VP437CQSD2SRY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-23T14:09:58Z","links":{"resolver":"https://pith.science/pith/YWLO2JJRFPYP7VP437CQSD2SRY","bundle":"https://pith.science/pith/YWLO2JJRFPYP7VP437CQSD2SRY/bundle.json","state":"https://pith.science/pith/YWLO2JJRFPYP7VP437CQSD2SRY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YWLO2JJRFPYP7VP437CQSD2SRY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YWLO2JJRFPYP7VP437CQSD2SRY","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":"cb54c10436ecc43b838e6d0ebd78a5631aa001ae1cb257ed60c87c0996f2aadb","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-20T17:10:31Z","title_canon_sha256":"35da05681e127de13b6c5df231c2e9d0295e74d06f995e23418a3d46bf27126a"},"schema_version":"1.0","source":{"id":"2605.21414","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21414","created_at":"2026-05-21T02:05:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21414v1","created_at":"2026-05-21T02:05:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21414","created_at":"2026-05-21T02:05:33Z"},{"alias_kind":"pith_short_12","alias_value":"YWLO2JJRFPYP","created_at":"2026-05-21T02:05:33Z"},{"alias_kind":"pith_short_16","alias_value":"YWLO2JJRFPYP7VP4","created_at":"2026-05-21T02:05:33Z"},{"alias_kind":"pith_short_8","alias_value":"YWLO2JJR","created_at":"2026-05-21T02:05:33Z"}],"graph_snapshots":[{"event_id":"sha256:938b7ee64c0e4725524e572992e7716d4bf79206f51679bebd038a882fc2b549","target":"graph","created_at":"2026-05-21T02:05:33Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.21414/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) models have shown strong potential for general-purpose robotic manipulation by leveraging large pretrained vision-language backbones. However, most existing VLAs rely primarily on 2D visual representations, which limit their ability to reason about fine-grained geometry and spatial grounding - capabilities that are essential for precise and robust manipulation in 3D environments. In this paper, we propose PointACT, a dual-system 3D-aware VLA policy that integrates hierarchical 3D point cloud representations directly into the action decoding process. PointACT employ","authors_text":"Cordelia Schmid, Paul Pacaud, Shizhe Chen","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-20T17:10:31Z","title":"PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21414","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3ac812c6b688f91cf424db0f9e0a68a50331f48cb9f77d6f33ab6e45188b7c15","target":"record","created_at":"2026-05-21T02:05:33Z","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":"cb54c10436ecc43b838e6d0ebd78a5631aa001ae1cb257ed60c87c0996f2aadb","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-20T17:10:31Z","title_canon_sha256":"35da05681e127de13b6c5df231c2e9d0295e74d06f995e23418a3d46bf27126a"},"schema_version":"1.0","source":{"id":"2605.21414","kind":"arxiv","version":1}},"canonical_sha256":"c596ed25312bf0ffd5fcdfc5090f528e2b0ae4ccec16be6ac682884ae3bf5b97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c596ed25312bf0ffd5fcdfc5090f528e2b0ae4ccec16be6ac682884ae3bf5b97","first_computed_at":"2026-05-21T02:05:33.604150Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T02:05:33.604150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hZ2Y6yUsIpLMa5h278AULCgt57imL/a4RziG5dy28bl1KQzAcRp+tFla3iEcxi/XnMHRFkbi0CcOeLxNnh0yCw==","signature_status":"signed_v1","signed_at":"2026-05-21T02:05:33.604987Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21414","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ac812c6b688f91cf424db0f9e0a68a50331f48cb9f77d6f33ab6e45188b7c15","sha256:938b7ee64c0e4725524e572992e7716d4bf79206f51679bebd038a882fc2b549"],"state_sha256":"5b969abb9b52db1274e6ec25853d459ebd65fcbe272a7a5300b4007f2626a7b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CxD+f060BkVe14jFH8qbsycItbH5o45lpYV7Je0848AbCBcIkMbMJRLEq7D2OuRF6DbV0Mpn8K98nlv/DhdpBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T14:09:58.069434Z","bundle_sha256":"584edfe468f005ae0eb87c580213b873d3f7d656180ef3c6369c0ed9a37c3682"}}