{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IXHGQ276HNYBXCNZJNRSCZF634","short_pith_number":"pith:IXHGQ276","canonical_record":{"source":{"id":"2605.22812","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-21T17:57:44Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"20cac9327927dba9e8b5336fd8e916c0dee22321cb0923f5ab46fd4d50f6c0b8","abstract_canon_sha256":"60f536441ee2f36951d856eda3d9922e3ba1aa3dce0e89fc6efc20d86f30c923"},"schema_version":"1.0"},"canonical_sha256":"45ce686bfe3b701b89b94b632164bedf051aaadd98079d3dbd9524bf5c200043","source":{"kind":"arxiv","id":"2605.22812","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22812","created_at":"2026-05-22T02:04:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22812v1","created_at":"2026-05-22T02:04:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22812","created_at":"2026-05-22T02:04:55Z"},{"alias_kind":"pith_short_12","alias_value":"IXHGQ276HNYB","created_at":"2026-05-22T02:04:55Z"},{"alias_kind":"pith_short_16","alias_value":"IXHGQ276HNYBXCNZ","created_at":"2026-05-22T02:04:55Z"},{"alias_kind":"pith_short_8","alias_value":"IXHGQ276","created_at":"2026-05-22T02:04:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IXHGQ276HNYBXCNZJNRSCZF634","target":"record","payload":{"canonical_record":{"source":{"id":"2605.22812","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-21T17:57:44Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"20cac9327927dba9e8b5336fd8e916c0dee22321cb0923f5ab46fd4d50f6c0b8","abstract_canon_sha256":"60f536441ee2f36951d856eda3d9922e3ba1aa3dce0e89fc6efc20d86f30c923"},"schema_version":"1.0"},"canonical_sha256":"45ce686bfe3b701b89b94b632164bedf051aaadd98079d3dbd9524bf5c200043","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T02:04:55.896565Z","signature_b64":"PR++qVEzJ96ZemFgvENVxq7Zgw8+H+FQx7TaPjjykmhLAKAutDn2BaDfNviJHCtjX0AT+D8nGMhYbgVuXXYuDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45ce686bfe3b701b89b94b632164bedf051aaadd98079d3dbd9524bf5c200043","last_reissued_at":"2026-05-22T02:04:55.895884Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T02:04:55.895884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.22812","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":"2026-05-22T02:04:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QQWEcb4LAcmNIP/W6/SY6ADeXRWTPOYnChcuUWbPwsDbww/8VTpp087xisRbZwLoD15vdtArpG9VwD0EbIJQDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:05:18.088542Z"},"content_sha256":"520d9556a983a9fd9bd74c9a137f0d2baec3a8a36718ccaf92b4427ce5510a70","schema_version":"1.0","event_id":"sha256:520d9556a983a9fd9bd74c9a137f0d2baec3a8a36718ccaf92b4427ce5510a70"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IXHGQ276HNYBXCNZJNRSCZF634","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GesVLA: Gesture-Aware Vision-Language-Action Model Embedded Representations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chuxi Xu, Erjin Zhou, Jianjiang Feng, Meng Zhang, Wenxuan Guo, Yichen Liu, Yimeng Dong, Yunfei Wei, Ze Chen, Ziyuan Li","submitted_at":"2026-05-21T17:57:44Z","abstract_excerpt":"Vision-Language-Action (VLA) models have shown strong potential for general-purpose robot manipulation by unifying perception and action. However, existing VLA systems primarily rely on textual instructions and struggle to resolve spatial ambiguity in complex scenes with multiple similar objects. To address this limitation, we introduce gesture as a parallel instruction modality and propose a Gesture-aware Vision-Language-Action model (GesVLA). Our approach encodes gesture features directly into the latent space, enabling them to participate in both high-level reasoning and low-level action ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22812","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/2605.22812/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":"2026-05-22T02:04:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k84oUnom+2JYJZZSUX5ATmlDva3so6JPNCW61nERh7GScEab1wfrD/3ll+yniwYjkfOs8SAx226c40//Cx77AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:05:18.089287Z"},"content_sha256":"6d6621046646b9615d99b22b0b20facccd830b8e30b9a9cea8c8df392c2fabb4","schema_version":"1.0","event_id":"sha256:6d6621046646b9615d99b22b0b20facccd830b8e30b9a9cea8c8df392c2fabb4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IXHGQ276HNYBXCNZJNRSCZF634/bundle.json","state_url":"https://pith.science/pith/IXHGQ276HNYBXCNZJNRSCZF634/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IXHGQ276HNYBXCNZJNRSCZF634/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":"2026-05-26T08:05:18Z","links":{"resolver":"https://pith.science/pith/IXHGQ276HNYBXCNZJNRSCZF634","bundle":"https://pith.science/pith/IXHGQ276HNYBXCNZJNRSCZF634/bundle.json","state":"https://pith.science/pith/IXHGQ276HNYBXCNZJNRSCZF634/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IXHGQ276HNYBXCNZJNRSCZF634/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IXHGQ276HNYBXCNZJNRSCZF634","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":"60f536441ee2f36951d856eda3d9922e3ba1aa3dce0e89fc6efc20d86f30c923","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-21T17:57:44Z","title_canon_sha256":"20cac9327927dba9e8b5336fd8e916c0dee22321cb0923f5ab46fd4d50f6c0b8"},"schema_version":"1.0","source":{"id":"2605.22812","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22812","created_at":"2026-05-22T02:04:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22812v1","created_at":"2026-05-22T02:04:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22812","created_at":"2026-05-22T02:04:55Z"},{"alias_kind":"pith_short_12","alias_value":"IXHGQ276HNYB","created_at":"2026-05-22T02:04:55Z"},{"alias_kind":"pith_short_16","alias_value":"IXHGQ276HNYBXCNZ","created_at":"2026-05-22T02:04:55Z"},{"alias_kind":"pith_short_8","alias_value":"IXHGQ276","created_at":"2026-05-22T02:04:55Z"}],"graph_snapshots":[{"event_id":"sha256:6d6621046646b9615d99b22b0b20facccd830b8e30b9a9cea8c8df392c2fabb4","target":"graph","created_at":"2026-05-22T02:04:55Z","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/2605.22812/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 robot manipulation by unifying perception and action. However, existing VLA systems primarily rely on textual instructions and struggle to resolve spatial ambiguity in complex scenes with multiple similar objects. To address this limitation, we introduce gesture as a parallel instruction modality and propose a Gesture-aware Vision-Language-Action model (GesVLA). Our approach encodes gesture features directly into the latent space, enabling them to participate in both high-level reasoning and low-level action ge","authors_text":"Chuxi Xu, Erjin Zhou, Jianjiang Feng, Meng Zhang, Wenxuan Guo, Yichen Liu, Yimeng Dong, Yunfei Wei, Ze Chen, Ziyuan Li","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-21T17:57:44Z","title":"GesVLA: Gesture-Aware Vision-Language-Action Model Embedded Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22812","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":"sha256:520d9556a983a9fd9bd74c9a137f0d2baec3a8a36718ccaf92b4427ce5510a70","target":"record","created_at":"2026-05-22T02:04:55Z","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":"60f536441ee2f36951d856eda3d9922e3ba1aa3dce0e89fc6efc20d86f30c923","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-21T17:57:44Z","title_canon_sha256":"20cac9327927dba9e8b5336fd8e916c0dee22321cb0923f5ab46fd4d50f6c0b8"},"schema_version":"1.0","source":{"id":"2605.22812","kind":"arxiv","version":1}},"canonical_sha256":"45ce686bfe3b701b89b94b632164bedf051aaadd98079d3dbd9524bf5c200043","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45ce686bfe3b701b89b94b632164bedf051aaadd98079d3dbd9524bf5c200043","first_computed_at":"2026-05-22T02:04:55.895884Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T02:04:55.895884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PR++qVEzJ96ZemFgvENVxq7Zgw8+H+FQx7TaPjjykmhLAKAutDn2BaDfNviJHCtjX0AT+D8nGMhYbgVuXXYuDA==","signature_status":"signed_v1","signed_at":"2026-05-22T02:04:55.896565Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22812","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:520d9556a983a9fd9bd74c9a137f0d2baec3a8a36718ccaf92b4427ce5510a70","sha256:6d6621046646b9615d99b22b0b20facccd830b8e30b9a9cea8c8df392c2fabb4"],"state_sha256":"d298e902c40d4ded7ea109b65b27434af4915d314a1289a6274de613eef1ccff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P/HiSCT9DLXX9Cyx6MliategrOivVoa/78SXpp0l/i4FWwrAOVmCZmmK26/QyQoIVPTtOeGvF4QExVoDkzdzBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T08:05:18.093610Z","bundle_sha256":"8a8e6f3d6cb6714b24fb996a5a29626231698c0e8b6fe193a5c78ee41f1b10bd"}}