{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NNKI34S7SAK4R6JCDXLJPUEGAQ","short_pith_number":"pith:NNKI34S7","canonical_record":{"source":{"id":"2508.09071","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-12T16:46:05Z","cross_cats_sorted":[],"title_canon_sha256":"ed0c2e59b341d7c1376d3b6ee246fd57f70059abb62e7b39b1a20dfa4b299f60","abstract_canon_sha256":"c5b045bcfc9446b722fa7bf685d212b64776619496da368609b70c548f70189a"},"schema_version":"1.0"},"canonical_sha256":"6b548df25f9015c8f9221dd697d086040d511a872677bae3aab5d7d60ec28c23","source":{"kind":"arxiv","id":"2508.09071","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.09071","created_at":"2026-07-05T11:53:08Z"},{"alias_kind":"arxiv_version","alias_value":"2508.09071v2","created_at":"2026-07-05T11:53:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09071","created_at":"2026-07-05T11:53:08Z"},{"alias_kind":"pith_short_12","alias_value":"NNKI34S7SAK4","created_at":"2026-07-05T11:53:08Z"},{"alias_kind":"pith_short_16","alias_value":"NNKI34S7SAK4R6JC","created_at":"2026-07-05T11:53:08Z"},{"alias_kind":"pith_short_8","alias_value":"NNKI34S7","created_at":"2026-07-05T11:53:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NNKI34S7SAK4R6JCDXLJPUEGAQ","target":"record","payload":{"canonical_record":{"source":{"id":"2508.09071","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-12T16:46:05Z","cross_cats_sorted":[],"title_canon_sha256":"ed0c2e59b341d7c1376d3b6ee246fd57f70059abb62e7b39b1a20dfa4b299f60","abstract_canon_sha256":"c5b045bcfc9446b722fa7bf685d212b64776619496da368609b70c548f70189a"},"schema_version":"1.0"},"canonical_sha256":"6b548df25f9015c8f9221dd697d086040d511a872677bae3aab5d7d60ec28c23","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:08.566125Z","signature_b64":"a7QbT5Dm7DOzB+loq0bBaXEmsdWYYWUZBp5YzcnSY7S6w+RTbfcCBSsaaH8+/8QuGeeWvyRKsVG30FvuCaLOBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b548df25f9015c8f9221dd697d086040d511a872677bae3aab5d7d60ec28c23","last_reissued_at":"2026-07-05T11:53:08.565667Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:08.565667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.09071","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:53:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cg8Lp3LnjF6ok6z5ZikrM077DE27UyK+3pPaUgLL4yawcq0fkKLW1PYJZh8GDzc6BRMRVmkG0XzfE8+aN1BTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-28T20:40:30.817605Z"},"content_sha256":"bb56afadfea911d32ba47e27d598b6ade9d7f0b3d7a7030d319aa8a31ee34ca1","schema_version":"1.0","event_id":"sha256:bb56afadfea911d32ba47e27d598b6ade9d7f0b3d7a7030d319aa8a31ee34ca1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NNKI34S7SAK4R6JCDXLJPUEGAQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GeoVLA: Empowering 3D Representations in Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Bin Xie, Hao Shi, Jiale Cao, Lin Sun, Tiancai Wang, Yingfei Liu","submitted_at":"2025-08-12T16:46:05Z","abstract_excerpt":"Vision-Language-Action (VLA) models have emerged as a promising approach for enabling robots to follow language instructions and predict corresponding actions. However, current VLA models mainly rely on 2D visual inputs, neglecting the rich geometric information in the 3D physical world, which limits their spatial awareness and adaptability. In this paper, we present GeoVLA, a novel VLA framework that effectively integrates 3D information to advance robotic manipulation. It uses a vision-language model (VLM) to process images and language instructions,extracting fused vision-language embedding"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09071","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/2508.09071/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":"2026-07-05T11:53:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L5COy1HmDZfWvF2WPl/9EiWLHE5gols+cKCqDPqBQOxWj/z5NC/BSn4h4riQyQy+OQlvrGvRMbfvBm+c9oKjBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-28T20:40:30.817975Z"},"content_sha256":"5ca2534d9dac44a4ad6e99b0dbec7b423e80299853bb1be3716cd1f85348cc00","schema_version":"1.0","event_id":"sha256:5ca2534d9dac44a4ad6e99b0dbec7b423e80299853bb1be3716cd1f85348cc00"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NNKI34S7SAK4R6JCDXLJPUEGAQ/bundle.json","state_url":"https://pith.science/pith/NNKI34S7SAK4R6JCDXLJPUEGAQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NNKI34S7SAK4R6JCDXLJPUEGAQ/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":"2026-07-28T20:40:30Z","links":{"resolver":"https://pith.science/pith/NNKI34S7SAK4R6JCDXLJPUEGAQ","bundle":"https://pith.science/pith/NNKI34S7SAK4R6JCDXLJPUEGAQ/bundle.json","state":"https://pith.science/pith/NNKI34S7SAK4R6JCDXLJPUEGAQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NNKI34S7SAK4R6JCDXLJPUEGAQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NNKI34S7SAK4R6JCDXLJPUEGAQ","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":"c5b045bcfc9446b722fa7bf685d212b64776619496da368609b70c548f70189a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-12T16:46:05Z","title_canon_sha256":"ed0c2e59b341d7c1376d3b6ee246fd57f70059abb62e7b39b1a20dfa4b299f60"},"schema_version":"1.0","source":{"id":"2508.09071","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.09071","created_at":"2026-07-05T11:53:08Z"},{"alias_kind":"arxiv_version","alias_value":"2508.09071v2","created_at":"2026-07-05T11:53:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09071","created_at":"2026-07-05T11:53:08Z"},{"alias_kind":"pith_short_12","alias_value":"NNKI34S7SAK4","created_at":"2026-07-05T11:53:08Z"},{"alias_kind":"pith_short_16","alias_value":"NNKI34S7SAK4R6JC","created_at":"2026-07-05T11:53:08Z"},{"alias_kind":"pith_short_8","alias_value":"NNKI34S7","created_at":"2026-07-05T11:53:08Z"}],"graph_snapshots":[{"event_id":"sha256:5ca2534d9dac44a4ad6e99b0dbec7b423e80299853bb1be3716cd1f85348cc00","target":"graph","created_at":"2026-07-05T11:53:08Z","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/2508.09071/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) models have emerged as a promising approach for enabling robots to follow language instructions and predict corresponding actions. However, current VLA models mainly rely on 2D visual inputs, neglecting the rich geometric information in the 3D physical world, which limits their spatial awareness and adaptability. In this paper, we present GeoVLA, a novel VLA framework that effectively integrates 3D information to advance robotic manipulation. It uses a vision-language model (VLM) to process images and language instructions,extracting fused vision-language embedding","authors_text":"Bin Xie, Hao Shi, Jiale Cao, Lin Sun, Tiancai Wang, Yingfei Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-12T16:46:05Z","title":"GeoVLA: Empowering 3D Representations in Vision-Language-Action Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09071","kind":"arxiv","version":2},"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:bb56afadfea911d32ba47e27d598b6ade9d7f0b3d7a7030d319aa8a31ee34ca1","target":"record","created_at":"2026-07-05T11:53:08Z","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":"c5b045bcfc9446b722fa7bf685d212b64776619496da368609b70c548f70189a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-12T16:46:05Z","title_canon_sha256":"ed0c2e59b341d7c1376d3b6ee246fd57f70059abb62e7b39b1a20dfa4b299f60"},"schema_version":"1.0","source":{"id":"2508.09071","kind":"arxiv","version":2}},"canonical_sha256":"6b548df25f9015c8f9221dd697d086040d511a872677bae3aab5d7d60ec28c23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b548df25f9015c8f9221dd697d086040d511a872677bae3aab5d7d60ec28c23","first_computed_at":"2026-07-05T11:53:08.565667Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:08.565667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a7QbT5Dm7DOzB+loq0bBaXEmsdWYYWUZBp5YzcnSY7S6w+RTbfcCBSsaaH8+/8QuGeeWvyRKsVG30FvuCaLOBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:08.566125Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.09071","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb56afadfea911d32ba47e27d598b6ade9d7f0b3d7a7030d319aa8a31ee34ca1","sha256:5ca2534d9dac44a4ad6e99b0dbec7b423e80299853bb1be3716cd1f85348cc00"],"state_sha256":"db5802a74259f2156721e0acb497fd3058d7036ec5738d5cd4f81dcba18e4499"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2BNmym5YY+7yxtPyMr9SVfG88rlChODGhn5caPYr7LcNl7k8LUwVw9d06LXN8ZBEZY42l27uO0+Usfx1tgohBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-28T20:40:30.820677Z","bundle_sha256":"500e61853643a17a7d99e1378ebe3ff288548d063fe14cd33f81e783769a5341"}}