{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CFJUE25W7JNTPDM6YDJBK5FQAR","short_pith_number":"pith:CFJUE25W","canonical_record":{"source":{"id":"2411.05821","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-04T18:01:34Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"6f049699e2ddd50c46f23c937646594883852c4ba1526f48fadf5c445f0dff1e","abstract_canon_sha256":"401b11369c278685693f24ed5e563ab046dae83003d1ae625b1daa29232aaa6a"},"schema_version":"1.0"},"canonical_sha256":"1153426bb6fa5b378d9ec0d21574b004459fef7112521e7ab2c0316e4c75e623","source":{"kind":"arxiv","id":"2411.05821","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.05821","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"arxiv_version","alias_value":"2411.05821v2","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05821","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"pith_short_12","alias_value":"CFJUE25W7JNT","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"pith_short_16","alias_value":"CFJUE25W7JNTPDM6","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"pith_short_8","alias_value":"CFJUE25W","created_at":"2026-07-05T09:45:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CFJUE25W7JNTPDM6YDJBK5FQAR","target":"record","payload":{"canonical_record":{"source":{"id":"2411.05821","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-04T18:01:34Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"6f049699e2ddd50c46f23c937646594883852c4ba1526f48fadf5c445f0dff1e","abstract_canon_sha256":"401b11369c278685693f24ed5e563ab046dae83003d1ae625b1daa29232aaa6a"},"schema_version":"1.0"},"canonical_sha256":"1153426bb6fa5b378d9ec0d21574b004459fef7112521e7ab2c0316e4c75e623","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:57.532182Z","signature_b64":"4SDXcSnJ4mg3gLVcR8T5eYRLF2XUZb7rU0wIfhuLgRMJPEIfn+SwSIWRHI1ucYgN0DdI9XIIEedns0AzNKEAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1153426bb6fa5b378d9ec0d21574b004459fef7112521e7ab2c0316e4c75e623","last_reissued_at":"2026-07-05T09:45:57.531644Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:57.531644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.05821","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":"2026-07-05T09:45:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/H4WUMSMfhACrxBr6vwt8b8knuydqqW3jzuMMtoZo8UUf2bkr91ti41+/JtR4B0IuHpsInOImkgFoDlZJ/2lBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:44:24.807729Z"},"content_sha256":"da989dd13ac3b74d3837847793b99141833f70f6a4bfa0e680ffa698dc33e2c4","schema_version":"1.0","event_id":"sha256:da989dd13ac3b74d3837847793b99141833f70f6a4bfa0e680ffa698dc33e2c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CFJUE25W7JNTPDM6YDJBK5FQAR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking Vision, Language, & Action Models on Robotic Learning Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Harshvardhan Sikka, Jaewoo Song, Paul Pu Liang, Pranav Guruprasad, Yangyue Wang","submitted_at":"2024-11-04T18:01:34Z","abstract_excerpt":"Vision-language-action (VLA) models represent a promising direction for developing general-purpose robotic systems, demonstrating the ability to combine visual understanding, language comprehension, and action generation. However, systematic evaluation of these models across diverse robotic tasks remains limited. In this work, we present a comprehensive evaluation framework and benchmark suite for assessing VLA models. We profile three state-of-the-art VLM and VLAs - GPT-4o, OpenVLA, and JAT - across 20 diverse datasets from the Open-X-Embodiment collection, evaluating their performance on var"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05821","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/2411.05821/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":"2026-07-05T09:45:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VBpCe9bgHhvNllkcP6nKV5EQp0YneSokM81sQLkq5Y9sI/FwbOtV9UMEhsrpiX6yPqo2nMETZlohlo49dI/wAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:44:24.808593Z"},"content_sha256":"2ab4a3775d7bfbac469f8c980e764a6e69af8f5c1b75208d54718c6d5bee295a","schema_version":"1.0","event_id":"sha256:2ab4a3775d7bfbac469f8c980e764a6e69af8f5c1b75208d54718c6d5bee295a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CFJUE25W7JNTPDM6YDJBK5FQAR/bundle.json","state_url":"https://pith.science/pith/CFJUE25W7JNTPDM6YDJBK5FQAR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CFJUE25W7JNTPDM6YDJBK5FQAR/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":"2026-08-08T20:44:24Z","links":{"resolver":"https://pith.science/pith/CFJUE25W7JNTPDM6YDJBK5FQAR","bundle":"https://pith.science/pith/CFJUE25W7JNTPDM6YDJBK5FQAR/bundle.json","state":"https://pith.science/pith/CFJUE25W7JNTPDM6YDJBK5FQAR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CFJUE25W7JNTPDM6YDJBK5FQAR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CFJUE25W7JNTPDM6YDJBK5FQAR","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":"401b11369c278685693f24ed5e563ab046dae83003d1ae625b1daa29232aaa6a","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-04T18:01:34Z","title_canon_sha256":"6f049699e2ddd50c46f23c937646594883852c4ba1526f48fadf5c445f0dff1e"},"schema_version":"1.0","source":{"id":"2411.05821","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.05821","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"arxiv_version","alias_value":"2411.05821v2","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05821","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"pith_short_12","alias_value":"CFJUE25W7JNT","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"pith_short_16","alias_value":"CFJUE25W7JNTPDM6","created_at":"2026-07-05T09:45:57Z"},{"alias_kind":"pith_short_8","alias_value":"CFJUE25W","created_at":"2026-07-05T09:45:57Z"}],"graph_snapshots":[{"event_id":"sha256:2ab4a3775d7bfbac469f8c980e764a6e69af8f5c1b75208d54718c6d5bee295a","target":"graph","created_at":"2026-07-05T09:45:57Z","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/2411.05821/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language-action (VLA) models represent a promising direction for developing general-purpose robotic systems, demonstrating the ability to combine visual understanding, language comprehension, and action generation. However, systematic evaluation of these models across diverse robotic tasks remains limited. In this work, we present a comprehensive evaluation framework and benchmark suite for assessing VLA models. We profile three state-of-the-art VLM and VLAs - GPT-4o, OpenVLA, and JAT - across 20 diverse datasets from the Open-X-Embodiment collection, evaluating their performance on var","authors_text":"Harshvardhan Sikka, Jaewoo Song, Paul Pu Liang, Pranav Guruprasad, Yangyue Wang","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-04T18:01:34Z","title":"Benchmarking Vision, Language, & Action Models on Robotic Learning Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05821","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:da989dd13ac3b74d3837847793b99141833f70f6a4bfa0e680ffa698dc33e2c4","target":"record","created_at":"2026-07-05T09:45:57Z","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":"401b11369c278685693f24ed5e563ab046dae83003d1ae625b1daa29232aaa6a","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-04T18:01:34Z","title_canon_sha256":"6f049699e2ddd50c46f23c937646594883852c4ba1526f48fadf5c445f0dff1e"},"schema_version":"1.0","source":{"id":"2411.05821","kind":"arxiv","version":2}},"canonical_sha256":"1153426bb6fa5b378d9ec0d21574b004459fef7112521e7ab2c0316e4c75e623","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1153426bb6fa5b378d9ec0d21574b004459fef7112521e7ab2c0316e4c75e623","first_computed_at":"2026-07-05T09:45:57.531644Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:57.531644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4SDXcSnJ4mg3gLVcR8T5eYRLF2XUZb7rU0wIfhuLgRMJPEIfn+SwSIWRHI1ucYgN0DdI9XIIEedns0AzNKEAAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:57.532182Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.05821","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da989dd13ac3b74d3837847793b99141833f70f6a4bfa0e680ffa698dc33e2c4","sha256:2ab4a3775d7bfbac469f8c980e764a6e69af8f5c1b75208d54718c6d5bee295a"],"state_sha256":"f9a20802915612e52ca6361174c0d6f556c8e1a28710b491c588dcce7aae99ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nyc6BjvmhZz7dzTTIDIly3yrn7T00fQ+n3Qjpr19J+FynCtIJe1exR01HBli9VyakRkVIL05ipFNmyxN9PARDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:44:24.814439Z","bundle_sha256":"54ee5c856529d7f2328337291c1c08c089683ce3db2ae7b006ff7cbc9d99d54c"}}