{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MKXB7KNHCLTLTYQM56RAOBVYC5","short_pith_number":"pith:MKXB7KNH","schema_version":"1.0","canonical_sha256":"62ae1fa9a712e6b9e20cefa20706b8175a48eab180a0570ef8cd0dc488af1812","source":{"kind":"arxiv","id":"2605.27759","version":1},"attestation_state":"computed","paper":{"title":"Colosseum V2: Benchmarking Generalization for Vision Language Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alina Du, Ashvin Arora, Gaurav Sukhatme, Hyeonho Oh, Ishika Singh, Jeremy Morgan, Jesse Thomason, Jincen Song, Prajwal Vijay","submitted_at":"2026-05-26T23:17:39Z","abstract_excerpt":"Vision-Language-Action (VLA) models demonstrate promising generalization in robotic manipulation, driven by advances in large-scale vision and language pre-training. This progress can be misleading. Despite the zero-shot perception and language capabilities of VLAs, their overall task performance often degrades under distribution shifts, revealing gaps in how these systems translate high-level understanding into robust behavior. To systematically study this gap, we introduce Colosseum V2, a large-scale simulation benchmark for evaluating VLA generalization in robot learning across diverse cond"},"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":"2605.27759","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-26T23:17:39Z","cross_cats_sorted":[],"title_canon_sha256":"7a1979d59fcb14d7154b98e5cd8ec39eae4bc1036ef6dc2f8297dd6d1776a0f3","abstract_canon_sha256":"22e619d8f30f1250f14cc3894c890885e9adc55dbc799dcaa8a1a86cef2a4590"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:48.139369Z","signature_b64":"rbF37YjrXWyr5Iy5eQmKsrRwAbyyVF4C1HOW2JW1C6bi9ERgTRFzAwLCybjrTJDpDyJfaaVKOeXaqhApiS95CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62ae1fa9a712e6b9e20cefa20706b8175a48eab180a0570ef8cd0dc488af1812","last_reissued_at":"2026-05-28T01:04:48.138944Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:48.138944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Colosseum V2: Benchmarking Generalization for Vision Language Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alina Du, Ashvin Arora, Gaurav Sukhatme, Hyeonho Oh, Ishika Singh, Jeremy Morgan, Jesse Thomason, Jincen Song, Prajwal Vijay","submitted_at":"2026-05-26T23:17:39Z","abstract_excerpt":"Vision-Language-Action (VLA) models demonstrate promising generalization in robotic manipulation, driven by advances in large-scale vision and language pre-training. This progress can be misleading. Despite the zero-shot perception and language capabilities of VLAs, their overall task performance often degrades under distribution shifts, revealing gaps in how these systems translate high-level understanding into robust behavior. To systematically study this gap, we introduce Colosseum V2, a large-scale simulation benchmark for evaluating VLA generalization in robot learning across diverse cond"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27759","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/2605.27759/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.27759","created_at":"2026-05-28T01:04:48.139002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27759v1","created_at":"2026-05-28T01:04:48.139002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27759","created_at":"2026-05-28T01:04:48.139002+00:00"},{"alias_kind":"pith_short_12","alias_value":"MKXB7KNHCLTL","created_at":"2026-05-28T01:04:48.139002+00:00"},{"alias_kind":"pith_short_16","alias_value":"MKXB7KNHCLTLTYQM","created_at":"2026-05-28T01:04:48.139002+00:00"},{"alias_kind":"pith_short_8","alias_value":"MKXB7KNH","created_at":"2026-05-28T01:04:48.139002+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MKXB7KNHCLTLTYQM56RAOBVYC5","json":"https://pith.science/pith/MKXB7KNHCLTLTYQM56RAOBVYC5.json","graph_json":"https://pith.science/api/pith-number/MKXB7KNHCLTLTYQM56RAOBVYC5/graph.json","events_json":"https://pith.science/api/pith-number/MKXB7KNHCLTLTYQM56RAOBVYC5/events.json","paper":"https://pith.science/paper/MKXB7KNH"},"agent_actions":{"view_html":"https://pith.science/pith/MKXB7KNHCLTLTYQM56RAOBVYC5","download_json":"https://pith.science/pith/MKXB7KNHCLTLTYQM56RAOBVYC5.json","view_paper":"https://pith.science/paper/MKXB7KNH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27759&json=true","fetch_graph":"https://pith.science/api/pith-number/MKXB7KNHCLTLTYQM56RAOBVYC5/graph.json","fetch_events":"https://pith.science/api/pith-number/MKXB7KNHCLTLTYQM56RAOBVYC5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MKXB7KNHCLTLTYQM56RAOBVYC5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MKXB7KNHCLTLTYQM56RAOBVYC5/action/storage_attestation","attest_author":"https://pith.science/pith/MKXB7KNHCLTLTYQM56RAOBVYC5/action/author_attestation","sign_citation":"https://pith.science/pith/MKXB7KNHCLTLTYQM56RAOBVYC5/action/citation_signature","submit_replication":"https://pith.science/pith/MKXB7KNHCLTLTYQM56RAOBVYC5/action/replication_record"}},"created_at":"2026-05-28T01:04:48.139002+00:00","updated_at":"2026-05-28T01:04:48.139002+00:00"}