{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BEXM4ALHFUVUKJCZIGU2DRN33L","short_pith_number":"pith:BEXM4ALH","schema_version":"1.0","canonical_sha256":"092ece01672d2b45245941a9a1c5bbdadd8c3a289d9e7ec4e7de5be447f3589c","source":{"kind":"arxiv","id":"2505.05540","version":2},"attestation_state":"computed","paper":{"title":"Benchmarking Vision, Language, & Action Models in Procedurally Generated, Open Ended Action Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Harshvardhan Sikka, Paul Pu Liang, Pranav Guruprasad, Sudipta Chowdhury, Yangyue Wang","submitted_at":"2025-05-08T16:51:36Z","abstract_excerpt":"Vision-language-action (VLA) models represent an important step toward general-purpose robotic systems by integrating visual perception, language understanding, and action execution. However, systematic evaluation of these models, particularly their zero-shot generalization capabilities in procedurally out-of-distribution (OOD) environments, remains limited. In this paper, we introduce MultiNet v0.2, a comprehensive benchmark designed to evaluate and analyze the generalization performance of state-of-the-art VLMs and VLAs - including GPT-4o, GPT-4.1, OpenVLA, Pi0 Base, and Pi0 FAST - on divers"},"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":"2505.05540","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-08T16:51:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1cb381e0a605c63ebf947e733ca7d0a54368765cc63de575cd03979abe7536ca","abstract_canon_sha256":"196bcb802ba4278c9edc6f2b98442af3d25302f1d6de91a16c9f371b93e47692"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:39.899143Z","signature_b64":"EFMl9cNzVp27qX79FZRzw43oO7sg44GF+RFRsa4YTeX8VS0cK+sLeVBmPhAstnA1bUrOYx93c8ES0AGFTYMmBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"092ece01672d2b45245941a9a1c5bbdadd8c3a289d9e7ec4e7de5be447f3589c","last_reissued_at":"2026-07-05T11:22:39.898585Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:39.898585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Vision, Language, & Action Models in Procedurally Generated, Open Ended Action Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Harshvardhan Sikka, Paul Pu Liang, Pranav Guruprasad, Sudipta Chowdhury, Yangyue Wang","submitted_at":"2025-05-08T16:51:36Z","abstract_excerpt":"Vision-language-action (VLA) models represent an important step toward general-purpose robotic systems by integrating visual perception, language understanding, and action execution. However, systematic evaluation of these models, particularly their zero-shot generalization capabilities in procedurally out-of-distribution (OOD) environments, remains limited. In this paper, we introduce MultiNet v0.2, a comprehensive benchmark designed to evaluate and analyze the generalization performance of state-of-the-art VLMs and VLAs - including GPT-4o, GPT-4.1, OpenVLA, Pi0 Base, and Pi0 FAST - on divers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05540","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/2505.05540/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":"2505.05540","created_at":"2026-07-05T11:22:39.898642+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.05540v2","created_at":"2026-07-05T11:22:39.898642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05540","created_at":"2026-07-05T11:22:39.898642+00:00"},{"alias_kind":"pith_short_12","alias_value":"BEXM4ALHFUVU","created_at":"2026-07-05T11:22:39.898642+00:00"},{"alias_kind":"pith_short_16","alias_value":"BEXM4ALHFUVUKJCZ","created_at":"2026-07-05T11:22:39.898642+00:00"},{"alias_kind":"pith_short_8","alias_value":"BEXM4ALH","created_at":"2026-07-05T11:22:39.898642+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11223","citing_title":"Do Vision-Language-Models show human-like logical problem-solving capability in point and click puzzle games?","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2602.15922","citing_title":"World Action Models are Zero-shot Policies","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BEXM4ALHFUVUKJCZIGU2DRN33L","json":"https://pith.science/pith/BEXM4ALHFUVUKJCZIGU2DRN33L.json","graph_json":"https://pith.science/api/pith-number/BEXM4ALHFUVUKJCZIGU2DRN33L/graph.json","events_json":"https://pith.science/api/pith-number/BEXM4ALHFUVUKJCZIGU2DRN33L/events.json","paper":"https://pith.science/paper/BEXM4ALH"},"agent_actions":{"view_html":"https://pith.science/pith/BEXM4ALHFUVUKJCZIGU2DRN33L","download_json":"https://pith.science/pith/BEXM4ALHFUVUKJCZIGU2DRN33L.json","view_paper":"https://pith.science/paper/BEXM4ALH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.05540&json=true","fetch_graph":"https://pith.science/api/pith-number/BEXM4ALHFUVUKJCZIGU2DRN33L/graph.json","fetch_events":"https://pith.science/api/pith-number/BEXM4ALHFUVUKJCZIGU2DRN33L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BEXM4ALHFUVUKJCZIGU2DRN33L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BEXM4ALHFUVUKJCZIGU2DRN33L/action/storage_attestation","attest_author":"https://pith.science/pith/BEXM4ALHFUVUKJCZIGU2DRN33L/action/author_attestation","sign_citation":"https://pith.science/pith/BEXM4ALHFUVUKJCZIGU2DRN33L/action/citation_signature","submit_replication":"https://pith.science/pith/BEXM4ALHFUVUKJCZIGU2DRN33L/action/replication_record"}},"created_at":"2026-07-05T11:22:39.898642+00:00","updated_at":"2026-07-05T11:22:39.898642+00:00"}