{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AOCTNULYBRWKVQENRIIQUQD4HF","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":"c4bd5b38f33aa6e29dd09169663cf52a62d22856954b87ab1a70480487937c67","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T18:38:19Z","title_canon_sha256":"214043295dad4debbf8de243eb972004558406a51a841c75b1514c2002783d3c"},"schema_version":"1.0","source":{"id":"2506.09172","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.09172","created_at":"2026-07-05T11:22:41Z"},{"alias_kind":"arxiv_version","alias_value":"2506.09172v2","created_at":"2026-07-05T11:22:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09172","created_at":"2026-07-05T11:22:41Z"},{"alias_kind":"pith_short_12","alias_value":"AOCTNULYBRWK","created_at":"2026-07-05T11:22:41Z"},{"alias_kind":"pith_short_16","alias_value":"AOCTNULYBRWKVQEN","created_at":"2026-07-05T11:22:41Z"},{"alias_kind":"pith_short_8","alias_value":"AOCTNULY","created_at":"2026-07-05T11:22:41Z"}],"graph_snapshots":[{"event_id":"sha256:2bfd2bde46d72761b6696355e57a41f1cdf32e56f3912678e09c375844a1ec73","target":"graph","created_at":"2026-07-05T11:22:41Z","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/2506.09172/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent innovations in multimodal action models represent a promising direction for developing general-purpose agentic systems, combining visual understanding, language comprehension, and action generation. We introduce MultiNet - a novel, fully open-source benchmark and surrounding software ecosystem designed to rigorously evaluate and adapt models across vision, language, and action domains. We establish standardized evaluation protocols for assessing vision-language models (VLMs) and vision-language-action models (VLAs), and provide open source software to download relevant data, models, and","authors_text":"Harshvardhan Sikka, Jaewoo Song, Pranav Guruprasad, Sudipta Chowdhury, Yangyue Wang","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T18:38:19Z","title":"An Open-Source Software Toolkit & Benchmark Suite for the Evaluation and Adaptation of Multimodal Action Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09172","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":"sha256:495c851ba1eb7e4891068846ee297db07d5cbef5d77d8503f9ced2a247242b2a","target":"record","created_at":"2026-07-05T11:22:41Z","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":"c4bd5b38f33aa6e29dd09169663cf52a62d22856954b87ab1a70480487937c67","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T18:38:19Z","title_canon_sha256":"214043295dad4debbf8de243eb972004558406a51a841c75b1514c2002783d3c"},"schema_version":"1.0","source":{"id":"2506.09172","kind":"arxiv","version":2}},"canonical_sha256":"038536d1780c6caac08d8a110a407c3972ff836b8fab2c54d2a6894797fce6c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"038536d1780c6caac08d8a110a407c3972ff836b8fab2c54d2a6894797fce6c6","first_computed_at":"2026-07-05T11:22:41.711268Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:41.711268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3SziKU5X6U0s8c6E3LYB2qOnKa+UblJcKwnbGC5pZOOAVI/H2OGk2t5odynSfG047C/N8Ms8mXzsTC4dH026Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:41.711749Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.09172","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:495c851ba1eb7e4891068846ee297db07d5cbef5d77d8503f9ced2a247242b2a","sha256:2bfd2bde46d72761b6696355e57a41f1cdf32e56f3912678e09c375844a1ec73"],"state_sha256":"2c196b09b3676788c8256749325cbda181f9a1dabac6d46b121dce504b1d110a"}