{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AOCTNULYBRWKVQENRIIQUQD4HF","short_pith_number":"pith:AOCTNULY","schema_version":"1.0","canonical_sha256":"038536d1780c6caac08d8a110a407c3972ff836b8fab2c54d2a6894797fce6c6","source":{"kind":"arxiv","id":"2506.09172","version":2},"attestation_state":"computed","paper":{"title":"An Open-Source Software Toolkit & Benchmark Suite for the Evaluation and Adaptation of Multimodal Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Harshvardhan Sikka, Jaewoo Song, Pranav Guruprasad, Sudipta Chowdhury, Yangyue Wang","submitted_at":"2025-06-10T18:38:19Z","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"},"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":"2506.09172","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T18:38:19Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"214043295dad4debbf8de243eb972004558406a51a841c75b1514c2002783d3c","abstract_canon_sha256":"c4bd5b38f33aa6e29dd09169663cf52a62d22856954b87ab1a70480487937c67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:41.711749Z","signature_b64":"3SziKU5X6U0s8c6E3LYB2qOnKa+UblJcKwnbGC5pZOOAVI/H2OGk2t5odynSfG047C/N8Ms8mXzsTC4dH026Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"038536d1780c6caac08d8a110a407c3972ff836b8fab2c54d2a6894797fce6c6","last_reissued_at":"2026-07-05T11:22:41.711268Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:41.711268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Open-Source Software Toolkit & Benchmark Suite for the Evaluation and Adaptation of Multimodal Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Harshvardhan Sikka, Jaewoo Song, Pranav Guruprasad, Sudipta Chowdhury, Yangyue Wang","submitted_at":"2025-06-10T18:38:19Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09172","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/2506.09172/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":"2506.09172","created_at":"2026-07-05T11:22:41.711323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.09172v2","created_at":"2026-07-05T11:22:41.711323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09172","created_at":"2026-07-05T11:22:41.711323+00:00"},{"alias_kind":"pith_short_12","alias_value":"AOCTNULYBRWK","created_at":"2026-07-05T11:22:41.711323+00:00"},{"alias_kind":"pith_short_16","alias_value":"AOCTNULYBRWKVQEN","created_at":"2026-07-05T11:22:41.711323+00:00"},{"alias_kind":"pith_short_8","alias_value":"AOCTNULY","created_at":"2026-07-05T11:22:41.711323+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/AOCTNULYBRWKVQENRIIQUQD4HF","json":"https://pith.science/pith/AOCTNULYBRWKVQENRIIQUQD4HF.json","graph_json":"https://pith.science/api/pith-number/AOCTNULYBRWKVQENRIIQUQD4HF/graph.json","events_json":"https://pith.science/api/pith-number/AOCTNULYBRWKVQENRIIQUQD4HF/events.json","paper":"https://pith.science/paper/AOCTNULY"},"agent_actions":{"view_html":"https://pith.science/pith/AOCTNULYBRWKVQENRIIQUQD4HF","download_json":"https://pith.science/pith/AOCTNULYBRWKVQENRIIQUQD4HF.json","view_paper":"https://pith.science/paper/AOCTNULY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.09172&json=true","fetch_graph":"https://pith.science/api/pith-number/AOCTNULYBRWKVQENRIIQUQD4HF/graph.json","fetch_events":"https://pith.science/api/pith-number/AOCTNULYBRWKVQENRIIQUQD4HF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AOCTNULYBRWKVQENRIIQUQD4HF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AOCTNULYBRWKVQENRIIQUQD4HF/action/storage_attestation","attest_author":"https://pith.science/pith/AOCTNULYBRWKVQENRIIQUQD4HF/action/author_attestation","sign_citation":"https://pith.science/pith/AOCTNULYBRWKVQENRIIQUQD4HF/action/citation_signature","submit_replication":"https://pith.science/pith/AOCTNULYBRWKVQENRIIQUQD4HF/action/replication_record"}},"created_at":"2026-07-05T11:22:41.711323+00:00","updated_at":"2026-07-05T11:22:41.711323+00:00"}