{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NWNHH7EEEV26AFRHJNJUO6EIBQ","short_pith_number":"pith:NWNHH7EE","schema_version":"1.0","canonical_sha256":"6d9a73fc842575e016274b534778880c0191e8cfda2306f251b52314ce24c2b8","source":{"kind":"arxiv","id":"2404.09992","version":2},"attestation_state":"computed","paper":{"title":"MMInA: Benchmarking Multihop Multimodal Internet Agents","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Liangyu Chen, Shulin Tian, Ziniu Zhang, Ziwei Liu","submitted_at":"2024-04-15T17:59:50Z","abstract_excerpt":"Autonomous embodied agents live on an Internet of multimedia websites. Can they hop around multimodal websites to complete complex user tasks? Existing benchmarks fail to assess them in a realistic, evolving environment for their embodiment across websites. To answer this question, we present MMInA, a multihop and multimodal benchmark to evaluate the embodied agents for compositional Internet tasks, with several appealing properties: 1) Evolving real-world multimodal websites. Our benchmark uniquely operates on evolving real-world websites, ensuring a high degree of realism and applicability t"},"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":"2404.09992","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T17:59:50Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"df149e6e6fe58477b2b17545fca9d3ce8878fe58844c1e2b0941e7197d14f982","abstract_canon_sha256":"55ebdb859d180ac3c37df453ef08b028be93e1b5eb957937bbba392575ba4ec5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:58.735031Z","signature_b64":"PxFv84eFWRythocoAmo6iUE+zYrfYV8FYTNp2SOVwM2l6S/UMu/132Q5H8EoHbO5/xmqzVLC1rYFDpXEflfUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d9a73fc842575e016274b534778880c0191e8cfda2306f251b52314ce24c2b8","last_reissued_at":"2026-07-05T11:28:58.734379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:58.734379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMInA: Benchmarking Multihop Multimodal Internet Agents","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Liangyu Chen, Shulin Tian, Ziniu Zhang, Ziwei Liu","submitted_at":"2024-04-15T17:59:50Z","abstract_excerpt":"Autonomous embodied agents live on an Internet of multimedia websites. Can they hop around multimodal websites to complete complex user tasks? Existing benchmarks fail to assess them in a realistic, evolving environment for their embodiment across websites. To answer this question, we present MMInA, a multihop and multimodal benchmark to evaluate the embodied agents for compositional Internet tasks, with several appealing properties: 1) Evolving real-world multimodal websites. Our benchmark uniquely operates on evolving real-world websites, ensuring a high degree of realism and applicability t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09992","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/2404.09992/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":"2404.09992","created_at":"2026-07-05T11:28:58.734490+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.09992v2","created_at":"2026-07-05T11:28:58.734490+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09992","created_at":"2026-07-05T11:28:58.734490+00:00"},{"alias_kind":"pith_short_12","alias_value":"NWNHH7EEEV26","created_at":"2026-07-05T11:28:58.734490+00:00"},{"alias_kind":"pith_short_16","alias_value":"NWNHH7EEEV26AFRH","created_at":"2026-07-05T11:28:58.734490+00:00"},{"alias_kind":"pith_short_8","alias_value":"NWNHH7EE","created_at":"2026-07-05T11:28:58.734490+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.16416","citing_title":"Survey on Evaluation of LLM-based Agents","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2405.14573","citing_title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17475","citing_title":"Waking Up Blind: Cold-Start Optimization of Supervision-Free Agentic Trajectories for Grounded Visual Perception","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NWNHH7EEEV26AFRHJNJUO6EIBQ","json":"https://pith.science/pith/NWNHH7EEEV26AFRHJNJUO6EIBQ.json","graph_json":"https://pith.science/api/pith-number/NWNHH7EEEV26AFRHJNJUO6EIBQ/graph.json","events_json":"https://pith.science/api/pith-number/NWNHH7EEEV26AFRHJNJUO6EIBQ/events.json","paper":"https://pith.science/paper/NWNHH7EE"},"agent_actions":{"view_html":"https://pith.science/pith/NWNHH7EEEV26AFRHJNJUO6EIBQ","download_json":"https://pith.science/pith/NWNHH7EEEV26AFRHJNJUO6EIBQ.json","view_paper":"https://pith.science/paper/NWNHH7EE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.09992&json=true","fetch_graph":"https://pith.science/api/pith-number/NWNHH7EEEV26AFRHJNJUO6EIBQ/graph.json","fetch_events":"https://pith.science/api/pith-number/NWNHH7EEEV26AFRHJNJUO6EIBQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NWNHH7EEEV26AFRHJNJUO6EIBQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NWNHH7EEEV26AFRHJNJUO6EIBQ/action/storage_attestation","attest_author":"https://pith.science/pith/NWNHH7EEEV26AFRHJNJUO6EIBQ/action/author_attestation","sign_citation":"https://pith.science/pith/NWNHH7EEEV26AFRHJNJUO6EIBQ/action/citation_signature","submit_replication":"https://pith.science/pith/NWNHH7EEEV26AFRHJNJUO6EIBQ/action/replication_record"}},"created_at":"2026-07-05T11:28:58.734490+00:00","updated_at":"2026-07-05T11:28:58.734490+00:00"}