{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2KDKCC2YYYWNN376CLCPWPIABN","short_pith_number":"pith:2KDKCC2Y","schema_version":"1.0","canonical_sha256":"d286a10b58c62cd6effe12c4fb3d000b788f9358aa98a5dbff5925bd4787f577","source":{"kind":"arxiv","id":"2605.27820","version":1},"attestation_state":"computed","paper":{"title":"EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jian Liu, Tong Niu, Weiqiang Wang, Yunqi Liu, Yuqi Qing, Zhenlong Dai, Zitong Wang","submitted_at":"2026-05-27T01:28:15Z","abstract_excerpt":"As AI agents increasingly operate in open, real-world environments, they require a deep synergy of multimodal perception, tool invocation with multi-hop reasoning, and dynamic interaction with users. However, existing benchmarks fail to jointly evaluate these capabilities due to challenges in designing strictly coupled multi-capability tasks, simulating natural and task-constrained user feedback, and ensuring objective evaluation of dynamic interaction. To bridge this gap, we introduce EgoBench, the first interactive multimodal benchmark for tool-using agents. EgoBench comprises 1,045 egocentr"},"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":"2605.27820","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T01:28:15Z","cross_cats_sorted":[],"title_canon_sha256":"bb247eeadbc085224d00ae90e1465b57b96694e9c513679c8a0e7859ca215265","abstract_canon_sha256":"26b27219e7a7484c7ccc7bd2b7249ef6734f4035a2c08590f6daf56d48d726a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:49.526635Z","signature_b64":"G0q16OmA+KkGNPL0b1sDEMzYhHXlD0z9bqKWPNqczcZXNgO8mK2dVE38zDHS2/9ezyvZ9+UU4JCZmhEWufLGAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d286a10b58c62cd6effe12c4fb3d000b788f9358aa98a5dbff5925bd4787f577","last_reissued_at":"2026-05-28T01:04:49.526175Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:49.526175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jian Liu, Tong Niu, Weiqiang Wang, Yunqi Liu, Yuqi Qing, Zhenlong Dai, Zitong Wang","submitted_at":"2026-05-27T01:28:15Z","abstract_excerpt":"As AI agents increasingly operate in open, real-world environments, they require a deep synergy of multimodal perception, tool invocation with multi-hop reasoning, and dynamic interaction with users. However, existing benchmarks fail to jointly evaluate these capabilities due to challenges in designing strictly coupled multi-capability tasks, simulating natural and task-constrained user feedback, and ensuring objective evaluation of dynamic interaction. To bridge this gap, we introduce EgoBench, the first interactive multimodal benchmark for tool-using agents. EgoBench comprises 1,045 egocentr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27820","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/2605.27820/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":"2605.27820","created_at":"2026-05-28T01:04:49.526248+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27820v1","created_at":"2026-05-28T01:04:49.526248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27820","created_at":"2026-05-28T01:04:49.526248+00:00"},{"alias_kind":"pith_short_12","alias_value":"2KDKCC2YYYWN","created_at":"2026-05-28T01:04:49.526248+00:00"},{"alias_kind":"pith_short_16","alias_value":"2KDKCC2YYYWNN376","created_at":"2026-05-28T01:04:49.526248+00:00"},{"alias_kind":"pith_short_8","alias_value":"2KDKCC2Y","created_at":"2026-05-28T01:04:49.526248+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/2KDKCC2YYYWNN376CLCPWPIABN","json":"https://pith.science/pith/2KDKCC2YYYWNN376CLCPWPIABN.json","graph_json":"https://pith.science/api/pith-number/2KDKCC2YYYWNN376CLCPWPIABN/graph.json","events_json":"https://pith.science/api/pith-number/2KDKCC2YYYWNN376CLCPWPIABN/events.json","paper":"https://pith.science/paper/2KDKCC2Y"},"agent_actions":{"view_html":"https://pith.science/pith/2KDKCC2YYYWNN376CLCPWPIABN","download_json":"https://pith.science/pith/2KDKCC2YYYWNN376CLCPWPIABN.json","view_paper":"https://pith.science/paper/2KDKCC2Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27820&json=true","fetch_graph":"https://pith.science/api/pith-number/2KDKCC2YYYWNN376CLCPWPIABN/graph.json","fetch_events":"https://pith.science/api/pith-number/2KDKCC2YYYWNN376CLCPWPIABN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2KDKCC2YYYWNN376CLCPWPIABN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2KDKCC2YYYWNN376CLCPWPIABN/action/storage_attestation","attest_author":"https://pith.science/pith/2KDKCC2YYYWNN376CLCPWPIABN/action/author_attestation","sign_citation":"https://pith.science/pith/2KDKCC2YYYWNN376CLCPWPIABN/action/citation_signature","submit_replication":"https://pith.science/pith/2KDKCC2YYYWNN376CLCPWPIABN/action/replication_record"}},"created_at":"2026-05-28T01:04:49.526248+00:00","updated_at":"2026-05-28T01:04:49.526248+00:00"}