{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F4MOSKZ3EAD7CV76EHH53WATPX","short_pith_number":"pith:F4MOSKZ3","schema_version":"1.0","canonical_sha256":"2f18e92b3b2007f157fe21cfddd8137dcdd92cd841055db82cacd0cfb7051774","source":{"kind":"arxiv","id":"2508.04681","version":1},"attestation_state":"computed","paper":{"title":"Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengqun Yang, Congsheng Xu, Fei Xu, Jie Qin, Liang Xu, Wenjun Zeng, Xiaokang Yang, Xingdong Sheng, Xin Jin, Yichao Yan, Yifan Liu, Yiyi Zhang, Yunhui Liu, Zili Lin","submitted_at":"2025-08-06T17:46:23Z","abstract_excerpt":"Learning action models from real-world human-centric interaction datasets is important towards building general-purpose intelligent assistants with efficiency. However, most existing datasets only offer specialist interaction category and ignore that AI assistants perceive and act based on first-person acquisition. We urge that both the generalist interaction knowledge and egocentric modality are indispensable. In this paper, we embed the manual-assisted task into a vision-language-action framework, where the assistant provides services to the instructor following egocentric vision and command"},"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":"2508.04681","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-06T17:46:23Z","cross_cats_sorted":[],"title_canon_sha256":"22aba78762ab1a06dd62e2501684c4d9d59ed61e489060fe8ff54a50c7342e52","abstract_canon_sha256":"e0ef2c47fa6bd88415d3673d711a03d99a82e028c7b77b94f97508651000ac1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:41.708579Z","signature_b64":"W9sATRs/nGNEWUvuo5z1xdk1tjwV0H2+ujf5Iq7xHCWX2wHcKFwaH7WGQx4uV/+7APALBQsFG432M2r0NqcWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f18e92b3b2007f157fe21cfddd8137dcdd92cd841055db82cacd0cfb7051774","last_reissued_at":"2026-07-05T11:49:41.708050Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:41.708050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengqun Yang, Congsheng Xu, Fei Xu, Jie Qin, Liang Xu, Wenjun Zeng, Xiaokang Yang, Xingdong Sheng, Xin Jin, Yichao Yan, Yifan Liu, Yiyi Zhang, Yunhui Liu, Zili Lin","submitted_at":"2025-08-06T17:46:23Z","abstract_excerpt":"Learning action models from real-world human-centric interaction datasets is important towards building general-purpose intelligent assistants with efficiency. However, most existing datasets only offer specialist interaction category and ignore that AI assistants perceive and act based on first-person acquisition. We urge that both the generalist interaction knowledge and egocentric modality are indispensable. In this paper, we embed the manual-assisted task into a vision-language-action framework, where the assistant provides services to the instructor following egocentric vision and command"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04681","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/2508.04681/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":"2508.04681","created_at":"2026-07-05T11:49:41.708117+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.04681v1","created_at":"2026-07-05T11:49:41.708117+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04681","created_at":"2026-07-05T11:49:41.708117+00:00"},{"alias_kind":"pith_short_12","alias_value":"F4MOSKZ3EAD7","created_at":"2026-07-05T11:49:41.708117+00:00"},{"alias_kind":"pith_short_16","alias_value":"F4MOSKZ3EAD7CV76","created_at":"2026-07-05T11:49:41.708117+00:00"},{"alias_kind":"pith_short_8","alias_value":"F4MOSKZ3","created_at":"2026-07-05T11:49:41.708117+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28604","citing_title":"IMU-HOI: A Symbiotic Framework for Coherent Human-Object Interaction and Motion Capture via Contact-Conscious Inertial Fusion","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F4MOSKZ3EAD7CV76EHH53WATPX","json":"https://pith.science/pith/F4MOSKZ3EAD7CV76EHH53WATPX.json","graph_json":"https://pith.science/api/pith-number/F4MOSKZ3EAD7CV76EHH53WATPX/graph.json","events_json":"https://pith.science/api/pith-number/F4MOSKZ3EAD7CV76EHH53WATPX/events.json","paper":"https://pith.science/paper/F4MOSKZ3"},"agent_actions":{"view_html":"https://pith.science/pith/F4MOSKZ3EAD7CV76EHH53WATPX","download_json":"https://pith.science/pith/F4MOSKZ3EAD7CV76EHH53WATPX.json","view_paper":"https://pith.science/paper/F4MOSKZ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.04681&json=true","fetch_graph":"https://pith.science/api/pith-number/F4MOSKZ3EAD7CV76EHH53WATPX/graph.json","fetch_events":"https://pith.science/api/pith-number/F4MOSKZ3EAD7CV76EHH53WATPX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F4MOSKZ3EAD7CV76EHH53WATPX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F4MOSKZ3EAD7CV76EHH53WATPX/action/storage_attestation","attest_author":"https://pith.science/pith/F4MOSKZ3EAD7CV76EHH53WATPX/action/author_attestation","sign_citation":"https://pith.science/pith/F4MOSKZ3EAD7CV76EHH53WATPX/action/citation_signature","submit_replication":"https://pith.science/pith/F4MOSKZ3EAD7CV76EHH53WATPX/action/replication_record"}},"created_at":"2026-07-05T11:49:41.708117+00:00","updated_at":"2026-07-05T11:49:41.708117+00:00"}