{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DF5W2V6PZKKFD2YO3MSP2AJMUH","short_pith_number":"pith:DF5W2V6P","schema_version":"1.0","canonical_sha256":"197b6d57cfca9451eb0edb24fd012ca1d6a12e5a7c81e1d08c73e12efaa01a90","source":{"kind":"arxiv","id":"2410.11623","version":1},"attestation_state":"computed","paper":{"title":"VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bohao Li, Kechen Fang, Lei Han, Sicheng Zhou, Sijie Cheng, Tingguang Li, Yang Liu, Yangyang Yu, Ye Tian","submitted_at":"2024-10-15T14:08:53Z","abstract_excerpt":"Recent advancements in Multi-modal Large Language Models (MLLMs) have opened new avenues for applications in Embodied AI. Building on previous work, EgoThink, we introduce VidEgoThink, a comprehensive benchmark for evaluating egocentric video understanding capabilities. To bridge the gap between MLLMs and low-level control in Embodied AI, we design four key interrelated tasks: video question-answering, hierarchy planning, visual grounding and reward modeling. To minimize manual annotation costs, we develop an automatic data generation pipeline based on the Ego4D dataset, leveraging the prior k"},"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":"2410.11623","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-15T14:08:53Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"f25727954e723329cc4e88c02ffad0896fc2173460a35f093aa44846659bc4e4","abstract_canon_sha256":"bde36ed4f59f66f08fd4b0601d4ff9b9cd0efa4d0a6188a5ad91f27d70cc553e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:56.776277Z","signature_b64":"DyETEr9oU416b67X+yI4ttxMxr5T+MgM8CYmOPavFdnmLVx7SHLkup7BBZZmvmAwC0LMfUnJzLv9aBIg4HI0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"197b6d57cfca9451eb0edb24fd012ca1d6a12e5a7c81e1d08c73e12efaa01a90","last_reissued_at":"2026-07-05T09:20:56.775776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:56.775776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bohao Li, Kechen Fang, Lei Han, Sicheng Zhou, Sijie Cheng, Tingguang Li, Yang Liu, Yangyang Yu, Ye Tian","submitted_at":"2024-10-15T14:08:53Z","abstract_excerpt":"Recent advancements in Multi-modal Large Language Models (MLLMs) have opened new avenues for applications in Embodied AI. Building on previous work, EgoThink, we introduce VidEgoThink, a comprehensive benchmark for evaluating egocentric video understanding capabilities. To bridge the gap between MLLMs and low-level control in Embodied AI, we design four key interrelated tasks: video question-answering, hierarchy planning, visual grounding and reward modeling. To minimize manual annotation costs, we develop an automatic data generation pipeline based on the Ego4D dataset, leveraging the prior k"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11623","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/2410.11623/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":"2410.11623","created_at":"2026-07-05T09:20:56.775851+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11623v1","created_at":"2026-07-05T09:20:56.775851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11623","created_at":"2026-07-05T09:20:56.775851+00:00"},{"alias_kind":"pith_short_12","alias_value":"DF5W2V6PZKKF","created_at":"2026-07-05T09:20:56.775851+00:00"},{"alias_kind":"pith_short_16","alias_value":"DF5W2V6PZKKFD2YO","created_at":"2026-07-05T09:20:56.775851+00:00"},{"alias_kind":"pith_short_8","alias_value":"DF5W2V6P","created_at":"2026-07-05T09:20:56.775851+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09164","citing_title":"Efficient Spatial-Temporal Focal Adapter with SSM for Temporal Action Detection","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15823","citing_title":"Watching Movies Like a Human: Egocentric Emotion Understanding for Embodied Companions","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DF5W2V6PZKKFD2YO3MSP2AJMUH","json":"https://pith.science/pith/DF5W2V6PZKKFD2YO3MSP2AJMUH.json","graph_json":"https://pith.science/api/pith-number/DF5W2V6PZKKFD2YO3MSP2AJMUH/graph.json","events_json":"https://pith.science/api/pith-number/DF5W2V6PZKKFD2YO3MSP2AJMUH/events.json","paper":"https://pith.science/paper/DF5W2V6P"},"agent_actions":{"view_html":"https://pith.science/pith/DF5W2V6PZKKFD2YO3MSP2AJMUH","download_json":"https://pith.science/pith/DF5W2V6PZKKFD2YO3MSP2AJMUH.json","view_paper":"https://pith.science/paper/DF5W2V6P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11623&json=true","fetch_graph":"https://pith.science/api/pith-number/DF5W2V6PZKKFD2YO3MSP2AJMUH/graph.json","fetch_events":"https://pith.science/api/pith-number/DF5W2V6PZKKFD2YO3MSP2AJMUH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DF5W2V6PZKKFD2YO3MSP2AJMUH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DF5W2V6PZKKFD2YO3MSP2AJMUH/action/storage_attestation","attest_author":"https://pith.science/pith/DF5W2V6PZKKFD2YO3MSP2AJMUH/action/author_attestation","sign_citation":"https://pith.science/pith/DF5W2V6PZKKFD2YO3MSP2AJMUH/action/citation_signature","submit_replication":"https://pith.science/pith/DF5W2V6PZKKFD2YO3MSP2AJMUH/action/replication_record"}},"created_at":"2026-07-05T09:20:56.775851+00:00","updated_at":"2026-07-05T09:20:56.775851+00:00"}