{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NCTW6RIU764ZXYKH7TLJRXIONG","short_pith_number":"pith:NCTW6RIU","schema_version":"1.0","canonical_sha256":"68a76f4514ffb99be147fcd698dd0e69b014c9dd6e58adaa0d0d6a83dd1ae8af","source":{"kind":"arxiv","id":"2410.07177","version":2},"attestation_state":"computed","paper":{"title":"MM-Ego: Towards Building Egocentric Multimodal LLMs for Video QA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bowen Zhang, Dan Xu, Erik Daxberger, Hanrong Ye, Haotian Zhang, Haoxuan You, Jiasen Lu, Lin Chen, Yanghao Li, Yinfei Yang, Zhe Gan, Zongyu Lin","submitted_at":"2024-10-09T17:59:59Z","abstract_excerpt":"This research aims to comprehensively explore building a multimodal foundation model for egocentric video understanding. To achieve this goal, we work on three fronts. First, as there is a lack of QA data for egocentric video understanding, we automatically generate 7M high-quality QA samples for egocentric videos ranging from 30 seconds to one hour long in Ego4D based on human-annotated data. This is one of the largest egocentric QA datasets. Second, we contribute a challenging egocentric QA benchmark with 629 videos and 7,026 questions to evaluate the models' ability in recognizing and memor"},"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":"2410.07177","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T17:59:59Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cc1f77c1633a2fcd9272e469908022f9403dd82e0d92c176f1be02f93399c6e4","abstract_canon_sha256":"862a7a44f986b9e65b326986c7831f5f9be098cb1cad72a03965895f16d46708"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:20.034442Z","signature_b64":"0GCRfaKseDU3SbbpBlx5LlJyiCbKcOzo87Kf8r6roKmhJv4ZQ6J36R6NKXRdR6veQf8Jn/ZESQM3VAsoWAHXBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68a76f4514ffb99be147fcd698dd0e69b014c9dd6e58adaa0d0d6a83dd1ae8af","last_reissued_at":"2026-07-05T10:48:20.033965Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:20.033965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MM-Ego: Towards Building Egocentric Multimodal LLMs for Video QA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bowen Zhang, Dan Xu, Erik Daxberger, Hanrong Ye, Haotian Zhang, Haoxuan You, Jiasen Lu, Lin Chen, Yanghao Li, Yinfei Yang, Zhe Gan, Zongyu Lin","submitted_at":"2024-10-09T17:59:59Z","abstract_excerpt":"This research aims to comprehensively explore building a multimodal foundation model for egocentric video understanding. To achieve this goal, we work on three fronts. First, as there is a lack of QA data for egocentric video understanding, we automatically generate 7M high-quality QA samples for egocentric videos ranging from 30 seconds to one hour long in Ego4D based on human-annotated data. This is one of the largest egocentric QA datasets. Second, we contribute a challenging egocentric QA benchmark with 629 videos and 7,026 questions to evaluate the models' ability in recognizing and memor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07177","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/2410.07177/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":"2410.07177","created_at":"2026-07-05T10:48:20.034019+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.07177v2","created_at":"2026-07-05T10:48:20.034019+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07177","created_at":"2026-07-05T10:48:20.034019+00:00"},{"alias_kind":"pith_short_12","alias_value":"NCTW6RIU764Z","created_at":"2026-07-05T10:48:20.034019+00:00"},{"alias_kind":"pith_short_16","alias_value":"NCTW6RIU764ZXYKH","created_at":"2026-07-05T10:48:20.034019+00:00"},{"alias_kind":"pith_short_8","alias_value":"NCTW6RIU","created_at":"2026-07-05T10:48:20.034019+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.14171","citing_title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17262","citing_title":"EgoIntrospect: An Egocentric Dataset and Benchmark for User-Centric Internal State Reasoning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18431","citing_title":"Seeing Together: Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2602.14122","citing_title":"EgoSound: Benchmarking Sound Understanding in Egocentric Videos","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04227","citing_title":"Pro$^2$Assist: Continuous Step-aware Proactive Assistance with Multi-modal Egocentric Perception for Long-horizon Procedural Tasks","ref_index":85,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NCTW6RIU764ZXYKH7TLJRXIONG","json":"https://pith.science/pith/NCTW6RIU764ZXYKH7TLJRXIONG.json","graph_json":"https://pith.science/api/pith-number/NCTW6RIU764ZXYKH7TLJRXIONG/graph.json","events_json":"https://pith.science/api/pith-number/NCTW6RIU764ZXYKH7TLJRXIONG/events.json","paper":"https://pith.science/paper/NCTW6RIU"},"agent_actions":{"view_html":"https://pith.science/pith/NCTW6RIU764ZXYKH7TLJRXIONG","download_json":"https://pith.science/pith/NCTW6RIU764ZXYKH7TLJRXIONG.json","view_paper":"https://pith.science/paper/NCTW6RIU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.07177&json=true","fetch_graph":"https://pith.science/api/pith-number/NCTW6RIU764ZXYKH7TLJRXIONG/graph.json","fetch_events":"https://pith.science/api/pith-number/NCTW6RIU764ZXYKH7TLJRXIONG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NCTW6RIU764ZXYKH7TLJRXIONG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NCTW6RIU764ZXYKH7TLJRXIONG/action/storage_attestation","attest_author":"https://pith.science/pith/NCTW6RIU764ZXYKH7TLJRXIONG/action/author_attestation","sign_citation":"https://pith.science/pith/NCTW6RIU764ZXYKH7TLJRXIONG/action/citation_signature","submit_replication":"https://pith.science/pith/NCTW6RIU764ZXYKH7TLJRXIONG/action/replication_record"}},"created_at":"2026-07-05T10:48:20.034019+00:00","updated_at":"2026-07-05T10:48:20.034019+00:00"}