{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NCTW6RIU764ZXYKH7TLJRXIONG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"862a7a44f986b9e65b326986c7831f5f9be098cb1cad72a03965895f16d46708","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T17:59:59Z","title_canon_sha256":"cc1f77c1633a2fcd9272e469908022f9403dd82e0d92c176f1be02f93399c6e4"},"schema_version":"1.0","source":{"id":"2410.07177","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.07177","created_at":"2026-07-05T10:48:20Z"},{"alias_kind":"arxiv_version","alias_value":"2410.07177v2","created_at":"2026-07-05T10:48:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07177","created_at":"2026-07-05T10:48:20Z"},{"alias_kind":"pith_short_12","alias_value":"NCTW6RIU764Z","created_at":"2026-07-05T10:48:20Z"},{"alias_kind":"pith_short_16","alias_value":"NCTW6RIU764ZXYKH","created_at":"2026-07-05T10:48:20Z"},{"alias_kind":"pith_short_8","alias_value":"NCTW6RIU","created_at":"2026-07-05T10:48:20Z"}],"graph_snapshots":[{"event_id":"sha256:fe04a1f649e96d8ec5470c9d6b730e1bac9ca2b78883eae1b8a4b67b206ecd97","target":"graph","created_at":"2026-07-05T10:48:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.07177/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T17:59:59Z","title":"MM-Ego: Towards Building Egocentric Multimodal LLMs for Video QA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07177","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:574441200ddb1f00bc661c2dcd96b0539900611b7c7706a8ec127fa4dc41a93f","target":"record","created_at":"2026-07-05T10:48:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"862a7a44f986b9e65b326986c7831f5f9be098cb1cad72a03965895f16d46708","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T17:59:59Z","title_canon_sha256":"cc1f77c1633a2fcd9272e469908022f9403dd82e0d92c176f1be02f93399c6e4"},"schema_version":"1.0","source":{"id":"2410.07177","kind":"arxiv","version":2}},"canonical_sha256":"68a76f4514ffb99be147fcd698dd0e69b014c9dd6e58adaa0d0d6a83dd1ae8af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68a76f4514ffb99be147fcd698dd0e69b014c9dd6e58adaa0d0d6a83dd1ae8af","first_computed_at":"2026-07-05T10:48:20.033965Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:20.033965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0GCRfaKseDU3SbbpBlx5LlJyiCbKcOzo87Kf8r6roKmhJv4ZQ6J36R6NKXRdR6veQf8Jn/ZESQM3VAsoWAHXBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:20.034442Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.07177","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:574441200ddb1f00bc661c2dcd96b0539900611b7c7706a8ec127fa4dc41a93f","sha256:fe04a1f649e96d8ec5470c9d6b730e1bac9ca2b78883eae1b8a4b67b206ecd97"],"state_sha256":"1b05717ddfbe70cbd90095801793ce185b76ab9821558dd46ed2132c0d285b1f"}