{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Y6OARUHJAHC2BMRI3L7FMH6XN4","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":"382283743065a43d5e7581161c4dd34003c1531fb8904569058b969bc15137cb","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-27T07:27:52Z","title_canon_sha256":"ceb89476c7da5b6e67f46e5fbf6257e878ed7bbec2ec2c79aded240cae1ed52f"},"schema_version":"1.0","source":{"id":"2306.15255","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.15255","created_at":"2026-07-05T06:24:56Z"},{"alias_kind":"arxiv_version","alias_value":"2306.15255v1","created_at":"2026-07-05T06:24:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.15255","created_at":"2026-07-05T06:24:56Z"},{"alias_kind":"pith_short_12","alias_value":"Y6OARUHJAHC2","created_at":"2026-07-05T06:24:56Z"},{"alias_kind":"pith_short_16","alias_value":"Y6OARUHJAHC2BMRI","created_at":"2026-07-05T06:24:56Z"},{"alias_kind":"pith_short_8","alias_value":"Y6OARUHJ","created_at":"2026-07-05T06:24:56Z"}],"graph_snapshots":[{"event_id":"sha256:dba321f8cebcb90f38af674d415d6c62bc36759014e3c34508a7d36cb8419ec7","target":"graph","created_at":"2026-07-05T06:24:56Z","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/2306.15255/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this report, we present our champion solution for Ego4D Natural Language Queries (NLQ) Challenge in CVPR 2023. Essentially, to accurately ground in a video, an effective egocentric feature extractor and a powerful grounding model are required. Motivated by this, we leverage a two-stage pre-training strategy to train egocentric feature extractors and the grounding model on video narrations, and further fine-tune the model on annotated data. In addition, we introduce a novel grounding model GroundNLQ, which employs a multi-modal multi-scale grounding module for effective video and text fusion","authors_text":"Chao Li, Chong-Wah Ngo, Difei Gao, Kun Yan, Lei Ji, Mike Zheng Shou, Nan Duan, Wanjun Zhong, Wing-Kwong Chan, Zhijian Hou","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-27T07:27:52Z","title":"GroundNLQ @ Ego4D Natural Language Queries Challenge 2023"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.15255","kind":"arxiv","version":1},"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":"sha256:0436a168ae70923131eff36c7e3cf4617aaa7e62d1ca72cbcfa3b8e3131c6e78","target":"record","created_at":"2026-07-05T06:24:56Z","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":"382283743065a43d5e7581161c4dd34003c1531fb8904569058b969bc15137cb","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-27T07:27:52Z","title_canon_sha256":"ceb89476c7da5b6e67f46e5fbf6257e878ed7bbec2ec2c79aded240cae1ed52f"},"schema_version":"1.0","source":{"id":"2306.15255","kind":"arxiv","version":1}},"canonical_sha256":"c79c08d0e901c5a0b228dafe561fd76f34a5d72a3afbda72d5e3da650e3b6d63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c79c08d0e901c5a0b228dafe561fd76f34a5d72a3afbda72d5e3da650e3b6d63","first_computed_at":"2026-07-05T06:24:56.724286Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:24:56.724286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"beoKJ22ijTbq4peEP4/WcODlawVEeA4NvTEr/Dk1N173XhlfOuRIj3hoWgMmpSjnh9zsWs3CfocA8HBFn/F3Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:24:56.724822Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.15255","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0436a168ae70923131eff36c7e3cf4617aaa7e62d1ca72cbcfa3b8e3131c6e78","sha256:dba321f8cebcb90f38af674d415d6c62bc36759014e3c34508a7d36cb8419ec7"],"state_sha256":"61b1c35e22f9133a2a54276a3f799abbb0f429895b0451ec8ff886e8c777ca99"}