{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K2YIASK5PV2OZPM5QKOF7JCUSQ","short_pith_number":"pith:K2YIASK5","schema_version":"1.0","canonical_sha256":"56b080495d7d74ecbd9d829c5fa45494082d88a34a50482c19d2a2cccfc7053a","source":{"kind":"arxiv","id":"2506.03710","version":1},"attestation_state":"computed","paper":{"title":"OSGNet @ Ego4D Episodic Memory Challenge 2025","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haoyu Zhang, Liqiang Nie, Meng Liu, Qiaohui Chu, Weili Guan, Yaowei Wang, Yisen Feng","submitted_at":"2025-06-04T08:41:42Z","abstract_excerpt":"In this report, we present our champion solutions for the three egocentric video localization tracks of the Ego4D Episodic Memory Challenge at CVPR 2025. All tracks require precise localization of the interval within an untrimmed egocentric video. Previous unified video localization approaches often rely on late fusion strategies, which tend to yield suboptimal results. To address this, we adopt an early fusion-based video localization model to tackle all three tasks, aiming to enhance localization accuracy. Ultimately, our method achieved first place in the Natural Language Queries, Goal Step"},"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":"2506.03710","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T08:41:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"25e9dde4051ac49a6f1d4876a570e91f736afa8f46e058961681f4e6975f2e23","abstract_canon_sha256":"3a1655c7b89c4f5d21cf5454305d156c7a91fa50f307b48d1b582cf93471c3a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:50.393863Z","signature_b64":"O7coC1SBCuNfZp6T0GejQB68Gc/3DC5TlY+ggjGlA+S93hp8zUHSFP49Vm+ttbOPsvLvSkvpp7xtAN4GQQAADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56b080495d7d74ecbd9d829c5fa45494082d88a34a50482c19d2a2cccfc7053a","last_reissued_at":"2026-07-05T11:15:50.393347Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:50.393347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OSGNet @ Ego4D Episodic Memory Challenge 2025","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haoyu Zhang, Liqiang Nie, Meng Liu, Qiaohui Chu, Weili Guan, Yaowei Wang, Yisen Feng","submitted_at":"2025-06-04T08:41:42Z","abstract_excerpt":"In this report, we present our champion solutions for the three egocentric video localization tracks of the Ego4D Episodic Memory Challenge at CVPR 2025. All tracks require precise localization of the interval within an untrimmed egocentric video. Previous unified video localization approaches often rely on late fusion strategies, which tend to yield suboptimal results. To address this, we adopt an early fusion-based video localization model to tackle all three tasks, aiming to enhance localization accuracy. Ultimately, our method achieved first place in the Natural Language Queries, Goal Step"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03710","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/2506.03710/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":"2506.03710","created_at":"2026-07-05T11:15:50.393406+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.03710v1","created_at":"2026-07-05T11:15:50.393406+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03710","created_at":"2026-07-05T11:15:50.393406+00:00"},{"alias_kind":"pith_short_12","alias_value":"K2YIASK5PV2O","created_at":"2026-07-05T11:15:50.393406+00:00"},{"alias_kind":"pith_short_16","alias_value":"K2YIASK5PV2OZPM5","created_at":"2026-07-05T11:15:50.393406+00:00"},{"alias_kind":"pith_short_8","alias_value":"K2YIASK5","created_at":"2026-07-05T11:15:50.393406+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31227","citing_title":"HiERO-StepG @ Ego4D Step Grounding Challenge: hierarchical activity understanding enables zero-shot step grounding","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20901","citing_title":"VISTA: Technical Report for the Ego4D Short-Term Object Interaction Anticipation at EgoVis 2026","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20904","citing_title":"JFAA: Technical Report for the EPIC-KITCHENS-100 Action Anticipation Challenge at EgoVis 2026","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20818","citing_title":"OSGNet with MLLM Reranking @ Ego4D Episodic Memory Challenge 2026","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18176","citing_title":"MARS: Technical Report for the CASTLE Challenge at EgoVis 2026","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K2YIASK5PV2OZPM5QKOF7JCUSQ","json":"https://pith.science/pith/K2YIASK5PV2OZPM5QKOF7JCUSQ.json","graph_json":"https://pith.science/api/pith-number/K2YIASK5PV2OZPM5QKOF7JCUSQ/graph.json","events_json":"https://pith.science/api/pith-number/K2YIASK5PV2OZPM5QKOF7JCUSQ/events.json","paper":"https://pith.science/paper/K2YIASK5"},"agent_actions":{"view_html":"https://pith.science/pith/K2YIASK5PV2OZPM5QKOF7JCUSQ","download_json":"https://pith.science/pith/K2YIASK5PV2OZPM5QKOF7JCUSQ.json","view_paper":"https://pith.science/paper/K2YIASK5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.03710&json=true","fetch_graph":"https://pith.science/api/pith-number/K2YIASK5PV2OZPM5QKOF7JCUSQ/graph.json","fetch_events":"https://pith.science/api/pith-number/K2YIASK5PV2OZPM5QKOF7JCUSQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K2YIASK5PV2OZPM5QKOF7JCUSQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K2YIASK5PV2OZPM5QKOF7JCUSQ/action/storage_attestation","attest_author":"https://pith.science/pith/K2YIASK5PV2OZPM5QKOF7JCUSQ/action/author_attestation","sign_citation":"https://pith.science/pith/K2YIASK5PV2OZPM5QKOF7JCUSQ/action/citation_signature","submit_replication":"https://pith.science/pith/K2YIASK5PV2OZPM5QKOF7JCUSQ/action/replication_record"}},"created_at":"2026-07-05T11:15:50.393406+00:00","updated_at":"2026-07-05T11:15:50.393406+00:00"}