{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FKW3DDS4SDHO3QSILIVH2UQ5EF","short_pith_number":"pith:FKW3DDS4","schema_version":"1.0","canonical_sha256":"2aadb18e5c90ceedc2485a2a7d521d2175bed08c1615a57f6dd546e76622610b","source":{"kind":"arxiv","id":"2605.20818","version":1},"attestation_state":"computed","paper":{"title":"OSGNet with MLLM Reranking @ Ego4D Episodic Memory Challenge 2026","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyu Zhang, Leigang Qu, Liqiang Nie, Meng Liu, Qiaohui Chu, Weili Guan, Xuemeng Song, Yisen Feng","submitted_at":"2026-05-20T07:14:11Z","abstract_excerpt":"In this report, we present our champion solutions for the Natural Language Queries and GoalStep tracks of the Ego4D Episodic Memory Challenge at CVPR 2026. Both tracks require accurately localizing temporal segments from long untrimmed egocentric videos. To address these tasks, we propose a reranking-based framework that effectively leverages the strong video-language reasoning capability of multimodal large language model (MLLM) while preserving the efficiency and candidate recall of conventional localization pipelines. Specifically, we first obtain a set of candidate segments from existing l"},"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":"2605.20818","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T07:14:11Z","cross_cats_sorted":[],"title_canon_sha256":"2e47abd0c82cd590209d1aac1ea4bd4ae6e8ec4be52f6eb79333500ab74866db","abstract_canon_sha256":"a77f0f119dfd938482926d0afd9c027bd8f63cc3d09eae661b9b3d6dbd352c2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:56.141356Z","signature_b64":"hMRIU7PlW8e3vZWNUoozQSgh5JLxwnsad2s74U7wNNv54e09OTSo8IxMo3c0Rla91hNNGkWUU8gl7qDtxLIODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2aadb18e5c90ceedc2485a2a7d521d2175bed08c1615a57f6dd546e76622610b","last_reissued_at":"2026-05-21T01:04:56.140637Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:56.140637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OSGNet with MLLM Reranking @ Ego4D Episodic Memory Challenge 2026","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyu Zhang, Leigang Qu, Liqiang Nie, Meng Liu, Qiaohui Chu, Weili Guan, Xuemeng Song, Yisen Feng","submitted_at":"2026-05-20T07:14:11Z","abstract_excerpt":"In this report, we present our champion solutions for the Natural Language Queries and GoalStep tracks of the Ego4D Episodic Memory Challenge at CVPR 2026. Both tracks require accurately localizing temporal segments from long untrimmed egocentric videos. To address these tasks, we propose a reranking-based framework that effectively leverages the strong video-language reasoning capability of multimodal large language model (MLLM) while preserving the efficiency and candidate recall of conventional localization pipelines. Specifically, we first obtain a set of candidate segments from existing l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20818","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/2605.20818/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":"2605.20818","created_at":"2026-05-21T01:04:56.140748+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20818v1","created_at":"2026-05-21T01:04:56.140748+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20818","created_at":"2026-05-21T01:04:56.140748+00:00"},{"alias_kind":"pith_short_12","alias_value":"FKW3DDS4SDHO","created_at":"2026-05-21T01:04:56.140748+00:00"},{"alias_kind":"pith_short_16","alias_value":"FKW3DDS4SDHO3QSI","created_at":"2026-05-21T01:04:56.140748+00:00"},{"alias_kind":"pith_short_8","alias_value":"FKW3DDS4","created_at":"2026-05-21T01:04:56.140748+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FKW3DDS4SDHO3QSILIVH2UQ5EF","json":"https://pith.science/pith/FKW3DDS4SDHO3QSILIVH2UQ5EF.json","graph_json":"https://pith.science/api/pith-number/FKW3DDS4SDHO3QSILIVH2UQ5EF/graph.json","events_json":"https://pith.science/api/pith-number/FKW3DDS4SDHO3QSILIVH2UQ5EF/events.json","paper":"https://pith.science/paper/FKW3DDS4"},"agent_actions":{"view_html":"https://pith.science/pith/FKW3DDS4SDHO3QSILIVH2UQ5EF","download_json":"https://pith.science/pith/FKW3DDS4SDHO3QSILIVH2UQ5EF.json","view_paper":"https://pith.science/paper/FKW3DDS4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20818&json=true","fetch_graph":"https://pith.science/api/pith-number/FKW3DDS4SDHO3QSILIVH2UQ5EF/graph.json","fetch_events":"https://pith.science/api/pith-number/FKW3DDS4SDHO3QSILIVH2UQ5EF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FKW3DDS4SDHO3QSILIVH2UQ5EF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FKW3DDS4SDHO3QSILIVH2UQ5EF/action/storage_attestation","attest_author":"https://pith.science/pith/FKW3DDS4SDHO3QSILIVH2UQ5EF/action/author_attestation","sign_citation":"https://pith.science/pith/FKW3DDS4SDHO3QSILIVH2UQ5EF/action/citation_signature","submit_replication":"https://pith.science/pith/FKW3DDS4SDHO3QSILIVH2UQ5EF/action/replication_record"}},"created_at":"2026-05-21T01:04:56.140748+00:00","updated_at":"2026-05-21T01:04:56.140748+00:00"}