{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IPG6XWDGD4SMUXILZABMSZGNB5","short_pith_number":"pith:IPG6XWDG","schema_version":"1.0","canonical_sha256":"43cdebd8661f24ca5d0bc802c964cd0f41acde6adb2066e628e79eb0c3613175","source":{"kind":"arxiv","id":"2605.18734","version":1},"attestation_state":"computed","paper":{"title":"EgoExoMem: Cross-View Memory Reasoning over Synchronized Egocentric and Exocentric Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengzhi Wu, Di Wen, Jiaming Zhang, Junwei Zheng, Kailun Yang, Kunyu Peng, Rainer Stiefelhagen, Ruiping Liu, Shaofang Quan, Yufan Chen","submitted_at":"2026-05-18T17:54:55Z","abstract_excerpt":"Egocentric memory is widely used in embodied intelligence, but it may be insufficient for comprehensive spatial-temporal reasoning. Inspired by human recall from both field and observer perspectives, we introduce EgoExoMem, the first benchmark for cross-view memory reasoning over synchronized egocentric and exocentric videos. EgoExoMem contains $2.6K$ high-quality MCQs across eight temporal, spatial, and cross-view QA types. To support dual-view retrieval, we propose E$^2$-Select, a training-free frame selection method for synchronized ego-exo videos. It combines relevance-based budget allocat"},"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":"2605.18734","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T17:54:55Z","cross_cats_sorted":[],"title_canon_sha256":"611bca65488c43492d9ea48cc540c8eba926b71cd89511bbdea521b601adfa4c","abstract_canon_sha256":"bc4f0c00062c5db3bf60359a469d7a2ab5e519a5747c2592fa2f62b4124963c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:18.038264Z","signature_b64":"fvnmri91FaQQkJXDkADAKNHNK/X2leQeb21deam9TIol1xgwMz3fQ3v+JGuhO8y3F/WIvd3HucRvdtKqkHMDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43cdebd8661f24ca5d0bc802c964cd0f41acde6adb2066e628e79eb0c3613175","last_reissued_at":"2026-05-20T00:06:18.037668Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:18.037668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EgoExoMem: Cross-View Memory Reasoning over Synchronized Egocentric and Exocentric Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengzhi Wu, Di Wen, Jiaming Zhang, Junwei Zheng, Kailun Yang, Kunyu Peng, Rainer Stiefelhagen, Ruiping Liu, Shaofang Quan, Yufan Chen","submitted_at":"2026-05-18T17:54:55Z","abstract_excerpt":"Egocentric memory is widely used in embodied intelligence, but it may be insufficient for comprehensive spatial-temporal reasoning. Inspired by human recall from both field and observer perspectives, we introduce EgoExoMem, the first benchmark for cross-view memory reasoning over synchronized egocentric and exocentric videos. EgoExoMem contains $2.6K$ high-quality MCQs across eight temporal, spatial, and cross-view QA types. To support dual-view retrieval, we propose E$^2$-Select, a training-free frame selection method for synchronized ego-exo videos. It combines relevance-based budget allocat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18734","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/2605.18734/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.013511Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"4a81654a91065ff00eedc06a738bef16d27376c843890cd48291c6bfeb3b3335"},"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":"2605.18734","created_at":"2026-05-20T00:06:18.037755+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18734v1","created_at":"2026-05-20T00:06:18.037755+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18734","created_at":"2026-05-20T00:06:18.037755+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPG6XWDGD4SM","created_at":"2026-05-20T00:06:18.037755+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPG6XWDGD4SMUXIL","created_at":"2026-05-20T00:06:18.037755+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPG6XWDG","created_at":"2026-05-20T00:06:18.037755+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/IPG6XWDGD4SMUXILZABMSZGNB5","json":"https://pith.science/pith/IPG6XWDGD4SMUXILZABMSZGNB5.json","graph_json":"https://pith.science/api/pith-number/IPG6XWDGD4SMUXILZABMSZGNB5/graph.json","events_json":"https://pith.science/api/pith-number/IPG6XWDGD4SMUXILZABMSZGNB5/events.json","paper":"https://pith.science/paper/IPG6XWDG"},"agent_actions":{"view_html":"https://pith.science/pith/IPG6XWDGD4SMUXILZABMSZGNB5","download_json":"https://pith.science/pith/IPG6XWDGD4SMUXILZABMSZGNB5.json","view_paper":"https://pith.science/paper/IPG6XWDG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18734&json=true","fetch_graph":"https://pith.science/api/pith-number/IPG6XWDGD4SMUXILZABMSZGNB5/graph.json","fetch_events":"https://pith.science/api/pith-number/IPG6XWDGD4SMUXILZABMSZGNB5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPG6XWDGD4SMUXILZABMSZGNB5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPG6XWDGD4SMUXILZABMSZGNB5/action/storage_attestation","attest_author":"https://pith.science/pith/IPG6XWDGD4SMUXILZABMSZGNB5/action/author_attestation","sign_citation":"https://pith.science/pith/IPG6XWDGD4SMUXILZABMSZGNB5/action/citation_signature","submit_replication":"https://pith.science/pith/IPG6XWDGD4SMUXILZABMSZGNB5/action/replication_record"}},"created_at":"2026-05-20T00:06:18.037755+00:00","updated_at":"2026-05-20T00:06:18.037755+00:00"}