{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SBRAKSJXMKHERCMNVCNPLYWYBZ","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":"fc87a4f96f9eb382c4bb4f83d057a505ee24a6bd19466cb946ad165aa109d688","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-17T09:51:51Z","title_canon_sha256":"423e234f030a449e4e7238da5e0dd989e94696172519bc9579d1f877bb9fa2f5"},"schema_version":"1.0","source":{"id":"2506.14356","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14356","created_at":"2026-07-05T11:22:53Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14356v1","created_at":"2026-07-05T11:22:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14356","created_at":"2026-07-05T11:22:53Z"},{"alias_kind":"pith_short_12","alias_value":"SBRAKSJXMKHE","created_at":"2026-07-05T11:22:53Z"},{"alias_kind":"pith_short_16","alias_value":"SBRAKSJXMKHERCMN","created_at":"2026-07-05T11:22:53Z"},{"alias_kind":"pith_short_8","alias_value":"SBRAKSJX","created_at":"2026-07-05T11:22:53Z"}],"graph_snapshots":[{"event_id":"sha256:8941f263d83521ad3a3723c8d6a24450bf0e83eed66395db009c000728386b99","target":"graph","created_at":"2026-07-05T11:22:53Z","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/2506.14356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Egocentric video-language understanding demands both high efficiency and accurate spatial-temporal modeling. Existing approaches face three key challenges: 1) Excessive pre-training cost arising from multi-stage pre-training pipelines, 2) Ineffective spatial-temporal encoding due to manually split 3D rotary positional embeddings that hinder feature interactions, and 3) Imprecise learning objectives in soft-label multi-instance retrieval, which neglect negative pair correlations. In this paper, we introduce EVA02-AT, a suite of EVA02-based video-language foundation models tailored to egocentric","authors_text":"Lap-Pui Chau, Xiaoqi Wang, Yi Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-17T09:51:51Z","title":"EVA02-AT: Egocentric Video-Language Understanding with Spatial-Temporal Rotary Positional Embeddings and Symmetric Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14356","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:bab70dbc3d9c5c8fa4905930f8d5e3da1b7ca4e705e08472753892acbc690c55","target":"record","created_at":"2026-07-05T11:22:53Z","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":"fc87a4f96f9eb382c4bb4f83d057a505ee24a6bd19466cb946ad165aa109d688","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-17T09:51:51Z","title_canon_sha256":"423e234f030a449e4e7238da5e0dd989e94696172519bc9579d1f877bb9fa2f5"},"schema_version":"1.0","source":{"id":"2506.14356","kind":"arxiv","version":1}},"canonical_sha256":"9062054937628e48898da89af5e2d80e67ceab2ad86ccf7f9d1eb7868c7fa615","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9062054937628e48898da89af5e2d80e67ceab2ad86ccf7f9d1eb7868c7fa615","first_computed_at":"2026-07-05T11:22:53.963643Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:53.963643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L+sm/Mw238zY6Y5WhrIS6aB926UbPrkHQWiI0q1wXkZsxRljRJ0VWjoMoxjBgqBQXyfVRWsB5GxE8PIVhup2Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:53.964024Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.14356","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bab70dbc3d9c5c8fa4905930f8d5e3da1b7ca4e705e08472753892acbc690c55","sha256:8941f263d83521ad3a3723c8d6a24450bf0e83eed66395db009c000728386b99"],"state_sha256":"2b83dcf03270e3c418fc8a19b137d94e8672ed42e5d8e3feecfacfdab7886f20"}