{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XMAC7HKD3RWAY4QLDIJIVRUIPW","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":"656ed1a9073df99dec624c4a2ebac031c6d123bc1837085a3a350fad6283c751","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-02T10:29:35Z","title_canon_sha256":"4d390ec9e38fd647d362a66efa9cdacec0196f0f2ad7ba3c3a3ebb6d99636725"},"schema_version":"1.0","source":{"id":"2307.00536","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.00536","created_at":"2026-07-05T06:51:27Z"},{"alias_kind":"arxiv_version","alias_value":"2307.00536v2","created_at":"2026-07-05T06:51:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00536","created_at":"2026-07-05T06:51:27Z"},{"alias_kind":"pith_short_12","alias_value":"XMAC7HKD3RWA","created_at":"2026-07-05T06:51:27Z"},{"alias_kind":"pith_short_16","alias_value":"XMAC7HKD3RWAY4QL","created_at":"2026-07-05T06:51:27Z"},{"alias_kind":"pith_short_8","alias_value":"XMAC7HKD","created_at":"2026-07-05T06:51:27Z"}],"graph_snapshots":[{"event_id":"sha256:de2fdf00c502cb949d11a928c11f147f4f73cecb8a80c106c27e4ced337b0412","target":"graph","created_at":"2026-07-05T06:51:27Z","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/2307.00536/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring video object segmentation (RVOS) aims to segment the target object in a video sequence described by a language expression. Typical multimodal Transformer based RVOS approaches process video sequence in a frame-independent manner to reduce the high computational cost, which however restricts the performance due to the lack of inter-frame interaction for temporal coherence modeling and spatio-temporal representation learning of the referred object. Besides, the absence of sufficient cross-modal interactions results in weak correlation between the visual and linguistic features, which i","authors_text":"Fu Rong, Lefei Zhang, Meng Lan, Wei Yu, Zuchao Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-02T10:29:35Z","title":"Bidirectional Correlation-Driven Inter-Frame Interaction Transformer for Referring Video Object Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00536","kind":"arxiv","version":2},"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":"sha256:68f54963c38d6ed83f3aafc4a6ca9fb8efa3a8b18dcddbf436db6bc9b9123c6c","target":"record","created_at":"2026-07-05T06:51:27Z","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":"656ed1a9073df99dec624c4a2ebac031c6d123bc1837085a3a350fad6283c751","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-02T10:29:35Z","title_canon_sha256":"4d390ec9e38fd647d362a66efa9cdacec0196f0f2ad7ba3c3a3ebb6d99636725"},"schema_version":"1.0","source":{"id":"2307.00536","kind":"arxiv","version":2}},"canonical_sha256":"bb002f9d43dc6c0c720b1a128ac6887d8586e6319ffe9d25b986c9d5b3b2c5fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb002f9d43dc6c0c720b1a128ac6887d8586e6319ffe9d25b986c9d5b3b2c5fc","first_computed_at":"2026-07-05T06:51:27.198413Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:51:27.198413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+FVzBeLm3yuCEVySTkULg//aGzg+Z60EpmvWSrpwyoNeGfiGxcJVHtaXMd4iK0jzZzvQQROC/hrMib2TVCrbCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:51:27.198848Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.00536","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68f54963c38d6ed83f3aafc4a6ca9fb8efa3a8b18dcddbf436db6bc9b9123c6c","sha256:de2fdf00c502cb949d11a928c11f147f4f73cecb8a80c106c27e4ced337b0412"],"state_sha256":"23d4a95e0e4cea7689c793e9ca6516243b7c76de903d8874609f2c0dd0c72dcd"}