{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:57IXEE6ONY6PKRPSZ6SEOTZ3UM","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":"58d9df55e20de79dce6d035f6262d067b99c4bc2b0087cd364629fe2434370bb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-31T04:01:10Z","title_canon_sha256":"3648cc524938140b387748c4b3c582bfcbda2572d969d83224f86ec68f4c2501"},"schema_version":"1.0","source":{"id":"2606.00987","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00987","created_at":"2026-06-02T01:04:17Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00987v1","created_at":"2026-06-02T01:04:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00987","created_at":"2026-06-02T01:04:17Z"},{"alias_kind":"pith_short_12","alias_value":"57IXEE6ONY6P","created_at":"2026-06-02T01:04:17Z"},{"alias_kind":"pith_short_16","alias_value":"57IXEE6ONY6PKRPS","created_at":"2026-06-02T01:04:17Z"},{"alias_kind":"pith_short_8","alias_value":"57IXEE6O","created_at":"2026-06-02T01:04:17Z"}],"graph_snapshots":[{"event_id":"sha256:c777ab6d0f3d03671b410a90ac7d5dfc156cc918e771f951c8fc70dda051955e","target":"graph","created_at":"2026-06-02T01:04:17Z","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/2606.00987/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision-Language Models (LVLMs) have shown strong visual understanding and language-guided grounding abilities, yet their capacity for multi-temporal visual reasoning remains underexplored. To bridge this gap, we introduce \\textbf{Multi-temporal Referring Segmentation (MTRS)}, a new task that aims to segment language-described temporal changes from multi-temporal images. MTRS extends conventional referring segmentation and change detection by jointly requiring temporal correspondence reasoning, language grounding, and pixel-level mask prediction. We propose \\textbf{CRAFT-Agent}, an automa","authors_text":"Bingyu Li, Da Zhang, Junyu Gao, Tao Huo, Xuelong Li, Zhiyuan Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-31T04:01:10Z","title":"An Open-Source Benchmark and Baseline for Multi-temporal Referring Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00987","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:aaa91275d301db3b9f86b0766dddaf05d256bafdd8c133c4cd94109876f5aef6","target":"record","created_at":"2026-06-02T01:04:17Z","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":"58d9df55e20de79dce6d035f6262d067b99c4bc2b0087cd364629fe2434370bb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-31T04:01:10Z","title_canon_sha256":"3648cc524938140b387748c4b3c582bfcbda2572d969d83224f86ec68f4c2501"},"schema_version":"1.0","source":{"id":"2606.00987","kind":"arxiv","version":1}},"canonical_sha256":"efd17213ce6e3cf545f2cfa4474f3ba31f7e764777ce3af52b4444df93523647","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"efd17213ce6e3cf545f2cfa4474f3ba31f7e764777ce3af52b4444df93523647","first_computed_at":"2026-06-02T01:04:17.065682Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:04:17.065682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v/VUg4ClQ4o64aBu6AYQ9XnHNKBnFHvIo8sr+CUawUPmbaD2GlQ7kajxVDEnROeIQKX0Oucnb97ZpnrwC2s6DA==","signature_status":"signed_v1","signed_at":"2026-06-02T01:04:17.066086Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.00987","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aaa91275d301db3b9f86b0766dddaf05d256bafdd8c133c4cd94109876f5aef6","sha256:c777ab6d0f3d03671b410a90ac7d5dfc156cc918e771f951c8fc70dda051955e"],"state_sha256":"19adf9558002ecfc850028db09e9e4ca2998df474bd536da0d0ebb80eeb93ee2"}