{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:57IXEE6ONY6PKRPSZ6SEOTZ3UM","short_pith_number":"pith:57IXEE6O","canonical_record":{"source":{"id":"2606.00987","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-31T04:01:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3648cc524938140b387748c4b3c582bfcbda2572d969d83224f86ec68f4c2501","abstract_canon_sha256":"58d9df55e20de79dce6d035f6262d067b99c4bc2b0087cd364629fe2434370bb"},"schema_version":"1.0"},"canonical_sha256":"efd17213ce6e3cf545f2cfa4474f3ba31f7e764777ce3af52b4444df93523647","source":{"kind":"arxiv","id":"2606.00987","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:57IXEE6ONY6PKRPSZ6SEOTZ3UM","target":"record","payload":{"canonical_record":{"source":{"id":"2606.00987","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-31T04:01:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3648cc524938140b387748c4b3c582bfcbda2572d969d83224f86ec68f4c2501","abstract_canon_sha256":"58d9df55e20de79dce6d035f6262d067b99c4bc2b0087cd364629fe2434370bb"},"schema_version":"1.0"},"canonical_sha256":"efd17213ce6e3cf545f2cfa4474f3ba31f7e764777ce3af52b4444df93523647","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:17.066086Z","signature_b64":"v/VUg4ClQ4o64aBu6AYQ9XnHNKBnFHvIo8sr+CUawUPmbaD2GlQ7kajxVDEnROeIQKX0Oucnb97ZpnrwC2s6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efd17213ce6e3cf545f2cfa4474f3ba31f7e764777ce3af52b4444df93523647","last_reissued_at":"2026-06-02T01:04:17.065682Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:17.065682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.00987","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:04:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NAqV5S8V2fXlCBJ6y5q1Yv8lwt0M6Nor8Y7CJdKW5aW7jK03NIDnQl2ulcTuLdpjhCA1O4rbBQjiq6cECHIlBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T07:00:38.275696Z"},"content_sha256":"aaa91275d301db3b9f86b0766dddaf05d256bafdd8c133c4cd94109876f5aef6","schema_version":"1.0","event_id":"sha256:aaa91275d301db3b9f86b0766dddaf05d256bafdd8c133c4cd94109876f5aef6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:57IXEE6ONY6PKRPSZ6SEOTZ3UM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Open-Source Benchmark and Baseline for Multi-temporal Referring Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bingyu Li, Da Zhang, Junyu Gao, Tao Huo, Xuelong Li, Zhiyuan Zhao","submitted_at":"2026-05-31T04:01:10Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00987","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/2606.00987/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:04:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B5ePlUTTT7n9H/0ARk9d3mIzw89clbephJTf1MCVte2X8SVrLAtVxzfpck81hzoHn4pf7GkwHuLJr8kOquXQDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T07:00:38.276482Z"},"content_sha256":"c777ab6d0f3d03671b410a90ac7d5dfc156cc918e771f951c8fc70dda051955e","schema_version":"1.0","event_id":"sha256:c777ab6d0f3d03671b410a90ac7d5dfc156cc918e771f951c8fc70dda051955e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/57IXEE6ONY6PKRPSZ6SEOTZ3UM/bundle.json","state_url":"https://pith.science/pith/57IXEE6ONY6PKRPSZ6SEOTZ3UM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/57IXEE6ONY6PKRPSZ6SEOTZ3UM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-10T07:00:38Z","links":{"resolver":"https://pith.science/pith/57IXEE6ONY6PKRPSZ6SEOTZ3UM","bundle":"https://pith.science/pith/57IXEE6ONY6PKRPSZ6SEOTZ3UM/bundle.json","state":"https://pith.science/pith/57IXEE6ONY6PKRPSZ6SEOTZ3UM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/57IXEE6ONY6PKRPSZ6SEOTZ3UM/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WMc5QNiyqaxmsiNv5sJUDuL+GCfMU5bVR9kxuKdIYoX04WCfbypszvsdY7BM3sir9OpdlQgjbk45eVwMPVEWBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T07:00:38.280390Z","bundle_sha256":"462054ab9b1d0b78ab29d78a79c2cab30447b11ce42119ef66a8236beb4e33de"}}