{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DDDQXKYHG27GELLBAY472UG6GB","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":"159a42ad18a4779e02ff36d15847e2b451970efbc6a3ccd403bbeb55768a8fde","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-23T13:53:33Z","title_canon_sha256":"78de7dd2145cc2212c43891af31b9dc6b5d61891ea336dc1ab6ce0c5b3e11926"},"schema_version":"1.0","source":{"id":"2501.13667","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13667","created_at":"2026-07-05T11:50:30Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13667v5","created_at":"2026-07-05T11:50:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13667","created_at":"2026-07-05T11:50:30Z"},{"alias_kind":"pith_short_12","alias_value":"DDDQXKYHG27G","created_at":"2026-07-05T11:50:30Z"},{"alias_kind":"pith_short_16","alias_value":"DDDQXKYHG27GELLB","created_at":"2026-07-05T11:50:30Z"},{"alias_kind":"pith_short_8","alias_value":"DDDQXKYH","created_at":"2026-07-05T11:50:30Z"}],"graph_snapshots":[{"event_id":"sha256:75fa4115bf0b5398e5b635def57410e180f16d1d305a955dd35f11597805454f","target":"graph","created_at":"2026-07-05T11:50:30Z","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/2501.13667/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 objects in a video according to textual descriptions, which requires the integration of multimodal information and temporal dynamics perception. The Segment Anything Model 2 (SAM 2) has shown great effectiveness across various video segmentation tasks. However, its application to offline RVOS is challenged by the translation of the text into effective prompts and a lack of global context awareness. In this paper, we propose a novel RVOS framework, termed MPG-SAM 2, to address these challenges. Specifically, MPG-SAM 2 employs a unified ","authors_text":"Fu Rong, Lefei Zhang, Meng Lan, Qian Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-23T13:53:33Z","title":"MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13667","kind":"arxiv","version":5},"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":"sha256:8d84f4f901c1aa69de25ebb7354c4b6819bd3c28c27a89d8684ddda94c7dce17","target":"record","created_at":"2026-07-05T11:50:30Z","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":"159a42ad18a4779e02ff36d15847e2b451970efbc6a3ccd403bbeb55768a8fde","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-23T13:53:33Z","title_canon_sha256":"78de7dd2145cc2212c43891af31b9dc6b5d61891ea336dc1ab6ce0c5b3e11926"},"schema_version":"1.0","source":{"id":"2501.13667","kind":"arxiv","version":5}},"canonical_sha256":"18c70bab0736be622d610639fd50de30427b2a785237a35ad96ba06f92fddd5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18c70bab0736be622d610639fd50de30427b2a785237a35ad96ba06f92fddd5f","first_computed_at":"2026-07-05T11:50:30.269249Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:30.269249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EYweUo3vaPlZgeWwqNnzQZ7bIZkKh7En4ewM3HzkjWAXCIeVGjrXHM6q2V5JxPei5Q5mW2atLviWaL2ztsLeAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:30.269745Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.13667","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d84f4f901c1aa69de25ebb7354c4b6819bd3c28c27a89d8684ddda94c7dce17","sha256:75fa4115bf0b5398e5b635def57410e180f16d1d305a955dd35f11597805454f"],"state_sha256":"bd33595f556fd7dc1883065d17b57704e5b23aa481d43176e67109748a824f69"}