{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7LF56GBIFFTYG5PCGULKWNGNFR","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":"4e5f355862d34493456232f8de5e6c4a71733b40187746cf6c67c143c7ad1548","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-01T07:06:47Z","title_canon_sha256":"876c5841c9c64bab8a302a7a4c17825273d185aa839c49005709e7e68eb91dbe"},"schema_version":"1.0","source":{"id":"2504.00476","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.00476","created_at":"2026-07-05T10:42:27Z"},{"alias_kind":"arxiv_version","alias_value":"2504.00476v1","created_at":"2026-07-05T10:42:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00476","created_at":"2026-07-05T10:42:27Z"},{"alias_kind":"pith_short_12","alias_value":"7LF56GBIFFTY","created_at":"2026-07-05T10:42:27Z"},{"alias_kind":"pith_short_16","alias_value":"7LF56GBIFFTYG5PC","created_at":"2026-07-05T10:42:27Z"},{"alias_kind":"pith_short_8","alias_value":"7LF56GBI","created_at":"2026-07-05T10:42:27Z"}],"graph_snapshots":[{"event_id":"sha256:3df1e3fe49b64677cfb2f54f62fdf3faae62cf39229f5fee839e7f441255c55a","target":"graph","created_at":"2026-07-05T10:42:27Z","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/2504.00476/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring video object segmentation (RVOS) is a challenging task that requires the model to segment the object in a video given the language description. MeViS is a recently proposed dataset that contains motion expressions of the target objects, leading to a challenging benchmark, compared with existing RVOS benchmarks. On the other hand, for referring expression tasks, a new trend is to adopt multi-modal large language model (MLLM) to achieve better image and text alignment. In this report, we show that with a simple modification to the test time inference method on stronger MLLMs, we can le","authors_text":"Haobo Yuan, Jiashi Feng, Lu Qi, Ming-Hsuan Yang, Shilin Xu, Tao Zhang, Xiangtai Li, Zilong Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-01T07:06:47Z","title":"4th PVUW MeViS 3rd Place Report: Sa2VA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00476","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:ecf69e597a6c5a89c64cf1e252e13a2e218450f46c9cc0c756c3643c1c2a9bb8","target":"record","created_at":"2026-07-05T10:42:27Z","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":"4e5f355862d34493456232f8de5e6c4a71733b40187746cf6c67c143c7ad1548","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-01T07:06:47Z","title_canon_sha256":"876c5841c9c64bab8a302a7a4c17825273d185aa839c49005709e7e68eb91dbe"},"schema_version":"1.0","source":{"id":"2504.00476","kind":"arxiv","version":1}},"canonical_sha256":"facbdf182829678375e23516ab34cd2c67bd4168d6ae7678ef1200474d9eb753","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"facbdf182829678375e23516ab34cd2c67bd4168d6ae7678ef1200474d9eb753","first_computed_at":"2026-07-05T10:42:27.132292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:42:27.132292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bFfHuDMsSD4mCRiYzGZo5JXXNc3aQyYxsfJYbToM8/ZNje8PuEWcnb35mnVEqIiBJAig/iyYbovGLqGHqsrADg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:42:27.132760Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.00476","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ecf69e597a6c5a89c64cf1e252e13a2e218450f46c9cc0c756c3643c1c2a9bb8","sha256:3df1e3fe49b64677cfb2f54f62fdf3faae62cf39229f5fee839e7f441255c55a"],"state_sha256":"67e4042b446d48ffe93eb271a29abfcbf7224234074cbf8e453b4e71e381cdbe"}