{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:L55NJMBZE7TWUWJ6OL4K5UVVJO","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":"82bf3e719219325c43f009caf46f9e29b7245059ab35e6dc28b4f03526b09a23","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-15T03:17:24Z","title_canon_sha256":"8e1a0adb0262b11059d350514a4ea41f32672aede1e885b27fe4001344014d0f"},"schema_version":"1.0","source":{"id":"2501.08549","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.08549","created_at":"2026-07-05T10:21:28Z"},{"alias_kind":"arxiv_version","alias_value":"2501.08549v1","created_at":"2026-07-05T10:21:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08549","created_at":"2026-07-05T10:21:28Z"},{"alias_kind":"pith_short_12","alias_value":"L55NJMBZE7TW","created_at":"2026-07-05T10:21:28Z"},{"alias_kind":"pith_short_16","alias_value":"L55NJMBZE7TWUWJ6","created_at":"2026-07-05T10:21:28Z"},{"alias_kind":"pith_short_8","alias_value":"L55NJMBZ","created_at":"2026-07-05T10:21:28Z"}],"graph_snapshots":[{"event_id":"sha256:13aaf1115f2abc9c4696e7f9505ee4a8c03192d5c0d8f178f851e0f5ccf9040f","target":"graph","created_at":"2026-07-05T10:21:28Z","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/2501.08549/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing methods for Video Reasoning Segmentation rely heavily on a single special token to represent the object in the keyframe or the entire video, inadequately capturing spatial complexity and inter-frame motion. To overcome these challenges, we propose VRS-HQ, an end-to-end video reasoning segmentation approach that leverages Multimodal Large Language Models (MLLMs) to inject rich spatiotemporal features into hierarchical tokens.Our key innovations include a Temporal Dynamic Aggregation (TDA) and a Token-driven Keyframe Selection (TKS). Specifically, we design frame-level <SEG> and tempora","authors_text":"Huchuan Lu, Lu Zhang, Pingping Zhang, Sitong Gong, Yunzhi Zhuge, Zongxin Yang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-15T03:17:24Z","title":"The Devil is in Temporal Token: High Quality Video Reasoning Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08549","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":"sha256:77a0c8d85a09f159b8dcbebb91f3056f04496ce1bb1ea7498efba83644211175","target":"record","created_at":"2026-07-05T10:21:28Z","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":"82bf3e719219325c43f009caf46f9e29b7245059ab35e6dc28b4f03526b09a23","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-15T03:17:24Z","title_canon_sha256":"8e1a0adb0262b11059d350514a4ea41f32672aede1e885b27fe4001344014d0f"},"schema_version":"1.0","source":{"id":"2501.08549","kind":"arxiv","version":1}},"canonical_sha256":"5f7ad4b03927e76a593e72f8aed2b54baafea2a6f4c64e9cdeb480586955ebd7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f7ad4b03927e76a593e72f8aed2b54baafea2a6f4c64e9cdeb480586955ebd7","first_computed_at":"2026-07-05T10:21:28.139534Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:28.139534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dVmlAWzsqh+XDVeysQwFnDx4pNOjJY4FN6WkdtDrD2dRL8YV7hCVchtYT58x03QCdEZdG3TYP0ZhwAkPHBa3Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:28.140119Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.08549","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77a0c8d85a09f159b8dcbebb91f3056f04496ce1bb1ea7498efba83644211175","sha256:13aaf1115f2abc9c4696e7f9505ee4a8c03192d5c0d8f178f851e0f5ccf9040f"],"state_sha256":"4b1044fbdc23b27f8edf4235986c8eda1b9dd60db7cecd5ba011d74a8d660193"}