{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VWG444UBSDIVQPTCLDC3IPWDJ3","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":"9b3c0c20189c695a4ae40ee5fcf1d7642edbc3388111e2ba15ef638ba24c81c6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T02:07:40Z","title_canon_sha256":"1b1797cdef11f384f29a861ed9b823a747f9bde70bb7bc7fdd90eafd46b4d588"},"schema_version":"1.0","source":{"id":"2506.04277","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04277","created_at":"2026-07-05T11:16:11Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04277v1","created_at":"2026-07-05T11:16:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04277","created_at":"2026-07-05T11:16:11Z"},{"alias_kind":"pith_short_12","alias_value":"VWG444UBSDIV","created_at":"2026-07-05T11:16:11Z"},{"alias_kind":"pith_short_16","alias_value":"VWG444UBSDIVQPTC","created_at":"2026-07-05T11:16:11Z"},{"alias_kind":"pith_short_8","alias_value":"VWG444UB","created_at":"2026-07-05T11:16:11Z"}],"graph_snapshots":[{"event_id":"sha256:385dd5611071a5491cfb61e7ddd4eef92ec04f699f5aaa811f79b9847dc784f2","target":"graph","created_at":"2026-07-05T11:16:11Z","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/2506.04277/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal Large Language Models (MLLMs) have demonstrated remarkable reasoning capability while lack explicit mechanisms for visual grounding and segmentation, creating a gap between cognitive reasoning and visual perception. To bridge this gap, we introduce Reasoning Segmentation via Visual Prompting (RSVP), a novel framework that unifies multi-step multimodal reasoning with grounded visual understanding. RSVP is a two-stage structuralized framework that integrates reasoning-driven localization with segmentation refinement. In the reasoning stage, RSVP employs multimodal chain-of-thought vi","authors_text":"Bozheng Li, Chong Wu, Jay Wu, Jiawang Cao, Licheng Tang, Wenbo Zhu, Yangguang Ji, Yi Lu, Yongliang Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T02:07:40Z","title":"RSVP: Reasoning Segmentation via Visual Prompting and Multi-modal Chain-of-Thought"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04277","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":"sha256:1d4d1902694097b3c64a5f13642205eb9400b214e5c4c2f9fb80dac6db04f58b","target":"record","created_at":"2026-07-05T11:16:11Z","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":"9b3c0c20189c695a4ae40ee5fcf1d7642edbc3388111e2ba15ef638ba24c81c6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T02:07:40Z","title_canon_sha256":"1b1797cdef11f384f29a861ed9b823a747f9bde70bb7bc7fdd90eafd46b4d588"},"schema_version":"1.0","source":{"id":"2506.04277","kind":"arxiv","version":1}},"canonical_sha256":"ad8dce728190d1583e6258c5b43ec34eeac6e95f948d71cb969c8ed7e0aad65f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad8dce728190d1583e6258c5b43ec34eeac6e95f948d71cb969c8ed7e0aad65f","first_computed_at":"2026-07-05T11:16:11.489859Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:11.489859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MDO41RgDdVCJrCJomBDlqcqRL4ZjGalhTB9bL1zylDhc0fXPEfJtyDJ0gWDB4pXYHoS+/pZTSimMeSTS4YKVBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:11.490302Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04277","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d4d1902694097b3c64a5f13642205eb9400b214e5c4c2f9fb80dac6db04f58b","sha256:385dd5611071a5491cfb61e7ddd4eef92ec04f699f5aaa811f79b9847dc784f2"],"state_sha256":"e01afab2e519430629eaa9fbcc1c85c8bb471993bd58fef447f16511f16a0b82"}