{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VWG444UBSDIVQPTCLDC3IPWDJ3","short_pith_number":"pith:VWG444UB","schema_version":"1.0","canonical_sha256":"ad8dce728190d1583e6258c5b43ec34eeac6e95f948d71cb969c8ed7e0aad65f","source":{"kind":"arxiv","id":"2506.04277","version":1},"attestation_state":"computed","paper":{"title":"RSVP: Reasoning Segmentation via Visual Prompting and Multi-modal Chain-of-Thought","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bozheng Li, Chong Wu, Jay Wu, Jiawang Cao, Licheng Tang, Wenbo Zhu, Yangguang Ji, Yi Lu, Yongliang Wu","submitted_at":"2025-06-04T02:07:40Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.04277","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T02:07:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1b1797cdef11f384f29a861ed9b823a747f9bde70bb7bc7fdd90eafd46b4d588","abstract_canon_sha256":"9b3c0c20189c695a4ae40ee5fcf1d7642edbc3388111e2ba15ef638ba24c81c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:11.490302Z","signature_b64":"MDO41RgDdVCJrCJomBDlqcqRL4ZjGalhTB9bL1zylDhc0fXPEfJtyDJ0gWDB4pXYHoS+/pZTSimMeSTS4YKVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad8dce728190d1583e6258c5b43ec34eeac6e95f948d71cb969c8ed7e0aad65f","last_reissued_at":"2026-07-05T11:16:11.489859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:11.489859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RSVP: Reasoning Segmentation via Visual Prompting and Multi-modal Chain-of-Thought","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bozheng Li, Chong Wu, Jay Wu, Jiawang Cao, Licheng Tang, Wenbo Zhu, Yangguang Ji, Yi Lu, Yongliang Wu","submitted_at":"2025-06-04T02:07:40Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04277","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/2506.04277/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.04277","created_at":"2026-07-05T11:16:11.489918+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04277v1","created_at":"2026-07-05T11:16:11.489918+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04277","created_at":"2026-07-05T11:16:11.489918+00:00"},{"alias_kind":"pith_short_12","alias_value":"VWG444UBSDIV","created_at":"2026-07-05T11:16:11.489918+00:00"},{"alias_kind":"pith_short_16","alias_value":"VWG444UBSDIVQPTC","created_at":"2026-07-05T11:16:11.489918+00:00"},{"alias_kind":"pith_short_8","alias_value":"VWG444UB","created_at":"2026-07-05T11:16:11.489918+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09303","citing_title":"Reason Twice: Segmentation via Candidate Discovery and Comparative Reasoning","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2602.18600","citing_title":"MapTab: A Diagnostic Benchmark for Long-Horizon Multi-Criteria Multimodal Reasoning on Heterogeneous Topological Graphs","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19410","citing_title":"Vision Harnessing Agent for Open Ad-hoc Segmentation","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2511.16719","citing_title":"SAM 3: Segment Anything with Concepts","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2602.18600","citing_title":"MapTab: A Diagnostic Benchmark for Long-Horizon Multi-Criteria Multimodal Reasoning on Heterogeneous Topological Graphs","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VWG444UBSDIVQPTCLDC3IPWDJ3","json":"https://pith.science/pith/VWG444UBSDIVQPTCLDC3IPWDJ3.json","graph_json":"https://pith.science/api/pith-number/VWG444UBSDIVQPTCLDC3IPWDJ3/graph.json","events_json":"https://pith.science/api/pith-number/VWG444UBSDIVQPTCLDC3IPWDJ3/events.json","paper":"https://pith.science/paper/VWG444UB"},"agent_actions":{"view_html":"https://pith.science/pith/VWG444UBSDIVQPTCLDC3IPWDJ3","download_json":"https://pith.science/pith/VWG444UBSDIVQPTCLDC3IPWDJ3.json","view_paper":"https://pith.science/paper/VWG444UB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04277&json=true","fetch_graph":"https://pith.science/api/pith-number/VWG444UBSDIVQPTCLDC3IPWDJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/VWG444UBSDIVQPTCLDC3IPWDJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VWG444UBSDIVQPTCLDC3IPWDJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VWG444UBSDIVQPTCLDC3IPWDJ3/action/storage_attestation","attest_author":"https://pith.science/pith/VWG444UBSDIVQPTCLDC3IPWDJ3/action/author_attestation","sign_citation":"https://pith.science/pith/VWG444UBSDIVQPTCLDC3IPWDJ3/action/citation_signature","submit_replication":"https://pith.science/pith/VWG444UBSDIVQPTCLDC3IPWDJ3/action/replication_record"}},"created_at":"2026-07-05T11:16:11.489918+00:00","updated_at":"2026-07-05T11:16:11.489918+00:00"}