{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DE5HB5NEEANUS4WY2X3QLHYLFJ","short_pith_number":"pith:DE5HB5NE","schema_version":"1.0","canonical_sha256":"193a70f5a4201b4972d8d5f7059f0b2a766b9922fa756479a597657115b20c1b","source":{"kind":"arxiv","id":"2503.06520","version":2},"attestation_state":"computed","paper":{"title":"Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Reinforcement learning with format and accuracy rewards enables explicit reasoning chains to guide image segmentation.","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Bei Yu, Bohao Peng, Fanbin Lu, Jiaya Jia, Yuqi Liu, Zhisheng Zhong, Zihao Yue","submitted_at":"2025-03-09T08:48:51Z","abstract_excerpt":"Traditional methods for reasoning segmentation rely on supervised fine-tuning with categorical labels and simple descriptions, limiting its out-of-domain generalization and lacking explicit reasoning processes. To address these limitations, we propose Seg-Zero, a novel framework that demonstrates remarkable generalizability and derives explicit chain-of-thought reasoning through cognitive reinforcement. Seg-Zero introduces a decoupled architecture consisting of a reasoning model and a segmentation model. The reasoning model interprets user intentions, generates explicit reasoning chains, and p"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2503.06520","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-09T08:48:51Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"59dc4ae3867082357577c8d924ebc5cfbdaa49794b05dbc0ca9b5cb5270779ec","abstract_canon_sha256":"75113e3d41151dbc49215b079d83c571ce82e218aa1668b01c8d75b710268a29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:47.875410Z","signature_b64":"/XKHaFLAv6/z6PhcUUyQBJKLR1qw42GKvejfXVvKHjaQ4ySnAmHeQjZ+wPhe8mkNxU9hOEuGScElreXYQ+LbCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"193a70f5a4201b4972d8d5f7059f0b2a766b9922fa756479a597657115b20c1b","last_reissued_at":"2026-05-17T23:38:47.874901Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:47.874901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Reinforcement learning with format and accuracy rewards enables explicit reasoning chains to guide image segmentation.","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Bei Yu, Bohao Peng, Fanbin Lu, Jiaya Jia, Yuqi Liu, Zhisheng Zhong, Zihao Yue","submitted_at":"2025-03-09T08:48:51Z","abstract_excerpt":"Traditional methods for reasoning segmentation rely on supervised fine-tuning with categorical labels and simple descriptions, limiting its out-of-domain generalization and lacking explicit reasoning processes. To address these limitations, we propose Seg-Zero, a novel framework that demonstrates remarkable generalizability and derives explicit chain-of-thought reasoning through cognitive reinforcement. Seg-Zero introduces a decoupled architecture consisting of a reasoning model and a segmentation model. The reasoning model interprets user intentions, generates explicit reasoning chains, and p"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Seg-Zero-7B achieves a zero-shot performance of 57.5 on the ReasonSeg benchmark, surpassing the prior LISA-7B by 18%.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the format-plus-accuracy reward mechanism, applied only through reinforcement learning without any explicit reasoning supervision, reliably produces useful and generalizable chain-of-thought reasoning rather than superficial patterns that happen to score well on the training distribution.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Seg-Zero uses cognitive reinforcement learning on a decoupled reasoning-plus-segmentation architecture to produce explicit reasoning chains and reach 57.5 zero-shot accuracy on ReasonSeg, beating prior supervised LISA-7B by 18%.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Reinforcement learning with format and accuracy rewards enables explicit reasoning chains to guide image segmentation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d4d9daea391d23569cc2e7031b0e2fd29746279130e22f10d41b8cc64f67839d"},"source":{"id":"2503.06520","kind":"arxiv","version":2},"verdict":{"id":"3f881baf-43c2-4cd6-b18e-dfa457c6dc42","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T12:27:04.945088Z","strongest_claim":"Seg-Zero-7B achieves a zero-shot performance of 57.5 on the ReasonSeg benchmark, surpassing the prior LISA-7B by 18%.","one_line_summary":"Seg-Zero uses cognitive reinforcement learning on a decoupled reasoning-plus-segmentation architecture to produce explicit reasoning chains and reach 57.5 zero-shot accuracy on ReasonSeg, beating prior supervised LISA-7B by 18%.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the format-plus-accuracy reward mechanism, applied only through reinforcement learning without any explicit reasoning supervision, reliably produces useful and generalizable chain-of-thought reasoning rather than superficial patterns that happen to score well on the training distribution.","pith_extraction_headline":"Reinforcement learning with format and accuracy rewards enables explicit reasoning chains to guide image segmentation."},"references":{"count":45,"sample":[{"doi":"","year":2017,"title":"Segnet: A deep convolutional encoder-decoder architecture for image segmentation","work_id":"c5380531-81cc-4c05-ab24-d89795bc0a27","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","ref_index":2,"cited_arxiv_id":"2502.13923","is_internal_anchor":true},{"doi":"","year":2025,"title":"One token to seg them all: Language instructed reasoning seg- mentation in videos","work_id":"ab23c2cb-5301-4a98-8234-5ffcf0ecf252","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolu- tion, and fully connected crfs","work_id":"57309a7b-831c-447b-92aa-115c5bb5aefb","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Rethinking Atrous Convolution for Semantic Image Segmentation","work_id":"6f5d4c68-8df6-4794-b125-a10bfe8d5876","ref_index":5,"cited_arxiv_id":"1706.05587","is_internal_anchor":true}],"resolved_work":45,"snapshot_sha256":"63d13e76de97e481fcfc316ef5dca57081624cce43973d00957b82d449c616ae","internal_anchors":12},"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":"2503.06520","created_at":"2026-05-17T23:38:47.874987+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06520v2","created_at":"2026-05-17T23:38:47.874987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06520","created_at":"2026-05-17T23:38:47.874987+00:00"},{"alias_kind":"pith_short_12","alias_value":"DE5HB5NEEANU","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"DE5HB5NEEANUS4WY","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"DE5HB5NE","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":41,"internal_anchor_count":41,"sample":[{"citing_arxiv_id":"2605.23500","citing_title":"B-GRTO: Bootstrapped Group Relative Tool Optimization for Referring Segmentation","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2511.20785","citing_title":"LongVT: Incentivizing \"Thinking with Long Videos\" via Native Tool Calling","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2512.15693","citing_title":"Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20385","citing_title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21130","citing_title":"VersusQ: Pairwise Margin Reasoning for Generalizable Video Quality Assessment","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15951","citing_title":"From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17531","citing_title":"Don't Guess, Just Ask: Resolving Ambiguity in Referring Segmentation via Multi-turn Clarification","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19852","citing_title":"Are Tools Always Beneficial? Learning to Invoke Tools Adaptively for Dual-Mode Multimodal LLM Reasoning","ref_index":85,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19410","citing_title":"Vision Harnessing Agent for Open Ad-hoc Segmentation","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20110","citing_title":"SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2505.18600","citing_title":"Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2506.16796","citing_title":"RealSR-R1: Reinforcement Learning for Real-World Image Super-Resolution with Vision-Language Chain-of-Thought","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2506.21546","citing_title":"Counterfactual Segmentation Reasoning: Diagnosing and Mitigating Pixel-Grounding Hallucination","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2507.00748","citing_title":"Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2509.21976","citing_title":"Geo-R1: Improving Few-Shot Geospatial Referring Expression Understanding with Reinforcement Fine-Tuning","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2510.10606","citing_title":"ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for Large Vision-and-Language Models","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2511.16719","citing_title":"SAM 3: Segment Anything with Concepts","ref_index":82,"is_internal_anchor":true},{"citing_arxiv_id":"2512.03043","citing_title":"OneThinker: All-in-one Reasoning Model for Image and Video","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2512.10554","citing_title":"Grounding Everything in Tokens for Multimodal Large Language Models","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2512.16918","citing_title":"AdaTooler-V: Adaptive Tool-Use for Images and Videos","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2601.03054","citing_title":"IBISAgent: Reinforcing Pixel-Level Visual Reasoning in MLLMs for Universal Biomedical Object Referring and Segmentation","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2601.15507","citing_title":"A Unified and Controllable Framework for Layered Image Generation with Visual Effects","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2504.06958","citing_title":"VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":246,"is_internal_anchor":true},{"citing_arxiv_id":"2603.13054","citing_title":"Topo-R1: Detecting Topological Anomalies via Vision-Language Models","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DE5HB5NEEANUS4WY2X3QLHYLFJ","json":"https://pith.science/pith/DE5HB5NEEANUS4WY2X3QLHYLFJ.json","graph_json":"https://pith.science/api/pith-number/DE5HB5NEEANUS4WY2X3QLHYLFJ/graph.json","events_json":"https://pith.science/api/pith-number/DE5HB5NEEANUS4WY2X3QLHYLFJ/events.json","paper":"https://pith.science/paper/DE5HB5NE"},"agent_actions":{"view_html":"https://pith.science/pith/DE5HB5NEEANUS4WY2X3QLHYLFJ","download_json":"https://pith.science/pith/DE5HB5NEEANUS4WY2X3QLHYLFJ.json","view_paper":"https://pith.science/paper/DE5HB5NE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06520&json=true","fetch_graph":"https://pith.science/api/pith-number/DE5HB5NEEANUS4WY2X3QLHYLFJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DE5HB5NEEANUS4WY2X3QLHYLFJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DE5HB5NEEANUS4WY2X3QLHYLFJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DE5HB5NEEANUS4WY2X3QLHYLFJ/action/storage_attestation","attest_author":"https://pith.science/pith/DE5HB5NEEANUS4WY2X3QLHYLFJ/action/author_attestation","sign_citation":"https://pith.science/pith/DE5HB5NEEANUS4WY2X3QLHYLFJ/action/citation_signature","submit_replication":"https://pith.science/pith/DE5HB5NEEANUS4WY2X3QLHYLFJ/action/replication_record"}},"created_at":"2026-05-17T23:38:47.874987+00:00","updated_at":"2026-05-17T23:38:47.874987+00:00"}