{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LBX2PA4GCD6J34XEFIRSWAPOUX","short_pith_number":"pith:LBX2PA4G","schema_version":"1.0","canonical_sha256":"586fa7838610fc9df2e42a232b01eea5ee859f3ee7de0435f79fe407f94bc627","source":{"kind":"arxiv","id":"2509.06321","version":1},"attestation_state":"computed","paper":{"title":"Text4Seg++: Advancing Image Segmentation via Generative Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaofeng Chen, Jiaxing Xu, Mengcheng Lan, Song Bai, Xudong Jiang, Yingchen Yu, Yiping Ke, Yunqing Zhao, Zongrui Li","submitted_at":"2025-09-08T04:07:14Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have shown exceptional capabilities in vision-language tasks. However, effectively integrating image segmentation into these models remains a significant challenge. In this work, we propose a novel text-as-mask paradigm that casts image segmentation as a text generation problem, eliminating the need for additional decoders and significantly simplifying the segmentation process. Our key innovation is semantic descriptors, a new textual representation of segmentation masks where each image patch is mapped to its corresponding text label. We first introduc"},"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":"2509.06321","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-08T04:07:14Z","cross_cats_sorted":[],"title_canon_sha256":"0baeca324ffd2e2a69a10f31fa3cb3010a63f3fb9190af2586488b0bdbee1f33","abstract_canon_sha256":"191c2625628687dc0a017b94d6d4300d1268e9fb42e1e7694a90060961e6c6f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:33.725221Z","signature_b64":"oluPe3nfV8rpJY+rP3fsDsWtJEuxYrTGLqXHP7rdUhB0hv/9xxiG+AMquSnAV+I9T0TY1cpAzBpazhJWqIQQBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"586fa7838610fc9df2e42a232b01eea5ee859f3ee7de0435f79fe407f94bc627","last_reissued_at":"2026-07-05T12:06:33.724730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:33.724730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text4Seg++: Advancing Image Segmentation via Generative Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaofeng Chen, Jiaxing Xu, Mengcheng Lan, Song Bai, Xudong Jiang, Yingchen Yu, Yiping Ke, Yunqing Zhao, Zongrui Li","submitted_at":"2025-09-08T04:07:14Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have shown exceptional capabilities in vision-language tasks. However, effectively integrating image segmentation into these models remains a significant challenge. In this work, we propose a novel text-as-mask paradigm that casts image segmentation as a text generation problem, eliminating the need for additional decoders and significantly simplifying the segmentation process. Our key innovation is semantic descriptors, a new textual representation of segmentation masks where each image patch is mapped to its corresponding text label. We first introduc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06321","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/2509.06321/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":"2509.06321","created_at":"2026-07-05T12:06:33.724786+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.06321v1","created_at":"2026-07-05T12:06:33.724786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06321","created_at":"2026-07-05T12:06:33.724786+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBX2PA4GCD6J","created_at":"2026-07-05T12:06:33.724786+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBX2PA4GCD6J34XE","created_at":"2026-07-05T12:06:33.724786+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBX2PA4G","created_at":"2026-07-05T12:06:33.724786+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11789","citing_title":"LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07765","citing_title":"RemoteAgent: Bridging Vague Human Intents and Earth Observation with RL-based Agentic MLLMs","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LBX2PA4GCD6J34XEFIRSWAPOUX","json":"https://pith.science/pith/LBX2PA4GCD6J34XEFIRSWAPOUX.json","graph_json":"https://pith.science/api/pith-number/LBX2PA4GCD6J34XEFIRSWAPOUX/graph.json","events_json":"https://pith.science/api/pith-number/LBX2PA4GCD6J34XEFIRSWAPOUX/events.json","paper":"https://pith.science/paper/LBX2PA4G"},"agent_actions":{"view_html":"https://pith.science/pith/LBX2PA4GCD6J34XEFIRSWAPOUX","download_json":"https://pith.science/pith/LBX2PA4GCD6J34XEFIRSWAPOUX.json","view_paper":"https://pith.science/paper/LBX2PA4G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.06321&json=true","fetch_graph":"https://pith.science/api/pith-number/LBX2PA4GCD6J34XEFIRSWAPOUX/graph.json","fetch_events":"https://pith.science/api/pith-number/LBX2PA4GCD6J34XEFIRSWAPOUX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBX2PA4GCD6J34XEFIRSWAPOUX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBX2PA4GCD6J34XEFIRSWAPOUX/action/storage_attestation","attest_author":"https://pith.science/pith/LBX2PA4GCD6J34XEFIRSWAPOUX/action/author_attestation","sign_citation":"https://pith.science/pith/LBX2PA4GCD6J34XEFIRSWAPOUX/action/citation_signature","submit_replication":"https://pith.science/pith/LBX2PA4GCD6J34XEFIRSWAPOUX/action/replication_record"}},"created_at":"2026-07-05T12:06:33.724786+00:00","updated_at":"2026-07-05T12:06:33.724786+00:00"}