{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V7YL6T5NAS5YNZJH26QJU6YX7K","short_pith_number":"pith:V7YL6T5N","schema_version":"1.0","canonical_sha256":"aff0bf4fad04bb86e527d7a09a7b17fa9e9fae74b48e82fc796413b49d3c484c","source":{"kind":"arxiv","id":"2410.09855","version":2},"attestation_state":"computed","paper":{"title":"Text4Seg: Reimagining Image Segmentation as Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaofeng Chen, Jiaxing Xu, Litong Feng, Mengcheng Lan, Wayne Zhang, Xinjiang Wang, Yiping Ke, Yue Zhou","submitted_at":"2024-10-13T14:28:16Z","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 paper, we introduce Text4Seg, 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. This"},"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":"2410.09855","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-13T14:28:16Z","cross_cats_sorted":[],"title_canon_sha256":"ecbd1aa34b6013db93d73581c4baaa1348fb7a535e70f2eb60ae7032945d9025","abstract_canon_sha256":"a1e1e6370a5c1d4e535b71c10fbe0a52827ae8b93355fa929dcf2fb3cd0671c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:20.365807Z","signature_b64":"6Zwp17HJHOU+HN6zLm2yySSZyR0YN9qIdrqMQ3h5l+C68rMlNMAxBkMlTMLwjIOmzzIKRCgUU3Jk38BXXPpYAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aff0bf4fad04bb86e527d7a09a7b17fa9e9fae74b48e82fc796413b49d3c484c","last_reissued_at":"2026-07-05T10:15:20.365305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:20.365305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text4Seg: Reimagining Image Segmentation as Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaofeng Chen, Jiaxing Xu, Litong Feng, Mengcheng Lan, Wayne Zhang, Xinjiang Wang, Yiping Ke, Yue Zhou","submitted_at":"2024-10-13T14:28:16Z","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 paper, we introduce Text4Seg, 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. This"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09855","kind":"arxiv","version":2},"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/2410.09855/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":"2410.09855","created_at":"2026-07-05T10:15:20.365376+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09855v2","created_at":"2026-07-05T10:15:20.365376+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09855","created_at":"2026-07-05T10:15:20.365376+00:00"},{"alias_kind":"pith_short_12","alias_value":"V7YL6T5NAS5Y","created_at":"2026-07-05T10:15:20.365376+00:00"},{"alias_kind":"pith_short_16","alias_value":"V7YL6T5NAS5YNZJH","created_at":"2026-07-05T10:15:20.365376+00:00"},{"alias_kind":"pith_short_8","alias_value":"V7YL6T5N","created_at":"2026-07-05T10:15:20.365376+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26196","citing_title":"From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models","ref_index":118,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01612","citing_title":"Self-Improving Small Object Grounding in LVLMs","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24553","citing_title":"IQA-Spider: Unifying Multi-Granularity Image Quality Assessment with Reasoning, Grounding and Referring","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11789","citing_title":"LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07141","citing_title":"Qwen3-VL-Seg: Unlocking Open-World Referring Segmentation with Vision-Language Grounding","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V7YL6T5NAS5YNZJH26QJU6YX7K","json":"https://pith.science/pith/V7YL6T5NAS5YNZJH26QJU6YX7K.json","graph_json":"https://pith.science/api/pith-number/V7YL6T5NAS5YNZJH26QJU6YX7K/graph.json","events_json":"https://pith.science/api/pith-number/V7YL6T5NAS5YNZJH26QJU6YX7K/events.json","paper":"https://pith.science/paper/V7YL6T5N"},"agent_actions":{"view_html":"https://pith.science/pith/V7YL6T5NAS5YNZJH26QJU6YX7K","download_json":"https://pith.science/pith/V7YL6T5NAS5YNZJH26QJU6YX7K.json","view_paper":"https://pith.science/paper/V7YL6T5N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09855&json=true","fetch_graph":"https://pith.science/api/pith-number/V7YL6T5NAS5YNZJH26QJU6YX7K/graph.json","fetch_events":"https://pith.science/api/pith-number/V7YL6T5NAS5YNZJH26QJU6YX7K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V7YL6T5NAS5YNZJH26QJU6YX7K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V7YL6T5NAS5YNZJH26QJU6YX7K/action/storage_attestation","attest_author":"https://pith.science/pith/V7YL6T5NAS5YNZJH26QJU6YX7K/action/author_attestation","sign_citation":"https://pith.science/pith/V7YL6T5NAS5YNZJH26QJU6YX7K/action/citation_signature","submit_replication":"https://pith.science/pith/V7YL6T5NAS5YNZJH26QJU6YX7K/action/replication_record"}},"created_at":"2026-07-05T10:15:20.365376+00:00","updated_at":"2026-07-05T10:15:20.365376+00:00"}