{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:V7YL6T5NAS5YNZJH26QJU6YX7K","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":"a1e1e6370a5c1d4e535b71c10fbe0a52827ae8b93355fa929dcf2fb3cd0671c8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-13T14:28:16Z","title_canon_sha256":"ecbd1aa34b6013db93d73581c4baaa1348fb7a535e70f2eb60ae7032945d9025"},"schema_version":"1.0","source":{"id":"2410.09855","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09855","created_at":"2026-07-05T10:15:20Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09855v2","created_at":"2026-07-05T10:15:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09855","created_at":"2026-07-05T10:15:20Z"},{"alias_kind":"pith_short_12","alias_value":"V7YL6T5NAS5Y","created_at":"2026-07-05T10:15:20Z"},{"alias_kind":"pith_short_16","alias_value":"V7YL6T5NAS5YNZJH","created_at":"2026-07-05T10:15:20Z"},{"alias_kind":"pith_short_8","alias_value":"V7YL6T5N","created_at":"2026-07-05T10:15:20Z"}],"graph_snapshots":[{"event_id":"sha256:ceb2bc8027cdebe533d907145e0f9a91adf10104edd67cea7c12c12264cbadcf","target":"graph","created_at":"2026-07-05T10:15:20Z","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/2410.09855/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chaofeng Chen, Jiaxing Xu, Litong Feng, Mengcheng Lan, Wayne Zhang, Xinjiang Wang, Yiping Ke, Yue Zhou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-13T14:28:16Z","title":"Text4Seg: Reimagining Image Segmentation as Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09855","kind":"arxiv","version":2},"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:fbd8f7197d2dc4c572b8f5c37f6563c7886b76804ae3bc62e0d7427afee485c5","target":"record","created_at":"2026-07-05T10:15:20Z","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":"a1e1e6370a5c1d4e535b71c10fbe0a52827ae8b93355fa929dcf2fb3cd0671c8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-13T14:28:16Z","title_canon_sha256":"ecbd1aa34b6013db93d73581c4baaa1348fb7a535e70f2eb60ae7032945d9025"},"schema_version":"1.0","source":{"id":"2410.09855","kind":"arxiv","version":2}},"canonical_sha256":"aff0bf4fad04bb86e527d7a09a7b17fa9e9fae74b48e82fc796413b49d3c484c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aff0bf4fad04bb86e527d7a09a7b17fa9e9fae74b48e82fc796413b49d3c484c","first_computed_at":"2026-07-05T10:15:20.365305Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:15:20.365305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6Zwp17HJHOU+HN6zLm2yySSZyR0YN9qIdrqMQ3h5l+C68rMlNMAxBkMlTMLwjIOmzzIKRCgUU3Jk38BXXPpYAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:15:20.365807Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.09855","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fbd8f7197d2dc4c572b8f5c37f6563c7886b76804ae3bc62e0d7427afee485c5","sha256:ceb2bc8027cdebe533d907145e0f9a91adf10104edd67cea7c12c12264cbadcf"],"state_sha256":"d5c89557678ebdeb02e44b9a2b2670e4a4546180dc3eed5eff8e80faeb7133ab"}