{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U3XBPZDYKECVDSP7E7JM2H54ED","short_pith_number":"pith:U3XBPZDY","schema_version":"1.0","canonical_sha256":"a6ee17e478510551c9ff27d2cd1fbc20dada203271de22d6442710499e75565f","source":{"kind":"arxiv","id":"2505.19422","version":1},"attestation_state":"computed","paper":{"title":"LlamaSeg: Image Segmentation via Autoregressive Mask Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiru Deng, Tengjin Weng, Tianyu Yang, Wenhan Luo, Wenhao Jiang, Zhiheng Li","submitted_at":"2025-05-26T02:22:41Z","abstract_excerpt":"We present LlamaSeg, a visual autoregressive framework that unifies multiple image segmentation tasks via natural language instructions. We reformulate image segmentation as a visual generation problem, representing masks as \"visual\" tokens and employing a LLaMA-style Transformer to predict them directly from image inputs. By adhering to the next-token prediction paradigm, our approach naturally integrates segmentation tasks into autoregressive architectures. To support large-scale training, we introduce a data annotation pipeline and construct the SA-OVRS dataset, which contains 2M segmentati"},"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":"2505.19422","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T02:22:41Z","cross_cats_sorted":[],"title_canon_sha256":"c244ed82e0ce0589e0937d653dc2e2fcdb115716f9f195ae80fe3cd2c0663d01","abstract_canon_sha256":"ea91947b767fd5c9f12743a5db67a8ef23a5d8160e68117ca19df812f64b988b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:30.023788Z","signature_b64":"eIqIGDb9rg5+B3E+toOOscOJvTFbGQwKLc/801bxQUVrjntM5DhAmmOrDHSDZxJt6+NQoRgy4Lg34FlwLlK+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6ee17e478510551c9ff27d2cd1fbc20dada203271de22d6442710499e75565f","last_reissued_at":"2026-07-05T11:09:30.023268Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:30.023268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LlamaSeg: Image Segmentation via Autoregressive Mask Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiru Deng, Tengjin Weng, Tianyu Yang, Wenhan Luo, Wenhao Jiang, Zhiheng Li","submitted_at":"2025-05-26T02:22:41Z","abstract_excerpt":"We present LlamaSeg, a visual autoregressive framework that unifies multiple image segmentation tasks via natural language instructions. We reformulate image segmentation as a visual generation problem, representing masks as \"visual\" tokens and employing a LLaMA-style Transformer to predict them directly from image inputs. By adhering to the next-token prediction paradigm, our approach naturally integrates segmentation tasks into autoregressive architectures. To support large-scale training, we introduce a data annotation pipeline and construct the SA-OVRS dataset, which contains 2M segmentati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19422","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/2505.19422/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":"2505.19422","created_at":"2026-07-05T11:09:30.023335+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19422v1","created_at":"2026-07-05T11:09:30.023335+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19422","created_at":"2026-07-05T11:09:30.023335+00:00"},{"alias_kind":"pith_short_12","alias_value":"U3XBPZDYKECV","created_at":"2026-07-05T11:09:30.023335+00:00"},{"alias_kind":"pith_short_16","alias_value":"U3XBPZDYKECVDSP7","created_at":"2026-07-05T11:09:30.023335+00:00"},{"alias_kind":"pith_short_8","alias_value":"U3XBPZDY","created_at":"2026-07-05T11:09:30.023335+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"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":107,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22660","citing_title":"Prompting Diffusion Models for Zero-Shot Instance Segmentation","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2607.00015","citing_title":"Towards an automated AI-based framework for floor plan compliance checks for residential buildings","ref_index":90,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U3XBPZDYKECVDSP7E7JM2H54ED","json":"https://pith.science/pith/U3XBPZDYKECVDSP7E7JM2H54ED.json","graph_json":"https://pith.science/api/pith-number/U3XBPZDYKECVDSP7E7JM2H54ED/graph.json","events_json":"https://pith.science/api/pith-number/U3XBPZDYKECVDSP7E7JM2H54ED/events.json","paper":"https://pith.science/paper/U3XBPZDY"},"agent_actions":{"view_html":"https://pith.science/pith/U3XBPZDYKECVDSP7E7JM2H54ED","download_json":"https://pith.science/pith/U3XBPZDYKECVDSP7E7JM2H54ED.json","view_paper":"https://pith.science/paper/U3XBPZDY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19422&json=true","fetch_graph":"https://pith.science/api/pith-number/U3XBPZDYKECVDSP7E7JM2H54ED/graph.json","fetch_events":"https://pith.science/api/pith-number/U3XBPZDYKECVDSP7E7JM2H54ED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U3XBPZDYKECVDSP7E7JM2H54ED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U3XBPZDYKECVDSP7E7JM2H54ED/action/storage_attestation","attest_author":"https://pith.science/pith/U3XBPZDYKECVDSP7E7JM2H54ED/action/author_attestation","sign_citation":"https://pith.science/pith/U3XBPZDYKECVDSP7E7JM2H54ED/action/citation_signature","submit_replication":"https://pith.science/pith/U3XBPZDYKECVDSP7E7JM2H54ED/action/replication_record"}},"created_at":"2026-07-05T11:09:30.023335+00:00","updated_at":"2026-07-05T11:09:30.023335+00:00"}