{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:62I7DRKXXLPTPYMT4F3P5AIXZR","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":"f2efab83fd12dc9ee8f7a0b7a3ed54c052e8063a893b58d286b47b74b00a4999","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T05:36:25Z","title_canon_sha256":"5294ab218ffd32a57c6a8b2d4274e3050bc2a534eb53d406aa0e171e229940a7"},"schema_version":"1.0","source":{"id":"2403.14141","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.14141","created_at":"2026-07-05T07:58:54Z"},{"alias_kind":"arxiv_version","alias_value":"2403.14141v1","created_at":"2026-07-05T07:58:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14141","created_at":"2026-07-05T07:58:54Z"},{"alias_kind":"pith_short_12","alias_value":"62I7DRKXXLPT","created_at":"2026-07-05T07:58:54Z"},{"alias_kind":"pith_short_16","alias_value":"62I7DRKXXLPTPYMT","created_at":"2026-07-05T07:58:54Z"},{"alias_kind":"pith_short_8","alias_value":"62I7DRKX","created_at":"2026-07-05T07:58:54Z"}],"graph_snapshots":[{"event_id":"sha256:da8d8dcb60dca1c962ff40b673207808761bbf2f36dd7c68363c14e54853c6e2","target":"graph","created_at":"2026-07-05T07:58:54Z","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/2403.14141/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal large language models (MLLMs) can understand image-language prompts and demonstrate impressive reasoning ability. In this paper, we extend MLLMs' output by empowering MLLMs with the segmentation ability. The extended MLLMs can both output language responses to the image-language prompts and segment the regions that the complex question or query in the language prompts focuses on. To this end, the existing work, LISA, enlarges the original word embeddings with an additional segment token and fine-tunes dialogue generation and query-focused segmentation together, where the feature of","authors_text":"Bo Li, Hao Zhang, Jing Wang, Jinwei Chen, Kai Zhao, Peng-Tao Jiang, Yuqi Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T05:36:25Z","title":"Empowering Segmentation Ability to Multi-modal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14141","kind":"arxiv","version":1},"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":"sha256:5143556578e2992f4764d5db6fff114f3e2238e8c674dadcf0f4271014d39bd5","target":"record","created_at":"2026-07-05T07:58:54Z","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":"f2efab83fd12dc9ee8f7a0b7a3ed54c052e8063a893b58d286b47b74b00a4999","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T05:36:25Z","title_canon_sha256":"5294ab218ffd32a57c6a8b2d4274e3050bc2a534eb53d406aa0e171e229940a7"},"schema_version":"1.0","source":{"id":"2403.14141","kind":"arxiv","version":1}},"canonical_sha256":"f691f1c557badf37e193e176fe8117cc4bed66cdb37ddd1955a5b7d1c362399c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f691f1c557badf37e193e176fe8117cc4bed66cdb37ddd1955a5b7d1c362399c","first_computed_at":"2026-07-05T07:58:54.992016Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:58:54.992016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uPan5qlkf5yJKDqZYUGDv0GSh3wS7CsdRtvQMEJnT/COJtHq9Ams69sHePrORlsvLhlrmMWUj/d88SyqR9qyBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:58:54.992425Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.14141","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5143556578e2992f4764d5db6fff114f3e2238e8c674dadcf0f4271014d39bd5","sha256:da8d8dcb60dca1c962ff40b673207808761bbf2f36dd7c68363c14e54853c6e2"],"state_sha256":"e474f890225a3fd130f58226b58081aad64b14f853688b1dd9878e64f684e813"}