{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YS4BFZQHLYBN5Y3Z7IJ5LUJ5Y5","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":"dc231d4a09af59ce4dbdb121742cc695c1c340b2c4e296683a682311ee0208f6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-15T02:54:31Z","title_canon_sha256":"b20d42b050aabf3c124a87abeea5f556b542055ce608090ced5108cb864a55ff"},"schema_version":"1.0","source":{"id":"2312.10103","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.10103","created_at":"2026-07-05T07:58:46Z"},{"alias_kind":"arxiv_version","alias_value":"2312.10103v3","created_at":"2026-07-05T07:58:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10103","created_at":"2026-07-05T07:58:46Z"},{"alias_kind":"pith_short_12","alias_value":"YS4BFZQHLYBN","created_at":"2026-07-05T07:58:46Z"},{"alias_kind":"pith_short_16","alias_value":"YS4BFZQHLYBN5Y3Z","created_at":"2026-07-05T07:58:46Z"},{"alias_kind":"pith_short_8","alias_value":"YS4BFZQH","created_at":"2026-07-05T07:58:46Z"}],"graph_snapshots":[{"event_id":"sha256:2e51a01bcf4205d1c606625ecae0a7478bee6ec9be69a1edc961f77e9929d1cb","target":"graph","created_at":"2026-07-05T07:58:46Z","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/2312.10103/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generalized Referring Expression Segmentation (GRES) extends the scope of classic RES to refer to multiple objects in one expression or identify the empty targets absent in the image. GRES poses challenges in modeling the complex spatial relationships of the instances in the image and identifying non-existing referents. Multimodal Large Language Models (MLLMs) have recently shown tremendous progress in these complicated vision-language tasks. Connecting Large Language Models (LLMs) and vision models, MLLMs are proficient in understanding contexts with visual inputs. Among them, LISA, as a repr","authors_text":"Dongchen Han, Gao Huang, Shiji Song, Xuran Pan, Yizeng Han, Zhuofan Xia","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-15T02:54:31Z","title":"GSVA: Generalized Segmentation via Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10103","kind":"arxiv","version":3},"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":"sha256:6e675da7ca9d7ae354f23e7e5d02adb6b1b07dabb48abe4a074a3160d7a37083","target":"record","created_at":"2026-07-05T07:58:46Z","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":"dc231d4a09af59ce4dbdb121742cc695c1c340b2c4e296683a682311ee0208f6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-15T02:54:31Z","title_canon_sha256":"b20d42b050aabf3c124a87abeea5f556b542055ce608090ced5108cb864a55ff"},"schema_version":"1.0","source":{"id":"2312.10103","kind":"arxiv","version":3}},"canonical_sha256":"c4b812e6075e02dee379fa13d5d13dc7486bc4a95c7213cbe42f4a60a96316f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4b812e6075e02dee379fa13d5d13dc7486bc4a95c7213cbe42f4a60a96316f9","first_computed_at":"2026-07-05T07:58:46.484179Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:58:46.484179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ygo5QB8bevSrya1ZLQ//1Ua7NUOTgJkJB40Ew5i5CJtXNA9F8cABXsI14jjb3eoJWw29u5AY0hvl24rimNcAAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:58:46.484743Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.10103","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e675da7ca9d7ae354f23e7e5d02adb6b1b07dabb48abe4a074a3160d7a37083","sha256:2e51a01bcf4205d1c606625ecae0a7478bee6ec9be69a1edc961f77e9929d1cb"],"state_sha256":"c4d3ecb5976de5bfaf25b9221cf9efb1c9e939d9cb5e5995ed88cd95f6e66315"}