{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MEQUU3QYJCNJ6FX77N6AHTDMKP","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":"780d2b05519e966e9780ef523ceeaece1c8bd7b468901b70e00537e67b0bee89","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T03:05:59Z","title_canon_sha256":"25507d0d1850cd17a89d8c2db51816944365e5a76ad033d83fa28b0187661206"},"schema_version":"1.0","source":{"id":"2312.02228","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.02228","created_at":"2026-07-05T08:45:23Z"},{"alias_kind":"arxiv_version","alias_value":"2312.02228v3","created_at":"2026-07-05T08:45:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02228","created_at":"2026-07-05T08:45:23Z"},{"alias_kind":"pith_short_12","alias_value":"MEQUU3QYJCNJ","created_at":"2026-07-05T08:45:23Z"},{"alias_kind":"pith_short_16","alias_value":"MEQUU3QYJCNJ6FX7","created_at":"2026-07-05T08:45:23Z"},{"alias_kind":"pith_short_8","alias_value":"MEQUU3QY","created_at":"2026-07-05T08:45:23Z"}],"graph_snapshots":[{"event_id":"sha256:9a55f2dda4201a6ae54b76fc4aeb0ff7ef956cb3dd9a9295305123025f4713cc","target":"graph","created_at":"2026-07-05T08:45:23Z","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/2312.02228/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While large multimodal models (LMMs) have achieved remarkable progress, generating pixel-level masks for image reasoning tasks involving multiple open-world targets remains a challenge. To bridge this gap, we introduce PixelLM, an effective and efficient LMM for pixel-level reasoning and understanding. Central to PixelLM is a novel, lightweight pixel decoder and a comprehensive segmentation codebook. The decoder efficiently produces masks from the hidden embeddings of the codebook tokens, which encode detailed target-relevant information. With this design, PixelLM harmonizes with the structure","authors_text":"Dongmei Fu, Jiashi Feng, Xiaojie Jin, Yao Zhao, Yunchao Wei, Zhicheng Huang, Zhongwei Ren","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T03:05:59Z","title":"PixelLM: Pixel Reasoning with Large Multimodal Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02228","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":"sha256:94a44bb41d8d9e9e79f44b0bb650b3ffbbaee08f310838a13b5c23c945f35243","target":"record","created_at":"2026-07-05T08:45:23Z","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":"780d2b05519e966e9780ef523ceeaece1c8bd7b468901b70e00537e67b0bee89","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T03:05:59Z","title_canon_sha256":"25507d0d1850cd17a89d8c2db51816944365e5a76ad033d83fa28b0187661206"},"schema_version":"1.0","source":{"id":"2312.02228","kind":"arxiv","version":3}},"canonical_sha256":"61214a6e18489a9f16fffb7c03cc6c53c7c1bb55fd4eb1e4f239dfb0c12a6ec7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61214a6e18489a9f16fffb7c03cc6c53c7c1bb55fd4eb1e4f239dfb0c12a6ec7","first_computed_at":"2026-07-05T08:45:23.900733Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:23.900733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3uDyX7lbCD9ju0PXC3lPrIol8p9Soz9TI2Mye4ycdTO8oertF9K10rZFJwXB0cb/7IauRGlmbO8H8Sbykc9pDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:23.901166Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.02228","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94a44bb41d8d9e9e79f44b0bb650b3ffbbaee08f310838a13b5c23c945f35243","sha256:9a55f2dda4201a6ae54b76fc4aeb0ff7ef956cb3dd9a9295305123025f4713cc"],"state_sha256":"13c032d274b232e4a179bc34667a81332878550d22c46f8e062900458d50720b"}