{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MEQUU3QYJCNJ6FX77N6AHTDMKP","short_pith_number":"pith:MEQUU3QY","schema_version":"1.0","canonical_sha256":"61214a6e18489a9f16fffb7c03cc6c53c7c1bb55fd4eb1e4f239dfb0c12a6ec7","source":{"kind":"arxiv","id":"2312.02228","version":3},"attestation_state":"computed","paper":{"title":"PixelLM: Pixel Reasoning with Large Multimodal Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongmei Fu, Jiashi Feng, Xiaojie Jin, Yao Zhao, Yunchao Wei, Zhicheng Huang, Zhongwei Ren","submitted_at":"2023-12-04T03:05:59Z","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"},"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":"2312.02228","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T03:05:59Z","cross_cats_sorted":[],"title_canon_sha256":"25507d0d1850cd17a89d8c2db51816944365e5a76ad033d83fa28b0187661206","abstract_canon_sha256":"780d2b05519e966e9780ef523ceeaece1c8bd7b468901b70e00537e67b0bee89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:23.901166Z","signature_b64":"3uDyX7lbCD9ju0PXC3lPrIol8p9Soz9TI2Mye4ycdTO8oertF9K10rZFJwXB0cb/7IauRGlmbO8H8Sbykc9pDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61214a6e18489a9f16fffb7c03cc6c53c7c1bb55fd4eb1e4f239dfb0c12a6ec7","last_reissued_at":"2026-07-05T08:45:23.900733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:23.900733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PixelLM: Pixel Reasoning with Large Multimodal Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongmei Fu, Jiashi Feng, Xiaojie Jin, Yao Zhao, Yunchao Wei, Zhicheng Huang, Zhongwei Ren","submitted_at":"2023-12-04T03:05:59Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02228","kind":"arxiv","version":3},"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/2312.02228/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":"2312.02228","created_at":"2026-07-05T08:45:23.900793+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.02228v3","created_at":"2026-07-05T08:45:23.900793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02228","created_at":"2026-07-05T08:45:23.900793+00:00"},{"alias_kind":"pith_short_12","alias_value":"MEQUU3QYJCNJ","created_at":"2026-07-05T08:45:23.900793+00:00"},{"alias_kind":"pith_short_16","alias_value":"MEQUU3QYJCNJ6FX7","created_at":"2026-07-05T08:45:23.900793+00:00"},{"alias_kind":"pith_short_8","alias_value":"MEQUU3QY","created_at":"2026-07-05T08:45:23.900793+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12195","citing_title":"InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning","ref_index":159,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19410","citing_title":"Vision Harnessing Agent for Open Ad-hoc Segmentation","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2509.13484","citing_title":"MINGLE: VLMs for Semantically Complex Region Detection in Urban Scenes","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MEQUU3QYJCNJ6FX77N6AHTDMKP","json":"https://pith.science/pith/MEQUU3QYJCNJ6FX77N6AHTDMKP.json","graph_json":"https://pith.science/api/pith-number/MEQUU3QYJCNJ6FX77N6AHTDMKP/graph.json","events_json":"https://pith.science/api/pith-number/MEQUU3QYJCNJ6FX77N6AHTDMKP/events.json","paper":"https://pith.science/paper/MEQUU3QY"},"agent_actions":{"view_html":"https://pith.science/pith/MEQUU3QYJCNJ6FX77N6AHTDMKP","download_json":"https://pith.science/pith/MEQUU3QYJCNJ6FX77N6AHTDMKP.json","view_paper":"https://pith.science/paper/MEQUU3QY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.02228&json=true","fetch_graph":"https://pith.science/api/pith-number/MEQUU3QYJCNJ6FX77N6AHTDMKP/graph.json","fetch_events":"https://pith.science/api/pith-number/MEQUU3QYJCNJ6FX77N6AHTDMKP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MEQUU3QYJCNJ6FX77N6AHTDMKP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MEQUU3QYJCNJ6FX77N6AHTDMKP/action/storage_attestation","attest_author":"https://pith.science/pith/MEQUU3QYJCNJ6FX77N6AHTDMKP/action/author_attestation","sign_citation":"https://pith.science/pith/MEQUU3QYJCNJ6FX77N6AHTDMKP/action/citation_signature","submit_replication":"https://pith.science/pith/MEQUU3QYJCNJ6FX77N6AHTDMKP/action/replication_record"}},"created_at":"2026-07-05T08:45:23.900793+00:00","updated_at":"2026-07-05T08:45:23.900793+00:00"}