{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NFLRSKYGVVF723VWT7GDU4OFFQ","short_pith_number":"pith:NFLRSKYG","schema_version":"1.0","canonical_sha256":"6957192b06ad4bfd6eb69fcc3a71c52c144f7924a80c53d908d3df2afafc4f33","source":{"kind":"arxiv","id":"2305.11172","version":1},"attestation_state":"computed","paper":{"title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Chang Zhou, Jingren Zhou, Junyang Lin, Peng Wang, Shijie Wang, Shuai Bai, Xiaohuan Zhou, Xinggang Wang","submitted_at":"2023-05-18T17:59:06Z","abstract_excerpt":"In this work, we explore a scalable way for building a general representation model toward unlimited modalities. We release ONE-PEACE, a highly extensible model with 4B parameters that can seamlessly align and integrate representations across vision, audio, and language modalities. The architecture of ONE-PEACE comprises modality adapters, shared self-attention layers, and modality FFNs. This design allows for the easy extension of new modalities by adding adapters and FFNs, while also enabling multi-modal fusion through self-attention layers. To pretrain ONE-PEACE, we develop two modality-agn"},"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":"2305.11172","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-18T17:59:06Z","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"title_canon_sha256":"dfc2a777c0f9c30f39dcf4af583509c421286ab29ea146f6eb812ab24c3944e8","abstract_canon_sha256":"e81f8cbf5a40a21cf5ec0319753c7fc1fa99db0a4abc6cefb224db67a87d6fe0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:31.093045Z","signature_b64":"B20X2APLi7p7LvpOlcn6xL2fW8EqJ7yw7i4QRFYBXwJ9OhcY227Cs/7ww6fX9K7VMg40UKJ8UvLlGxL6E6waCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6957192b06ad4bfd6eb69fcc3a71c52c144f7924a80c53d908d3df2afafc4f33","last_reissued_at":"2026-07-05T06:11:31.092566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:31.092566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Chang Zhou, Jingren Zhou, Junyang Lin, Peng Wang, Shijie Wang, Shuai Bai, Xiaohuan Zhou, Xinggang Wang","submitted_at":"2023-05-18T17:59:06Z","abstract_excerpt":"In this work, we explore a scalable way for building a general representation model toward unlimited modalities. We release ONE-PEACE, a highly extensible model with 4B parameters that can seamlessly align and integrate representations across vision, audio, and language modalities. The architecture of ONE-PEACE comprises modality adapters, shared self-attention layers, and modality FFNs. This design allows for the easy extension of new modalities by adding adapters and FFNs, while also enabling multi-modal fusion through self-attention layers. To pretrain ONE-PEACE, we develop two modality-agn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11172","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/2305.11172/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":"2305.11172","created_at":"2026-07-05T06:11:31.092626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11172v1","created_at":"2026-07-05T06:11:31.092626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11172","created_at":"2026-07-05T06:11:31.092626+00:00"},{"alias_kind":"pith_short_12","alias_value":"NFLRSKYGVVF7","created_at":"2026-07-05T06:11:31.092626+00:00"},{"alias_kind":"pith_short_16","alias_value":"NFLRSKYGVVF723VW","created_at":"2026-07-05T06:11:31.092626+00:00"},{"alias_kind":"pith_short_8","alias_value":"NFLRSKYG","created_at":"2026-07-05T06:11:31.092626+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17030","citing_title":"Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation","ref_index":117,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30307","citing_title":"Grounded 3D-Aware Spatial Vision-Language Modeling","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2412.16855","citing_title":"GME: Improving Universal Multimodal Retrieval by Multimodal LLMs","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2312.14238","citing_title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","ref_index":144,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11043","citing_title":"EmergentBridge: Improving Zero-Shot Cross-Modal Transfer in Unified Multimodal Embedding Models","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2412.10302","citing_title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11043","citing_title":"EmergentBridge: Improving Zero-Shot Cross-Modal Transfer in Unified Multimodal Embedding Models","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07763","citing_title":"Beyond Surface Artifacts: Capturing Shared Latent Forgery Knowledge Across Modalities","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07175","citing_title":"Multiple Domain Generalization Using Category Information Independent of Domain Differences","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2504.10479","citing_title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","ref_index":123,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":248,"is_internal_anchor":false},{"citing_arxiv_id":"2508.18265","citing_title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","ref_index":140,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17889","citing_title":"AeroRAG: Structured Multimodal Retrieval-Augmented LLM for Fine-Grained Aerial Visual Reasoning","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NFLRSKYGVVF723VWT7GDU4OFFQ","json":"https://pith.science/pith/NFLRSKYGVVF723VWT7GDU4OFFQ.json","graph_json":"https://pith.science/api/pith-number/NFLRSKYGVVF723VWT7GDU4OFFQ/graph.json","events_json":"https://pith.science/api/pith-number/NFLRSKYGVVF723VWT7GDU4OFFQ/events.json","paper":"https://pith.science/paper/NFLRSKYG"},"agent_actions":{"view_html":"https://pith.science/pith/NFLRSKYGVVF723VWT7GDU4OFFQ","download_json":"https://pith.science/pith/NFLRSKYGVVF723VWT7GDU4OFFQ.json","view_paper":"https://pith.science/paper/NFLRSKYG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11172&json=true","fetch_graph":"https://pith.science/api/pith-number/NFLRSKYGVVF723VWT7GDU4OFFQ/graph.json","fetch_events":"https://pith.science/api/pith-number/NFLRSKYGVVF723VWT7GDU4OFFQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NFLRSKYGVVF723VWT7GDU4OFFQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NFLRSKYGVVF723VWT7GDU4OFFQ/action/storage_attestation","attest_author":"https://pith.science/pith/NFLRSKYGVVF723VWT7GDU4OFFQ/action/author_attestation","sign_citation":"https://pith.science/pith/NFLRSKYGVVF723VWT7GDU4OFFQ/action/citation_signature","submit_replication":"https://pith.science/pith/NFLRSKYGVVF723VWT7GDU4OFFQ/action/replication_record"}},"created_at":"2026-07-05T06:11:31.092626+00:00","updated_at":"2026-07-05T06:11:31.092626+00:00"}