{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P3IBQU7WRXFJZ4MULUBJUBDRDL","short_pith_number":"pith:P3IBQU7W","schema_version":"1.0","canonical_sha256":"7ed01853f68dca9cf1945d029a04711ad08291765602c7c88171eb441caa3f1e","source":{"kind":"arxiv","id":"2506.02975","version":1},"attestation_state":"computed","paper":{"title":"HaploOmni: Unified Single Transformer for Multimodal Video Understanding and Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Cheng cheng, Lin Song, Rui Yang, Xiu Li, Yicheng Xiao, Ying Shan, Yixiao Ge, Zhaoyang Zhang, Zunnan Xu","submitted_at":"2025-06-03T15:14:00Z","abstract_excerpt":"With the advancement of language models, unified multimodal understanding and generation have made significant strides, with model architectures evolving from separated components to unified single-model frameworks. This paper explores an efficient training paradigm to build a single transformer for unified multimodal understanding and generation. Specifically, we propose a multimodal warmup strategy utilizing prior knowledge to extend capabilities. To address cross-modal compatibility challenges, we introduce feature pre-scaling and multimodal AdaLN techniques. Integrating the proposed techno"},"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":"2506.02975","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T15:14:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b020c486cf94a24655222e6df5217e27585e6ae0f783f66dd37bfe0fb8aa49a0","abstract_canon_sha256":"4c071e083bd32407b9302ae2e74e7a87513d0377e869037b211a2eb348dfa693"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:12.803279Z","signature_b64":"vwSKAV87ZPB6KYQLuSL2swxOtABQKuQekxJrAkyU2z0V9bLzaEVoo+wYODQpkxNWE+XFG+7U+qH5boNp5RlbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ed01853f68dca9cf1945d029a04711ad08291765602c7c88171eb441caa3f1e","last_reissued_at":"2026-07-05T11:15:12.802855Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:12.802855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HaploOmni: Unified Single Transformer for Multimodal Video Understanding and Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Cheng cheng, Lin Song, Rui Yang, Xiu Li, Yicheng Xiao, Ying Shan, Yixiao Ge, Zhaoyang Zhang, Zunnan Xu","submitted_at":"2025-06-03T15:14:00Z","abstract_excerpt":"With the advancement of language models, unified multimodal understanding and generation have made significant strides, with model architectures evolving from separated components to unified single-model frameworks. This paper explores an efficient training paradigm to build a single transformer for unified multimodal understanding and generation. Specifically, we propose a multimodal warmup strategy utilizing prior knowledge to extend capabilities. To address cross-modal compatibility challenges, we introduce feature pre-scaling and multimodal AdaLN techniques. Integrating the proposed techno"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02975","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/2506.02975/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":"2506.02975","created_at":"2026-07-05T11:15:12.802913+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02975v1","created_at":"2026-07-05T11:15:12.802913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02975","created_at":"2026-07-05T11:15:12.802913+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3IBQU7WRXFJ","created_at":"2026-07-05T11:15:12.802913+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3IBQU7WRXFJZ4MU","created_at":"2026-07-05T11:15:12.802913+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3IBQU7W","created_at":"2026-07-05T11:15:12.802913+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13289","citing_title":"HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers","ref_index":206,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31326","citing_title":"Bridging Video Understanding and Generation in a Unified Framework","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18678","citing_title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","ref_index":134,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18678","citing_title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","ref_index":133,"is_internal_anchor":false},{"citing_arxiv_id":"2506.15564","citing_title":"Show-o2: Improved Native Unified Multimodal Models","ref_index":124,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P3IBQU7WRXFJZ4MULUBJUBDRDL","json":"https://pith.science/pith/P3IBQU7WRXFJZ4MULUBJUBDRDL.json","graph_json":"https://pith.science/api/pith-number/P3IBQU7WRXFJZ4MULUBJUBDRDL/graph.json","events_json":"https://pith.science/api/pith-number/P3IBQU7WRXFJZ4MULUBJUBDRDL/events.json","paper":"https://pith.science/paper/P3IBQU7W"},"agent_actions":{"view_html":"https://pith.science/pith/P3IBQU7WRXFJZ4MULUBJUBDRDL","download_json":"https://pith.science/pith/P3IBQU7WRXFJZ4MULUBJUBDRDL.json","view_paper":"https://pith.science/paper/P3IBQU7W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02975&json=true","fetch_graph":"https://pith.science/api/pith-number/P3IBQU7WRXFJZ4MULUBJUBDRDL/graph.json","fetch_events":"https://pith.science/api/pith-number/P3IBQU7WRXFJZ4MULUBJUBDRDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3IBQU7WRXFJZ4MULUBJUBDRDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3IBQU7WRXFJZ4MULUBJUBDRDL/action/storage_attestation","attest_author":"https://pith.science/pith/P3IBQU7WRXFJZ4MULUBJUBDRDL/action/author_attestation","sign_citation":"https://pith.science/pith/P3IBQU7WRXFJZ4MULUBJUBDRDL/action/citation_signature","submit_replication":"https://pith.science/pith/P3IBQU7WRXFJZ4MULUBJUBDRDL/action/replication_record"}},"created_at":"2026-07-05T11:15:12.802913+00:00","updated_at":"2026-07-05T11:15:12.802913+00:00"}