{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CU7RBPWBK4CQEILSCW7XVACKSY","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":"dfa51f464f94b4f93b696e3a11dc4b58fff6230661dd8bbbcf1ff599e16cbd66","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T18:56:24Z","title_canon_sha256":"4fcf04f9d183675524ebe4f8195841490ab382ee866e9184c31bf81e91a00162"},"schema_version":"1.0","source":{"id":"2412.15188","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15188","created_at":"2026-07-05T10:09:50Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15188v4","created_at":"2026-07-05T10:09:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15188","created_at":"2026-07-05T10:09:50Z"},{"alias_kind":"pith_short_12","alias_value":"CU7RBPWBK4CQ","created_at":"2026-07-05T10:09:50Z"},{"alias_kind":"pith_short_16","alias_value":"CU7RBPWBK4CQEILS","created_at":"2026-07-05T10:09:50Z"},{"alias_kind":"pith_short_8","alias_value":"CU7RBPWB","created_at":"2026-07-05T10:09:50Z"}],"graph_snapshots":[{"event_id":"sha256:7d9cef8a324234803b196dabdab9865b488908928d4994dc2a9bc0cb3d3b8d13","target":"graph","created_at":"2026-07-05T10:09:50Z","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/2412.15188/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present LMFusion, a framework for empowering pretrained text-only large language models (LLMs) with multimodal generative capabilities, enabling them to understand and generate both text and images in arbitrary sequences. LMFusion leverages existing Llama-3's weights for processing texts autoregressively while introducing additional and parallel transformer modules for processing images with diffusion. During training, the data from each modality is routed to its dedicated modules: modality-specific feedforward layers, query-key-value projections, and normalization layers process each modal","authors_text":"Chunting Zhou, Lili Yu, Luke Zettlemoyer, Weijia Shi, Weixin Liang, Xiaochuang Han, Xi Victoria Lin","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T18:56:24Z","title":"LMFusion: Adapting Pretrained Language Models for Multimodal Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15188","kind":"arxiv","version":4},"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:de913f995619c6a0a1c52696ec6189216668d5d87a4e9eb5818d6d6c9b6dc008","target":"record","created_at":"2026-07-05T10:09:50Z","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":"dfa51f464f94b4f93b696e3a11dc4b58fff6230661dd8bbbcf1ff599e16cbd66","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T18:56:24Z","title_canon_sha256":"4fcf04f9d183675524ebe4f8195841490ab382ee866e9184c31bf81e91a00162"},"schema_version":"1.0","source":{"id":"2412.15188","kind":"arxiv","version":4}},"canonical_sha256":"153f10bec1570502217215bf7a804a96312678628318a8b2039f53ccd4e44a7d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"153f10bec1570502217215bf7a804a96312678628318a8b2039f53ccd4e44a7d","first_computed_at":"2026-07-05T10:09:50.792050Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:50.792050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nHSFS/ohrMEHZG6//CtCcRe1WtqvyEacY55FMth36qb1evLT2kQEYygwWaXnnZQ1e/dqLeLNfBv5+eh++GqyDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:50.792598Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15188","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de913f995619c6a0a1c52696ec6189216668d5d87a4e9eb5818d6d6c9b6dc008","sha256:7d9cef8a324234803b196dabdab9865b488908928d4994dc2a9bc0cb3d3b8d13"],"state_sha256":"c56ba6b84ef8ede5c4a6f8cd23dd63da9058f7cc9a021c64e6369846305851dd"}