{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QGA2SARJKR5ALBUUTGOHTN26ZV","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":"9a5c097831ec29ae1ca5ff2bc87374366b1f776cbfa49634c2c02f250c7d6bc2","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-10T00:20:06Z","title_canon_sha256":"b75341c4e25d15dddf2a6bc0dcd2d868af74b204af32d1d64ca7477650150207"},"schema_version":"1.0","source":{"id":"2301.03728","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.03728","created_at":"2026-07-05T05:32:05Z"},{"alias_kind":"arxiv_version","alias_value":"2301.03728v1","created_at":"2026-07-05T05:32:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.03728","created_at":"2026-07-05T05:32:05Z"},{"alias_kind":"pith_short_12","alias_value":"QGA2SARJKR5A","created_at":"2026-07-05T05:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"QGA2SARJKR5ALBUU","created_at":"2026-07-05T05:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"QGA2SARJ","created_at":"2026-07-05T05:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:c157a5707ad4cfc4f5f1f76a9ab2154ba468358f4b20591caa189518801bfd5b","target":"graph","created_at":"2026-07-05T05:32:05Z","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/2301.03728/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative language models define distributions over sequences of tokens that can represent essentially any combination of data modalities (e.g., any permutation of image tokens from VQ-VAEs, speech tokens from HuBERT, BPE tokens for language or code, and so on). To better understand the scaling properties of such mixed-modal models, we conducted over 250 experiments using seven different modalities and model sizes ranging from 8 million to 30 billion, trained on 5-100 billion tokens. We report new mixed-modal scaling laws that unify the contributions of individual modalities and the interacti","authors_text":"Alexis Conneau, Armen Aghajanyan, Karen Hambardzumyan, Lili Yu, Luke Zettlemoyer, Naman Goyal, Omer Levy, Stephen Roller, Susan Zhang, Wei-Ning Hsu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-10T00:20:06Z","title":"Scaling Laws for Generative Mixed-Modal Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.03728","kind":"arxiv","version":1},"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":"sha256:81e81323c50e14e28131f3d439fb9b0052fcb90d2b2fd0445bb53ba76b087b89","target":"record","created_at":"2026-07-05T05:32:05Z","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":"9a5c097831ec29ae1ca5ff2bc87374366b1f776cbfa49634c2c02f250c7d6bc2","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-10T00:20:06Z","title_canon_sha256":"b75341c4e25d15dddf2a6bc0dcd2d868af74b204af32d1d64ca7477650150207"},"schema_version":"1.0","source":{"id":"2301.03728","kind":"arxiv","version":1}},"canonical_sha256":"8181a90229547a058694999c79b75ecd55b47446399cc63262b53fd9fb4d7f74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8181a90229547a058694999c79b75ecd55b47446399cc63262b53fd9fb4d7f74","first_computed_at":"2026-07-05T05:32:05.052780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:32:05.052780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5yNXENxrfggPpOPg0V4+96UrLVeD+i4Coefg4f8sSt9JDuUC4ZY157JbMezjrDk2ZkZu5W20eeDVXssVEflpAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:32:05.053262Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.03728","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81e81323c50e14e28131f3d439fb9b0052fcb90d2b2fd0445bb53ba76b087b89","sha256:c157a5707ad4cfc4f5f1f76a9ab2154ba468358f4b20591caa189518801bfd5b"],"state_sha256":"7a55928a8a84d247a5874bc7557522a3e139356dfb2d12e6083d5bc173fdc398"}