{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DAD7OYF6I4J3BDIKQAN6OQE24Y","short_pith_number":"pith:DAD7OYF6","canonical_record":{"source":{"id":"2402.19155","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-29T13:38:07Z","cross_cats_sorted":[],"title_canon_sha256":"6cbe0532cf4c817fe36b9698f43a16c24608c6b481a2bb84440c089f4cefc70b","abstract_canon_sha256":"43d13b7b560394a9685c6e5a4a98d2da6a77c828c96fc95a28b943ad9aafb276"},"schema_version":"1.0"},"canonical_sha256":"1807f760be4713b08d0a801be7409ae6294acfc9ea5aeb1835d4b67ca9c6ffca","source":{"kind":"arxiv","id":"2402.19155","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.19155","created_at":"2026-07-05T07:50:41Z"},{"alias_kind":"arxiv_version","alias_value":"2402.19155v1","created_at":"2026-07-05T07:50:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.19155","created_at":"2026-07-05T07:50:41Z"},{"alias_kind":"pith_short_12","alias_value":"DAD7OYF6I4J3","created_at":"2026-07-05T07:50:41Z"},{"alias_kind":"pith_short_16","alias_value":"DAD7OYF6I4J3BDIK","created_at":"2026-07-05T07:50:41Z"},{"alias_kind":"pith_short_8","alias_value":"DAD7OYF6","created_at":"2026-07-05T07:50:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DAD7OYF6I4J3BDIKQAN6OQE24Y","target":"record","payload":{"canonical_record":{"source":{"id":"2402.19155","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-29T13:38:07Z","cross_cats_sorted":[],"title_canon_sha256":"6cbe0532cf4c817fe36b9698f43a16c24608c6b481a2bb84440c089f4cefc70b","abstract_canon_sha256":"43d13b7b560394a9685c6e5a4a98d2da6a77c828c96fc95a28b943ad9aafb276"},"schema_version":"1.0"},"canonical_sha256":"1807f760be4713b08d0a801be7409ae6294acfc9ea5aeb1835d4b67ca9c6ffca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:41.779745Z","signature_b64":"VRiQugI+8RYTtAUCwlvA3kQLr5X7HYQwa1mZoF2LRBJUW5Oz+kPPX0vPqsxPmSSMD0k0yNmnqRmuR5iauVrxBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1807f760be4713b08d0a801be7409ae6294acfc9ea5aeb1835d4b67ca9c6ffca","last_reissued_at":"2026-07-05T07:50:41.779311Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:41.779311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.19155","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:50:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"We75Fl1+/O+R9K0Dxu4ap5sKZCG2AbABqo0dyfIoRyGEej853z1dcb4Q7qwTIfuOZL20QT9YuzIIO0x1QUszDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:55:38.008443Z"},"content_sha256":"84f8810fdfc88613e50c97dd00c269327e468a8e825e30387e34bded50d3dd13","schema_version":"1.0","event_id":"sha256:84f8810fdfc88613e50c97dd00c269327e468a8e825e30387e34bded50d3dd13"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DAD7OYF6I4J3BDIKQAN6OQE24Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Language Models: Byte Models are Digital World Simulators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Maosong Sun, Rui Wang, Shangda Wu, Xiaobing Li, Xu Tan, Zili Wang","submitted_at":"2024-02-29T13:38:07Z","abstract_excerpt":"Traditional deep learning often overlooks bytes, the basic units of the digital world, where all forms of information and operations are encoded and manipulated in binary format. Inspired by the success of next token prediction in natural language processing, we introduce bGPT, a model with next byte prediction to simulate the digital world. bGPT matches specialized models in performance across various modalities, including text, audio, and images, and offers new possibilities for predicting, simulating, and diagnosing algorithm or hardware behaviour. It has almost flawlessly replicated the pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.19155","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/2402.19155/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:50:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F9aKXsgpnEUKfuXLp7O1lQXd4Yeu9CBPr9OHm5xWU9DnY+mQQOtdZjgNEl/O9c58rnx19uQcdSRJHvGwgXENAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:55:38.009401Z"},"content_sha256":"6ea879a39d7985d6d5f86272b34d9ecf28ded19082c8d78477e01b314466cfa3","schema_version":"1.0","event_id":"sha256:6ea879a39d7985d6d5f86272b34d9ecf28ded19082c8d78477e01b314466cfa3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DAD7OYF6I4J3BDIKQAN6OQE24Y/bundle.json","state_url":"https://pith.science/pith/DAD7OYF6I4J3BDIKQAN6OQE24Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DAD7OYF6I4J3BDIKQAN6OQE24Y/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T16:55:38Z","links":{"resolver":"https://pith.science/pith/DAD7OYF6I4J3BDIKQAN6OQE24Y","bundle":"https://pith.science/pith/DAD7OYF6I4J3BDIKQAN6OQE24Y/bundle.json","state":"https://pith.science/pith/DAD7OYF6I4J3BDIKQAN6OQE24Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DAD7OYF6I4J3BDIKQAN6OQE24Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DAD7OYF6I4J3BDIKQAN6OQE24Y","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":"43d13b7b560394a9685c6e5a4a98d2da6a77c828c96fc95a28b943ad9aafb276","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-29T13:38:07Z","title_canon_sha256":"6cbe0532cf4c817fe36b9698f43a16c24608c6b481a2bb84440c089f4cefc70b"},"schema_version":"1.0","source":{"id":"2402.19155","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.19155","created_at":"2026-07-05T07:50:41Z"},{"alias_kind":"arxiv_version","alias_value":"2402.19155v1","created_at":"2026-07-05T07:50:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.19155","created_at":"2026-07-05T07:50:41Z"},{"alias_kind":"pith_short_12","alias_value":"DAD7OYF6I4J3","created_at":"2026-07-05T07:50:41Z"},{"alias_kind":"pith_short_16","alias_value":"DAD7OYF6I4J3BDIK","created_at":"2026-07-05T07:50:41Z"},{"alias_kind":"pith_short_8","alias_value":"DAD7OYF6","created_at":"2026-07-05T07:50:41Z"}],"graph_snapshots":[{"event_id":"sha256:6ea879a39d7985d6d5f86272b34d9ecf28ded19082c8d78477e01b314466cfa3","target":"graph","created_at":"2026-07-05T07:50:41Z","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/2402.19155/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional deep learning often overlooks bytes, the basic units of the digital world, where all forms of information and operations are encoded and manipulated in binary format. Inspired by the success of next token prediction in natural language processing, we introduce bGPT, a model with next byte prediction to simulate the digital world. bGPT matches specialized models in performance across various modalities, including text, audio, and images, and offers new possibilities for predicting, simulating, and diagnosing algorithm or hardware behaviour. It has almost flawlessly replicated the pr","authors_text":"Maosong Sun, Rui Wang, Shangda Wu, Xiaobing Li, Xu Tan, Zili Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-29T13:38:07Z","title":"Beyond Language Models: Byte Models are Digital World Simulators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.19155","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":"sha256:84f8810fdfc88613e50c97dd00c269327e468a8e825e30387e34bded50d3dd13","target":"record","created_at":"2026-07-05T07:50:41Z","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":"43d13b7b560394a9685c6e5a4a98d2da6a77c828c96fc95a28b943ad9aafb276","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-29T13:38:07Z","title_canon_sha256":"6cbe0532cf4c817fe36b9698f43a16c24608c6b481a2bb84440c089f4cefc70b"},"schema_version":"1.0","source":{"id":"2402.19155","kind":"arxiv","version":1}},"canonical_sha256":"1807f760be4713b08d0a801be7409ae6294acfc9ea5aeb1835d4b67ca9c6ffca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1807f760be4713b08d0a801be7409ae6294acfc9ea5aeb1835d4b67ca9c6ffca","first_computed_at":"2026-07-05T07:50:41.779311Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:50:41.779311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VRiQugI+8RYTtAUCwlvA3kQLr5X7HYQwa1mZoF2LRBJUW5Oz+kPPX0vPqsxPmSSMD0k0yNmnqRmuR5iauVrxBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:50:41.779745Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.19155","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84f8810fdfc88613e50c97dd00c269327e468a8e825e30387e34bded50d3dd13","sha256:6ea879a39d7985d6d5f86272b34d9ecf28ded19082c8d78477e01b314466cfa3"],"state_sha256":"b4340fc38bd6d302d259b3b57910b2eb68c032c8e3d716152108b0604f1995c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y2WPuUdUFfpizgtqrMzPEXh/6mXdsdT4x+bCvyH4KIr51o5sOOz9vW0tFF3So/QCvHLy2St3lntjpETVE49ABQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T16:55:38.015489Z","bundle_sha256":"5a957d2a6843de13bb72da7292b9583398bbf48b8452b7f076cbc4bd7edb0062"}}