{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5ZCXPXBDDQVKNRYKEFJTZO7LQ7","short_pith_number":"pith:5ZCXPXBD","canonical_record":{"source":{"id":"2502.14553","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T13:31:50Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"87bea37924d7d1ec0ea8e7165b9422a3d9c9a6fdf00b45b854103ec1bc5ae725","abstract_canon_sha256":"8a0ed6644ec6b6d877f5068b51dec8da490acdd5e21e140dd320d9a2928c0dc0"},"schema_version":"1.0"},"canonical_sha256":"ee4577dc231c2aa6c70a21533cbbeb87ed2cab08c4dc2e3e1b6100d4a4f11cc9","source":{"kind":"arxiv","id":"2502.14553","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14553","created_at":"2026-07-05T10:17:29Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14553v1","created_at":"2026-07-05T10:17:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14553","created_at":"2026-07-05T10:17:29Z"},{"alias_kind":"pith_short_12","alias_value":"5ZCXPXBDDQVK","created_at":"2026-07-05T10:17:29Z"},{"alias_kind":"pith_short_16","alias_value":"5ZCXPXBDDQVKNRYK","created_at":"2026-07-05T10:17:29Z"},{"alias_kind":"pith_short_8","alias_value":"5ZCXPXBD","created_at":"2026-07-05T10:17:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5ZCXPXBDDQVKNRYKEFJTZO7LQ7","target":"record","payload":{"canonical_record":{"source":{"id":"2502.14553","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T13:31:50Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"87bea37924d7d1ec0ea8e7165b9422a3d9c9a6fdf00b45b854103ec1bc5ae725","abstract_canon_sha256":"8a0ed6644ec6b6d877f5068b51dec8da490acdd5e21e140dd320d9a2928c0dc0"},"schema_version":"1.0"},"canonical_sha256":"ee4577dc231c2aa6c70a21533cbbeb87ed2cab08c4dc2e3e1b6100d4a4f11cc9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:29.010854Z","signature_b64":"qQ/fzbbsc7498bx11pnkhj6XIfoz42NyJuWXWhZ+ys6msv3w+U8RrvuVUqrX4hvoO64ljdBPvDyBzSZe6EcFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee4577dc231c2aa6c70a21533cbbeb87ed2cab08c4dc2e3e1b6100d4a4f11cc9","last_reissued_at":"2026-07-05T10:17:29.010384Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:29.010384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.14553","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":"2026-07-05T10:17:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gfgsIqCSGsrupmCiUJYUcR/MQ2K7u27mqJkmtCFf6wwMBGQlVkgVCBnyxyWbZNXRmEw9zTx7FTHpwEE498vrCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T01:45:45.951846Z"},"content_sha256":"880daa8ad8bfc73490bf6e18abb54c12ffe38d490a108f098eea524fc7808c9f","schema_version":"1.0","event_id":"sha256:880daa8ad8bfc73490bf6e18abb54c12ffe38d490a108f098eea524fc7808c9f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5ZCXPXBDDQVKNRYKEFJTZO7LQ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multiscale Byte Language Models -- A Hierarchical Architecture for Causal Million-Length Sequence Modeling","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Eric Egli, Jannis Born, Matteo Manica","submitted_at":"2025-02-20T13:31:50Z","abstract_excerpt":"Bytes form the basis of the digital world and thus are a promising building block for multimodal foundation models. Recently, Byte Language Models (BLMs) have emerged to overcome tokenization, yet the excessive length of bytestreams requires new architectural paradigms. Therefore, we present the Multiscale Byte Language Model (MBLM), a model-agnostic hierarchical decoder stack that allows training with context windows of $5$M bytes on single GPU in full model precision. We thoroughly examine MBLM's performance with Transformer and Mamba blocks on both unimodal and multimodal tasks. Our experim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14553","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/2502.14553/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":"2026-07-05T10:17:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2acxeqMNGBYO8hLeq/RLNy4Z9il4P8tlv1HzyOdEMwMXP24dZCg1JY7oIeQbqpkBKiaJRGEo9aBNjCf5C1qBBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T01:45:45.952941Z"},"content_sha256":"8615e181af2a66ebda3b7074f1361f18b4d25c68c8ee53ee0fe75d06e9ea9f9d","schema_version":"1.0","event_id":"sha256:8615e181af2a66ebda3b7074f1361f18b4d25c68c8ee53ee0fe75d06e9ea9f9d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5ZCXPXBDDQVKNRYKEFJTZO7LQ7/bundle.json","state_url":"https://pith.science/pith/5ZCXPXBDDQVKNRYKEFJTZO7LQ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5ZCXPXBDDQVKNRYKEFJTZO7LQ7/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":"2026-08-14T01:45:45Z","links":{"resolver":"https://pith.science/pith/5ZCXPXBDDQVKNRYKEFJTZO7LQ7","bundle":"https://pith.science/pith/5ZCXPXBDDQVKNRYKEFJTZO7LQ7/bundle.json","state":"https://pith.science/pith/5ZCXPXBDDQVKNRYKEFJTZO7LQ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5ZCXPXBDDQVKNRYKEFJTZO7LQ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5ZCXPXBDDQVKNRYKEFJTZO7LQ7","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":"8a0ed6644ec6b6d877f5068b51dec8da490acdd5e21e140dd320d9a2928c0dc0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T13:31:50Z","title_canon_sha256":"87bea37924d7d1ec0ea8e7165b9422a3d9c9a6fdf00b45b854103ec1bc5ae725"},"schema_version":"1.0","source":{"id":"2502.14553","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14553","created_at":"2026-07-05T10:17:29Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14553v1","created_at":"2026-07-05T10:17:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14553","created_at":"2026-07-05T10:17:29Z"},{"alias_kind":"pith_short_12","alias_value":"5ZCXPXBDDQVK","created_at":"2026-07-05T10:17:29Z"},{"alias_kind":"pith_short_16","alias_value":"5ZCXPXBDDQVKNRYK","created_at":"2026-07-05T10:17:29Z"},{"alias_kind":"pith_short_8","alias_value":"5ZCXPXBD","created_at":"2026-07-05T10:17:29Z"}],"graph_snapshots":[{"event_id":"sha256:8615e181af2a66ebda3b7074f1361f18b4d25c68c8ee53ee0fe75d06e9ea9f9d","target":"graph","created_at":"2026-07-05T10:17:29Z","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/2502.14553/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Bytes form the basis of the digital world and thus are a promising building block for multimodal foundation models. Recently, Byte Language Models (BLMs) have emerged to overcome tokenization, yet the excessive length of bytestreams requires new architectural paradigms. Therefore, we present the Multiscale Byte Language Model (MBLM), a model-agnostic hierarchical decoder stack that allows training with context windows of $5$M bytes on single GPU in full model precision. We thoroughly examine MBLM's performance with Transformer and Mamba blocks on both unimodal and multimodal tasks. Our experim","authors_text":"Eric Egli, Jannis Born, Matteo Manica","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T13:31:50Z","title":"Multiscale Byte Language Models -- A Hierarchical Architecture for Causal Million-Length Sequence Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14553","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":"sha256:880daa8ad8bfc73490bf6e18abb54c12ffe38d490a108f098eea524fc7808c9f","target":"record","created_at":"2026-07-05T10:17:29Z","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":"8a0ed6644ec6b6d877f5068b51dec8da490acdd5e21e140dd320d9a2928c0dc0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T13:31:50Z","title_canon_sha256":"87bea37924d7d1ec0ea8e7165b9422a3d9c9a6fdf00b45b854103ec1bc5ae725"},"schema_version":"1.0","source":{"id":"2502.14553","kind":"arxiv","version":1}},"canonical_sha256":"ee4577dc231c2aa6c70a21533cbbeb87ed2cab08c4dc2e3e1b6100d4a4f11cc9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee4577dc231c2aa6c70a21533cbbeb87ed2cab08c4dc2e3e1b6100d4a4f11cc9","first_computed_at":"2026-07-05T10:17:29.010384Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:29.010384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qQ/fzbbsc7498bx11pnkhj6XIfoz42NyJuWXWhZ+ys6msv3w+U8RrvuVUqrX4hvoO64ljdBPvDyBzSZe6EcFBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:29.010854Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14553","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:880daa8ad8bfc73490bf6e18abb54c12ffe38d490a108f098eea524fc7808c9f","sha256:8615e181af2a66ebda3b7074f1361f18b4d25c68c8ee53ee0fe75d06e9ea9f9d"],"state_sha256":"0840692601e22f6dbb903ebcefc8fc4c0ee52157b444ad28e8730e99fe722a7c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dbpXhoC27UYXKfYR7SbJwiPvC5Mrjge+PyN/4aVGqWTGJHaL7tsMoqc7ZUEEexh0FgyBNR+zVe9iq5E5UBxHAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T01:45:45.960203Z","bundle_sha256":"f54f181177849d8452e5d1442c8520002f656245deb6ab5932e33a81f3c6ade6"}}