{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DYNLK7TO35TJ27EPQDCER7UCGM","short_pith_number":"pith:DYNLK7TO","canonical_record":{"source":{"id":"2606.02834","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-01T19:56:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2e7f0ad19cd52201a5d0fd2e3579c80f10f7113c1f0fa88db0201bc10a81bf9b","abstract_canon_sha256":"c9ef77f2d7f5dcf35f2cda968fd6e2ea4e22504dce9ff8abdda5e92e94382dd3"},"schema_version":"1.0"},"canonical_sha256":"1e1ab57e6edf669d7c8f80c448fe8233151aaeadda7a258121bfb4bb40a2dbf6","source":{"kind":"arxiv","id":"2606.02834","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02834","created_at":"2026-06-03T01:05:24Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02834v1","created_at":"2026-06-03T01:05:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02834","created_at":"2026-06-03T01:05:24Z"},{"alias_kind":"pith_short_12","alias_value":"DYNLK7TO35TJ","created_at":"2026-06-03T01:05:24Z"},{"alias_kind":"pith_short_16","alias_value":"DYNLK7TO35TJ27EP","created_at":"2026-06-03T01:05:24Z"},{"alias_kind":"pith_short_8","alias_value":"DYNLK7TO","created_at":"2026-06-03T01:05:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DYNLK7TO35TJ27EPQDCER7UCGM","target":"record","payload":{"canonical_record":{"source":{"id":"2606.02834","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-01T19:56:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2e7f0ad19cd52201a5d0fd2e3579c80f10f7113c1f0fa88db0201bc10a81bf9b","abstract_canon_sha256":"c9ef77f2d7f5dcf35f2cda968fd6e2ea4e22504dce9ff8abdda5e92e94382dd3"},"schema_version":"1.0"},"canonical_sha256":"1e1ab57e6edf669d7c8f80c448fe8233151aaeadda7a258121bfb4bb40a2dbf6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:24.169263Z","signature_b64":"B2ia9rda/GQaR4mmI+/K7Js5GRVxPULcop+HaKKCATzkNPwJfWiTfaDxwpxZulF3M0H4G0w1f69ckhRmDd3jDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e1ab57e6edf669d7c8f80c448fe8233151aaeadda7a258121bfb4bb40a2dbf6","last_reissued_at":"2026-06-03T01:05:24.168873Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:24.168873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.02834","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":"2026-06-03T01:05:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2HvSGHVYDAqxb4c1vFvCP5DvDUtbh18Vs+jQRRV0H7O7B0mdJlgOUDr/uiU00queU/sqe343EXb7z4epEVyMAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T10:38:51.240033Z"},"content_sha256":"5496ce372d8cbd0bab1b84af7b5635bb96d03a94c02e9e6d5794f0a1213ecb1f","schema_version":"1.0","event_id":"sha256:5496ce372d8cbd0bab1b84af7b5635bb96d03a94c02e9e6d5794f0a1213ecb1f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DYNLK7TO35TJ27EPQDCER7UCGM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Byte Model: Teaching Language Models About Compiled Code","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Alexandru Dinu, Calin Miron, Catalin-Andrei Stan, Edward Raff, Florian St\\\"ortz, Mihaela Gaman, Sandra Servia-Rodr\\'iguez","submitted_at":"2026-06-01T19:56:02Z","abstract_excerpt":"Malware analysis starts with the raw bytes of an executable program, and tools to \"lift\" these to higher-level representations, such as assembly, are expensive and subject to error. Large Language Models (LLMs) cannot process raw byte representations and answer questions about them. To this end, we present the first byte-native LLM. Based on a vocabulary expansion technique using a bespoke byte tokenizer, such a model is capable of responding to complex questions about malware binaries, with accuracies ranging from 69% for malware family classification to 98% for architecture classification. O"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02834","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/2606.02834/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":"2026-06-03T01:05:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S43O3/L7CVRUpIgh9jj4mXoBYIBbLz4tByikaqoYMNenwB2ZGqA9+l9JpkZUm8nJM4/3rj3teU/S+Z9ORk+oAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T10:38:51.240413Z"},"content_sha256":"3ad3033002e269e3702c0cdca93e07cc0694ce68e44161e9e910aa36167c51fb","schema_version":"1.0","event_id":"sha256:3ad3033002e269e3702c0cdca93e07cc0694ce68e44161e9e910aa36167c51fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DYNLK7TO35TJ27EPQDCER7UCGM/bundle.json","state_url":"https://pith.science/pith/DYNLK7TO35TJ27EPQDCER7UCGM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DYNLK7TO35TJ27EPQDCER7UCGM/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":"2026-06-03T10:38:51Z","links":{"resolver":"https://pith.science/pith/DYNLK7TO35TJ27EPQDCER7UCGM","bundle":"https://pith.science/pith/DYNLK7TO35TJ27EPQDCER7UCGM/bundle.json","state":"https://pith.science/pith/DYNLK7TO35TJ27EPQDCER7UCGM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DYNLK7TO35TJ27EPQDCER7UCGM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DYNLK7TO35TJ27EPQDCER7UCGM","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":"c9ef77f2d7f5dcf35f2cda968fd6e2ea4e22504dce9ff8abdda5e92e94382dd3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-01T19:56:02Z","title_canon_sha256":"2e7f0ad19cd52201a5d0fd2e3579c80f10f7113c1f0fa88db0201bc10a81bf9b"},"schema_version":"1.0","source":{"id":"2606.02834","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02834","created_at":"2026-06-03T01:05:24Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02834v1","created_at":"2026-06-03T01:05:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02834","created_at":"2026-06-03T01:05:24Z"},{"alias_kind":"pith_short_12","alias_value":"DYNLK7TO35TJ","created_at":"2026-06-03T01:05:24Z"},{"alias_kind":"pith_short_16","alias_value":"DYNLK7TO35TJ27EP","created_at":"2026-06-03T01:05:24Z"},{"alias_kind":"pith_short_8","alias_value":"DYNLK7TO","created_at":"2026-06-03T01:05:24Z"}],"graph_snapshots":[{"event_id":"sha256:3ad3033002e269e3702c0cdca93e07cc0694ce68e44161e9e910aa36167c51fb","target":"graph","created_at":"2026-06-03T01:05:24Z","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/2606.02834/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Malware analysis starts with the raw bytes of an executable program, and tools to \"lift\" these to higher-level representations, such as assembly, are expensive and subject to error. Large Language Models (LLMs) cannot process raw byte representations and answer questions about them. To this end, we present the first byte-native LLM. Based on a vocabulary expansion technique using a bespoke byte tokenizer, such a model is capable of responding to complex questions about malware binaries, with accuracies ranging from 69% for malware family classification to 98% for architecture classification. O","authors_text":"Alexandru Dinu, Calin Miron, Catalin-Andrei Stan, Edward Raff, Florian St\\\"ortz, Mihaela Gaman, Sandra Servia-Rodr\\'iguez","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-01T19:56:02Z","title":"Large Byte Model: Teaching Language Models About Compiled Code"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02834","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":"sha256:5496ce372d8cbd0bab1b84af7b5635bb96d03a94c02e9e6d5794f0a1213ecb1f","target":"record","created_at":"2026-06-03T01:05:24Z","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":"c9ef77f2d7f5dcf35f2cda968fd6e2ea4e22504dce9ff8abdda5e92e94382dd3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-01T19:56:02Z","title_canon_sha256":"2e7f0ad19cd52201a5d0fd2e3579c80f10f7113c1f0fa88db0201bc10a81bf9b"},"schema_version":"1.0","source":{"id":"2606.02834","kind":"arxiv","version":1}},"canonical_sha256":"1e1ab57e6edf669d7c8f80c448fe8233151aaeadda7a258121bfb4bb40a2dbf6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e1ab57e6edf669d7c8f80c448fe8233151aaeadda7a258121bfb4bb40a2dbf6","first_computed_at":"2026-06-03T01:05:24.168873Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:24.168873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B2ia9rda/GQaR4mmI+/K7Js5GRVxPULcop+HaKKCATzkNPwJfWiTfaDxwpxZulF3M0H4G0w1f69ckhRmDd3jDQ==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:24.169263Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.02834","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5496ce372d8cbd0bab1b84af7b5635bb96d03a94c02e9e6d5794f0a1213ecb1f","sha256:3ad3033002e269e3702c0cdca93e07cc0694ce68e44161e9e910aa36167c51fb"],"state_sha256":"040df371dbaa65a469e7d6e65cf1d1e9d24df7c295f4f9fa45883e34eae02e50"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y3VHdYo2+HxZ3EIsF+qC2G7RmkylsXYAYMkECr2GLiOixywjoM0HA1oPA/kIxLAQaVKnnIYPrJ50fJo2XWUVDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T10:38:51.242349Z","bundle_sha256":"53662bed5daefa718275ade42a84d07b0631a9c65e008a8898bfa2bf71750024"}}