{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CMNQRXSCTUKTWEWUFTDIVWXHGX","short_pith_number":"pith:CMNQRXSC","canonical_record":{"source":{"id":"2411.08671","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2024-11-13T15:04:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a4e806cd9500865b63a90e5142fb6221e8afc288750b8b65a268728c38d4506c","abstract_canon_sha256":"0890d92a6fbfa48a0b22803d745ec8779a364b79f7b9835a51c97b77adcb4db4"},"schema_version":"1.0"},"canonical_sha256":"131b08de429d153b12d42cc68adae735c1926359fefd50f69ad04e694c1fac44","source":{"kind":"arxiv","id":"2411.08671","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.08671","created_at":"2026-07-05T09:35:00Z"},{"alias_kind":"arxiv_version","alias_value":"2411.08671v1","created_at":"2026-07-05T09:35:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08671","created_at":"2026-07-05T09:35:00Z"},{"alias_kind":"pith_short_12","alias_value":"CMNQRXSCTUKT","created_at":"2026-07-05T09:35:00Z"},{"alias_kind":"pith_short_16","alias_value":"CMNQRXSCTUKTWEWU","created_at":"2026-07-05T09:35:00Z"},{"alias_kind":"pith_short_8","alias_value":"CMNQRXSC","created_at":"2026-07-05T09:35:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CMNQRXSCTUKTWEWUFTDIVWXHGX","target":"record","payload":{"canonical_record":{"source":{"id":"2411.08671","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2024-11-13T15:04:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a4e806cd9500865b63a90e5142fb6221e8afc288750b8b65a268728c38d4506c","abstract_canon_sha256":"0890d92a6fbfa48a0b22803d745ec8779a364b79f7b9835a51c97b77adcb4db4"},"schema_version":"1.0"},"canonical_sha256":"131b08de429d153b12d42cc68adae735c1926359fefd50f69ad04e694c1fac44","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:00.653792Z","signature_b64":"pMz6uOpGEqJNyFUmqFytsLWcpZr0lmSlxquUp+ClSjxY35MKQiV9BfOzhoAS+sUFripl2hZY2e0QGNsBavDjBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"131b08de429d153b12d42cc68adae735c1926359fefd50f69ad04e694c1fac44","last_reissued_at":"2026-07-05T09:35:00.653302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:00.653302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.08671","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":"2026-07-05T09:35:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5sUqXufd5urjlAculWU+LQ+OPvIH7IFxbZTgGmmfiIZGmNJYHOf2xx9YTsUaCmu53cxa9LCeDmkYVsuTtDczAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:07:46.190659Z"},"content_sha256":"25d369bc879f46e7d246c543f85e012d46f36fb9f4be29eaf7b4cc9666df2ad0","schema_version":"1.0","event_id":"sha256:25d369bc879f46e7d246c543f85e012d46f36fb9f4be29eaf7b4cc9666df2ad0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CMNQRXSCTUKTWEWUFTDIVWXHGX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Theoretical Analysis of Byte-Pair Encoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.DS","authors_text":"Johannes Voderholzer, L\\'aszl\\'o Kozma","submitted_at":"2024-11-13T15:04:02Z","abstract_excerpt":"Byte-Pair Encoding (BPE) is a widely used method for subword tokenization, with origins in grammar-based text compression. It is employed in a variety of language processing tasks such as machine translation or large language model (LLM) pretraining, to create a token dictionary of a prescribed size. Most evaluations of BPE to date are empirical, and the reasons for its good practical performance are not well understood.\n  In this paper we focus on the optimization problem underlying BPE: finding a pair encoding that achieves optimal compression utility. We show that this problem is APX-comple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08671","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/2411.08671/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":"2026-07-05T09:35:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WMaRSXrHCmcuTsplP1lBGXCcQcgm6SuMlVqUjpCIPFSzj1s65MMcthwXouRC7W0jKsSK36KIbU76PZnLzFTgBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:07:46.191317Z"},"content_sha256":"f771bd41240dd0581667bc9f1d31284e837517390c58d1b8f5f4a4bd5145e616","schema_version":"1.0","event_id":"sha256:f771bd41240dd0581667bc9f1d31284e837517390c58d1b8f5f4a4bd5145e616"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CMNQRXSCTUKTWEWUFTDIVWXHGX/bundle.json","state_url":"https://pith.science/pith/CMNQRXSCTUKTWEWUFTDIVWXHGX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CMNQRXSCTUKTWEWUFTDIVWXHGX/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":"2026-08-06T13:07:46Z","links":{"resolver":"https://pith.science/pith/CMNQRXSCTUKTWEWUFTDIVWXHGX","bundle":"https://pith.science/pith/CMNQRXSCTUKTWEWUFTDIVWXHGX/bundle.json","state":"https://pith.science/pith/CMNQRXSCTUKTWEWUFTDIVWXHGX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CMNQRXSCTUKTWEWUFTDIVWXHGX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CMNQRXSCTUKTWEWUFTDIVWXHGX","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":"0890d92a6fbfa48a0b22803d745ec8779a364b79f7b9835a51c97b77adcb4db4","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2024-11-13T15:04:02Z","title_canon_sha256":"a4e806cd9500865b63a90e5142fb6221e8afc288750b8b65a268728c38d4506c"},"schema_version":"1.0","source":{"id":"2411.08671","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.08671","created_at":"2026-07-05T09:35:00Z"},{"alias_kind":"arxiv_version","alias_value":"2411.08671v1","created_at":"2026-07-05T09:35:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08671","created_at":"2026-07-05T09:35:00Z"},{"alias_kind":"pith_short_12","alias_value":"CMNQRXSCTUKT","created_at":"2026-07-05T09:35:00Z"},{"alias_kind":"pith_short_16","alias_value":"CMNQRXSCTUKTWEWU","created_at":"2026-07-05T09:35:00Z"},{"alias_kind":"pith_short_8","alias_value":"CMNQRXSC","created_at":"2026-07-05T09:35:00Z"}],"graph_snapshots":[{"event_id":"sha256:f771bd41240dd0581667bc9f1d31284e837517390c58d1b8f5f4a4bd5145e616","target":"graph","created_at":"2026-07-05T09:35:00Z","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/2411.08671/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Byte-Pair Encoding (BPE) is a widely used method for subword tokenization, with origins in grammar-based text compression. It is employed in a variety of language processing tasks such as machine translation or large language model (LLM) pretraining, to create a token dictionary of a prescribed size. Most evaluations of BPE to date are empirical, and the reasons for its good practical performance are not well understood.\n  In this paper we focus on the optimization problem underlying BPE: finding a pair encoding that achieves optimal compression utility. We show that this problem is APX-comple","authors_text":"Johannes Voderholzer, L\\'aszl\\'o Kozma","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2024-11-13T15:04:02Z","title":"Theoretical Analysis of Byte-Pair Encoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08671","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":"sha256:25d369bc879f46e7d246c543f85e012d46f36fb9f4be29eaf7b4cc9666df2ad0","target":"record","created_at":"2026-07-05T09:35:00Z","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":"0890d92a6fbfa48a0b22803d745ec8779a364b79f7b9835a51c97b77adcb4db4","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2024-11-13T15:04:02Z","title_canon_sha256":"a4e806cd9500865b63a90e5142fb6221e8afc288750b8b65a268728c38d4506c"},"schema_version":"1.0","source":{"id":"2411.08671","kind":"arxiv","version":1}},"canonical_sha256":"131b08de429d153b12d42cc68adae735c1926359fefd50f69ad04e694c1fac44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"131b08de429d153b12d42cc68adae735c1926359fefd50f69ad04e694c1fac44","first_computed_at":"2026-07-05T09:35:00.653302Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:35:00.653302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pMz6uOpGEqJNyFUmqFytsLWcpZr0lmSlxquUp+ClSjxY35MKQiV9BfOzhoAS+sUFripl2hZY2e0QGNsBavDjBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:35:00.653792Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.08671","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25d369bc879f46e7d246c543f85e012d46f36fb9f4be29eaf7b4cc9666df2ad0","sha256:f771bd41240dd0581667bc9f1d31284e837517390c58d1b8f5f4a4bd5145e616"],"state_sha256":"92e2611e453c58f846dbfb69406aec399a762918227b234718ae6cc17bda1274"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uh3e2B2eyhR+RLXSGNdB3kJitvARCNzEMezYlnMcIiwUH3IV50F1IpXeoUfuTS/7i/N5qca3ImZwmPz+tu7RCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T13:07:46.195780Z","bundle_sha256":"4032f10aa606a1d9f0954066502f5179e3f14fb33033d04c7fc42a31303c3a3f"}}