{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QVE2BYSZPMQPIOA7UFVE53U3WO","short_pith_number":"pith:QVE2BYSZ","canonical_record":{"source":{"id":"2506.18674","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T14:18:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"704e1fc72d62f2169add642f17682fc0f27e1d09b1fdd5afe8571020cc9b3f65","abstract_canon_sha256":"79df6e558e41514c17cca848feb268afab6c5de74a74086fd2f6dfe1d0031151"},"schema_version":"1.0"},"canonical_sha256":"8549a0e2597b20f4381fa16a4eee9bb3962f176ea79d7d15cca9f7fc68afbf95","source":{"kind":"arxiv","id":"2506.18674","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18674","created_at":"2026-07-05T11:25:54Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18674v1","created_at":"2026-07-05T11:25:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18674","created_at":"2026-07-05T11:25:54Z"},{"alias_kind":"pith_short_12","alias_value":"QVE2BYSZPMQP","created_at":"2026-07-05T11:25:54Z"},{"alias_kind":"pith_short_16","alias_value":"QVE2BYSZPMQPIOA7","created_at":"2026-07-05T11:25:54Z"},{"alias_kind":"pith_short_8","alias_value":"QVE2BYSZ","created_at":"2026-07-05T11:25:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QVE2BYSZPMQPIOA7UFVE53U3WO","target":"record","payload":{"canonical_record":{"source":{"id":"2506.18674","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T14:18:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"704e1fc72d62f2169add642f17682fc0f27e1d09b1fdd5afe8571020cc9b3f65","abstract_canon_sha256":"79df6e558e41514c17cca848feb268afab6c5de74a74086fd2f6dfe1d0031151"},"schema_version":"1.0"},"canonical_sha256":"8549a0e2597b20f4381fa16a4eee9bb3962f176ea79d7d15cca9f7fc68afbf95","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:54.021738Z","signature_b64":"4w117JJXHTtLvJqUkDrfbHE2W8UCq1uBOunZB3ZWtKxIJaEPJnC1HlPGc14VoFJafjjceLBLQFYbUsa10FwMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8549a0e2597b20f4381fa16a4eee9bb3962f176ea79d7d15cca9f7fc68afbf95","last_reissued_at":"2026-07-05T11:25:54.021258Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:54.021258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.18674","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":"2026-07-05T11:25:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LJLMFPb1xYC9l5UoRu1zZMthK7Uzb6Nb9F5tEmGC54rqnAimI6wwFXF/2OUzVeyPIXWaOMnCHI/MMkHhjy7YBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:23:31.158833Z"},"content_sha256":"18d9012f06e3d4a2bae7e44fc378fa0ba1ff9c65a1ab9e252fac96df33d8f7f7","schema_version":"1.0","event_id":"sha256:18d9012f06e3d4a2bae7e44fc378fa0ba1ff9c65a1ab9e252fac96df33d8f7f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QVE2BYSZPMQPIOA7UFVE53U3WO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Is There a Case for Conversation Optimized Tokenizers in Large Language Models?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gonzalo Mart\\'inez, Javier Conde, Pedro Reviriego, Raquel Ferrando","submitted_at":"2025-06-23T14:18:46Z","abstract_excerpt":"The computational and energy costs of Large Language Models (LLMs) have increased exponentially driven by the growing model sizes and the massive adoption of LLMs by hundreds of millions of users. The unit cost of an LLM is the computation of a token. Therefore, the tokenizer plays an important role in the efficiency of a model, and they are carefully optimized to minimize the number of tokens for the text in their training corpus. One of the most popular applications of LLMs are chatbots that interact with users. A key observation is that, for those chatbots, what is important is the performa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18674","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/2506.18674/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":"2026-07-05T11:25:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uIaSIJGZa9BO9NKe45Q6LgUc5+NL8hGLJD80xST+AzKqNidR+5rEJJt8nY23bg7ogP6o10VXDtex7ocdtUqjCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:23:31.159699Z"},"content_sha256":"82e8482b44b3e523d0796cd8a2617a03c2fd63412b655cf3d1c9f372beec8aaf","schema_version":"1.0","event_id":"sha256:82e8482b44b3e523d0796cd8a2617a03c2fd63412b655cf3d1c9f372beec8aaf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QVE2BYSZPMQPIOA7UFVE53U3WO/bundle.json","state_url":"https://pith.science/pith/QVE2BYSZPMQPIOA7UFVE53U3WO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QVE2BYSZPMQPIOA7UFVE53U3WO/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":"2026-08-10T06:23:31Z","links":{"resolver":"https://pith.science/pith/QVE2BYSZPMQPIOA7UFVE53U3WO","bundle":"https://pith.science/pith/QVE2BYSZPMQPIOA7UFVE53U3WO/bundle.json","state":"https://pith.science/pith/QVE2BYSZPMQPIOA7UFVE53U3WO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QVE2BYSZPMQPIOA7UFVE53U3WO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QVE2BYSZPMQPIOA7UFVE53U3WO","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":"79df6e558e41514c17cca848feb268afab6c5de74a74086fd2f6dfe1d0031151","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T14:18:46Z","title_canon_sha256":"704e1fc72d62f2169add642f17682fc0f27e1d09b1fdd5afe8571020cc9b3f65"},"schema_version":"1.0","source":{"id":"2506.18674","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18674","created_at":"2026-07-05T11:25:54Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18674v1","created_at":"2026-07-05T11:25:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18674","created_at":"2026-07-05T11:25:54Z"},{"alias_kind":"pith_short_12","alias_value":"QVE2BYSZPMQP","created_at":"2026-07-05T11:25:54Z"},{"alias_kind":"pith_short_16","alias_value":"QVE2BYSZPMQPIOA7","created_at":"2026-07-05T11:25:54Z"},{"alias_kind":"pith_short_8","alias_value":"QVE2BYSZ","created_at":"2026-07-05T11:25:54Z"}],"graph_snapshots":[{"event_id":"sha256:82e8482b44b3e523d0796cd8a2617a03c2fd63412b655cf3d1c9f372beec8aaf","target":"graph","created_at":"2026-07-05T11:25:54Z","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/2506.18674/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The computational and energy costs of Large Language Models (LLMs) have increased exponentially driven by the growing model sizes and the massive adoption of LLMs by hundreds of millions of users. The unit cost of an LLM is the computation of a token. Therefore, the tokenizer plays an important role in the efficiency of a model, and they are carefully optimized to minimize the number of tokens for the text in their training corpus. One of the most popular applications of LLMs are chatbots that interact with users. A key observation is that, for those chatbots, what is important is the performa","authors_text":"Gonzalo Mart\\'inez, Javier Conde, Pedro Reviriego, Raquel Ferrando","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T14:18:46Z","title":"Is There a Case for Conversation Optimized Tokenizers in Large Language Models?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18674","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":"sha256:18d9012f06e3d4a2bae7e44fc378fa0ba1ff9c65a1ab9e252fac96df33d8f7f7","target":"record","created_at":"2026-07-05T11:25:54Z","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":"79df6e558e41514c17cca848feb268afab6c5de74a74086fd2f6dfe1d0031151","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T14:18:46Z","title_canon_sha256":"704e1fc72d62f2169add642f17682fc0f27e1d09b1fdd5afe8571020cc9b3f65"},"schema_version":"1.0","source":{"id":"2506.18674","kind":"arxiv","version":1}},"canonical_sha256":"8549a0e2597b20f4381fa16a4eee9bb3962f176ea79d7d15cca9f7fc68afbf95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8549a0e2597b20f4381fa16a4eee9bb3962f176ea79d7d15cca9f7fc68afbf95","first_computed_at":"2026-07-05T11:25:54.021258Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:54.021258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4w117JJXHTtLvJqUkDrfbHE2W8UCq1uBOunZB3ZWtKxIJaEPJnC1HlPGc14VoFJafjjceLBLQFYbUsa10FwMAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:54.021738Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.18674","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18d9012f06e3d4a2bae7e44fc378fa0ba1ff9c65a1ab9e252fac96df33d8f7f7","sha256:82e8482b44b3e523d0796cd8a2617a03c2fd63412b655cf3d1c9f372beec8aaf"],"state_sha256":"961fb7b97bf0f13d2fc0d922ffc0eb58e83b32d211762119ad47cb853aa37b3a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y2emYc1dcN3Xmf+94oFgtgZ8RUPpwh89eaT5QGzdwS8OjX41nF6f9M9B/GtoPUlpUI5zFWclorEiNe7uNWHMCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T06:23:31.165787Z","bundle_sha256":"84e5a0d44baa02e7eaa73c110b58b56589577cc1789f33cffb0725d9dd72301e"}}