{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AOLNCIKK547JHIIMG5OIZKWQMV","short_pith_number":"pith:AOLNCIKK","canonical_record":{"source":{"id":"2607.15232","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T17:32:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5b299d29e6363e673558c73ea518785982fce1f1e53244e5207f4bf3bf609f39","abstract_canon_sha256":"77c0af245c48f7945e717a17ca955583d70251bec7e06484289f85c70d591b7f"},"schema_version":"1.0"},"canonical_sha256":"0396d1214aef3e93a10c375c8caad0656caa9d7f2a9b84d6e73bd0d2bda88e52","source":{"kind":"arxiv","id":"2607.15232","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15232","created_at":"2026-07-17T01:22:15Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15232v1","created_at":"2026-07-17T01:22:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15232","created_at":"2026-07-17T01:22:15Z"},{"alias_kind":"pith_short_12","alias_value":"AOLNCIKK547J","created_at":"2026-07-17T01:22:15Z"},{"alias_kind":"pith_short_16","alias_value":"AOLNCIKK547JHIIM","created_at":"2026-07-17T01:22:15Z"},{"alias_kind":"pith_short_8","alias_value":"AOLNCIKK","created_at":"2026-07-17T01:22:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AOLNCIKK547JHIIMG5OIZKWQMV","target":"record","payload":{"canonical_record":{"source":{"id":"2607.15232","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T17:32:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5b299d29e6363e673558c73ea518785982fce1f1e53244e5207f4bf3bf609f39","abstract_canon_sha256":"77c0af245c48f7945e717a17ca955583d70251bec7e06484289f85c70d591b7f"},"schema_version":"1.0"},"canonical_sha256":"0396d1214aef3e93a10c375c8caad0656caa9d7f2a9b84d6e73bd0d2bda88e52","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:22:15.928001Z","signature_b64":"aJnLXScib0YaisN5UXX7qFj59BYAznE/XzHj6kuCUx7aR5qkczptxdhphbYTY4GotpN6b1xCWrTNuFpeonGPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0396d1214aef3e93a10c375c8caad0656caa9d7f2a9b84d6e73bd0d2bda88e52","last_reissued_at":"2026-07-17T01:22:15.927174Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:22:15.927174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.15232","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":"2026-07-17T01:22:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UbMr/AK409EX4mvMUO35YcOHdJJRosMKbgWsn/OQqgUXWDS3OyTe/sfwK6kagORYUoRXKaQV2c8lsd2f2CgyDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T02:58:18.508667Z"},"content_sha256":"00a4d9aa39de40c95737708e520b9048b620d26c562e13d34dc6888d00a404f4","schema_version":"1.0","event_id":"sha256:00a4d9aa39de40c95737708e520b9048b620d26c562e13d34dc6888d00a404f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AOLNCIKK547JHIIMG5OIZKWQMV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"In-Place Tokenizer Expansion for Pre-trained LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aditya Tadimeti, Alberto Cabrera, Alexander Amini, Jimmy T.H. Smith, Mathias Lechner, Maxime Labonne, Paul Pak, Simon S. Lee, Tarek Dakhran, Tim Seyde","submitted_at":"2026-07-16T17:32:38Z","abstract_excerpt":"A tokenizer fixed at the start of pre-training allocates vocabulary in proportion to the pre-training corpus, reflecting the deployment priorities at that time. When those priorities shift, languages added later are split into many more tokens per word, which can raise latency, compute, and energy consumption for users of those languages. Cloud models can afford a broad vocabulary because the embedding and LM-head matrices are a small fraction of their parameters. On a compact model those matrices are a material share of per-token decode bandwidth, so on-device models ship small vocabularies a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15232","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/2607.15232/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":"2026-07-17T01:22:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BdLhD1xiId2JPLZmPOpx1QY6bGUtfGiv5y4S4V/sdcX4Lxmi/rzyj1O6F4GhwT50b9YV/TbYlAZkYDngFo6RCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T02:58:18.509228Z"},"content_sha256":"5aa4a02b89c0e93908d47a0940a9d4630943294c33db237a668b52ea5e2cc8f9","schema_version":"1.0","event_id":"sha256:5aa4a02b89c0e93908d47a0940a9d4630943294c33db237a668b52ea5e2cc8f9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AOLNCIKK547JHIIMG5OIZKWQMV/bundle.json","state_url":"https://pith.science/pith/AOLNCIKK547JHIIMG5OIZKWQMV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AOLNCIKK547JHIIMG5OIZKWQMV/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":"2026-08-23T02:58:18Z","links":{"resolver":"https://pith.science/pith/AOLNCIKK547JHIIMG5OIZKWQMV","bundle":"https://pith.science/pith/AOLNCIKK547JHIIMG5OIZKWQMV/bundle.json","state":"https://pith.science/pith/AOLNCIKK547JHIIMG5OIZKWQMV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AOLNCIKK547JHIIMG5OIZKWQMV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AOLNCIKK547JHIIMG5OIZKWQMV","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":"77c0af245c48f7945e717a17ca955583d70251bec7e06484289f85c70d591b7f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T17:32:38Z","title_canon_sha256":"5b299d29e6363e673558c73ea518785982fce1f1e53244e5207f4bf3bf609f39"},"schema_version":"1.0","source":{"id":"2607.15232","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15232","created_at":"2026-07-17T01:22:15Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15232v1","created_at":"2026-07-17T01:22:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15232","created_at":"2026-07-17T01:22:15Z"},{"alias_kind":"pith_short_12","alias_value":"AOLNCIKK547J","created_at":"2026-07-17T01:22:15Z"},{"alias_kind":"pith_short_16","alias_value":"AOLNCIKK547JHIIM","created_at":"2026-07-17T01:22:15Z"},{"alias_kind":"pith_short_8","alias_value":"AOLNCIKK","created_at":"2026-07-17T01:22:15Z"}],"graph_snapshots":[{"event_id":"sha256:5aa4a02b89c0e93908d47a0940a9d4630943294c33db237a668b52ea5e2cc8f9","target":"graph","created_at":"2026-07-17T01:22:15Z","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/2607.15232/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A tokenizer fixed at the start of pre-training allocates vocabulary in proportion to the pre-training corpus, reflecting the deployment priorities at that time. When those priorities shift, languages added later are split into many more tokens per word, which can raise latency, compute, and energy consumption for users of those languages. Cloud models can afford a broad vocabulary because the embedding and LM-head matrices are a small fraction of their parameters. On a compact model those matrices are a material share of per-token decode bandwidth, so on-device models ship small vocabularies a","authors_text":"Aditya Tadimeti, Alberto Cabrera, Alexander Amini, Jimmy T.H. Smith, Mathias Lechner, Maxime Labonne, Paul Pak, Simon S. Lee, Tarek Dakhran, Tim Seyde","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T17:32:38Z","title":"In-Place Tokenizer Expansion for Pre-trained LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15232","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":"sha256:00a4d9aa39de40c95737708e520b9048b620d26c562e13d34dc6888d00a404f4","target":"record","created_at":"2026-07-17T01:22:15Z","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":"77c0af245c48f7945e717a17ca955583d70251bec7e06484289f85c70d591b7f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T17:32:38Z","title_canon_sha256":"5b299d29e6363e673558c73ea518785982fce1f1e53244e5207f4bf3bf609f39"},"schema_version":"1.0","source":{"id":"2607.15232","kind":"arxiv","version":1}},"canonical_sha256":"0396d1214aef3e93a10c375c8caad0656caa9d7f2a9b84d6e73bd0d2bda88e52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0396d1214aef3e93a10c375c8caad0656caa9d7f2a9b84d6e73bd0d2bda88e52","first_computed_at":"2026-07-17T01:22:15.927174Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T01:22:15.927174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aJnLXScib0YaisN5UXX7qFj59BYAznE/XzHj6kuCUx7aR5qkczptxdhphbYTY4GotpN6b1xCWrTNuFpeonGPDg==","signature_status":"signed_v1","signed_at":"2026-07-17T01:22:15.928001Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.15232","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00a4d9aa39de40c95737708e520b9048b620d26c562e13d34dc6888d00a404f4","sha256:5aa4a02b89c0e93908d47a0940a9d4630943294c33db237a668b52ea5e2cc8f9"],"state_sha256":"9accd081a410922255346c64dcac917212159b4753df49cc437d68df1604ffcb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3fvUAekpfqPY+8aB41gAKOx4c+v4vacG/nxWvtVJwJmGyjprAVZg5DvPA+FhgCGYgI3ISNz7XFuRJQ/OwT7sDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T02:58:18.514387Z","bundle_sha256":"57b8e767e2640b26f265f8f7d248c6847428659d32f64ec1661d1d42fd38d354"}}