{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:N6U5LTAVFUDMWNR2G4JFYBLTH2","short_pith_number":"pith:N6U5LTAV","canonical_record":{"source":{"id":"2411.18553","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-27T17:51:58Z","cross_cats_sorted":[],"title_canon_sha256":"b6a23a53fa0e20ae580430d03c883ae180fa50faf904938eebc2dfcd8b4ca8e2","abstract_canon_sha256":"c3eb755b130a8c96cf3d7b1d0fad1514afcda39a662c614a3707606f0b8c7522"},"schema_version":"1.0"},"canonical_sha256":"6fa9d5cc152d06cb363a37125c05733eb0fb94af655c7b26ae9923a9eac7efc7","source":{"kind":"arxiv","id":"2411.18553","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.18553","created_at":"2026-07-05T11:19:50Z"},{"alias_kind":"arxiv_version","alias_value":"2411.18553v3","created_at":"2026-07-05T11:19:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18553","created_at":"2026-07-05T11:19:50Z"},{"alias_kind":"pith_short_12","alias_value":"N6U5LTAVFUDM","created_at":"2026-07-05T11:19:50Z"},{"alias_kind":"pith_short_16","alias_value":"N6U5LTAVFUDMWNR2","created_at":"2026-07-05T11:19:50Z"},{"alias_kind":"pith_short_8","alias_value":"N6U5LTAV","created_at":"2026-07-05T11:19:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:N6U5LTAVFUDMWNR2G4JFYBLTH2","target":"record","payload":{"canonical_record":{"source":{"id":"2411.18553","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-27T17:51:58Z","cross_cats_sorted":[],"title_canon_sha256":"b6a23a53fa0e20ae580430d03c883ae180fa50faf904938eebc2dfcd8b4ca8e2","abstract_canon_sha256":"c3eb755b130a8c96cf3d7b1d0fad1514afcda39a662c614a3707606f0b8c7522"},"schema_version":"1.0"},"canonical_sha256":"6fa9d5cc152d06cb363a37125c05733eb0fb94af655c7b26ae9923a9eac7efc7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:50.146085Z","signature_b64":"sNzTVUZ8VpCjIapRBuA4PhwiH9Ra6qIjOQRNYb8/wpXalC5QxeIoKnUbLgoTba5Id+QMhbR4JwYXuhBu2jvqAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fa9d5cc152d06cb363a37125c05733eb0fb94af655c7b26ae9923a9eac7efc7","last_reissued_at":"2026-07-05T11:19:50.145511Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:50.145511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.18553","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:19:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qmTGtPowaSZT16KhbYtDspO6VDauPTTFrjOymEMsE0cBr08QZzek9sqRtlf13D3lYwMJ9HLArssNwIPAgkMoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T23:17:27.492574Z"},"content_sha256":"70694e16f2809ae674ab6876a3de623139035e784081d014acb83c48340ad0ff","schema_version":"1.0","event_id":"sha256:70694e16f2809ae674ab6876a3de623139035e784081d014acb83c48340ad0ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:N6U5LTAVFUDMWNR2G4JFYBLTH2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Retrofitting Large Language Models with Dynamic Tokenization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Minixhofer, Darius Feher, Ivan Vuli\\'c","submitted_at":"2024-11-27T17:51:58Z","abstract_excerpt":"Current language models (LMs) use a fixed, static subword tokenizer. This default choice typically results in degraded efficiency and language capabilities, especially in languages other than English. To address this issue, we challenge the static design and propose retrofitting LMs with dynamic tokenization: a way to dynamically decide on token boundaries based on the input text via a subword-merging algorithm inspired by byte-pair encoding. We merge frequent subword sequences in a batch, then apply a pre-trained embedding-prediction hypernetwork to compute the token embeddings on-the-fly. Fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18553","kind":"arxiv","version":3},"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/2411.18553/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":"2026-07-05T11:19:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dDaDi8+p2I5DDYBZOJ1XSveHlGTc71Oev3dB+9i4nea6OfIjkOFq6NrVCiUCYnaBz5XfJ8+/7dueZwE2Gv1jAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T23:17:27.493073Z"},"content_sha256":"20ff51ebe80877d7943f2902129fccb713be6ae883a4fd39b0c738c980eb71ce","schema_version":"1.0","event_id":"sha256:20ff51ebe80877d7943f2902129fccb713be6ae883a4fd39b0c738c980eb71ce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N6U5LTAVFUDMWNR2G4JFYBLTH2/bundle.json","state_url":"https://pith.science/pith/N6U5LTAVFUDMWNR2G4JFYBLTH2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N6U5LTAVFUDMWNR2G4JFYBLTH2/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":"2026-08-12T23:17:27Z","links":{"resolver":"https://pith.science/pith/N6U5LTAVFUDMWNR2G4JFYBLTH2","bundle":"https://pith.science/pith/N6U5LTAVFUDMWNR2G4JFYBLTH2/bundle.json","state":"https://pith.science/pith/N6U5LTAVFUDMWNR2G4JFYBLTH2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N6U5LTAVFUDMWNR2G4JFYBLTH2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:N6U5LTAVFUDMWNR2G4JFYBLTH2","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":"c3eb755b130a8c96cf3d7b1d0fad1514afcda39a662c614a3707606f0b8c7522","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-27T17:51:58Z","title_canon_sha256":"b6a23a53fa0e20ae580430d03c883ae180fa50faf904938eebc2dfcd8b4ca8e2"},"schema_version":"1.0","source":{"id":"2411.18553","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.18553","created_at":"2026-07-05T11:19:50Z"},{"alias_kind":"arxiv_version","alias_value":"2411.18553v3","created_at":"2026-07-05T11:19:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18553","created_at":"2026-07-05T11:19:50Z"},{"alias_kind":"pith_short_12","alias_value":"N6U5LTAVFUDM","created_at":"2026-07-05T11:19:50Z"},{"alias_kind":"pith_short_16","alias_value":"N6U5LTAVFUDMWNR2","created_at":"2026-07-05T11:19:50Z"},{"alias_kind":"pith_short_8","alias_value":"N6U5LTAV","created_at":"2026-07-05T11:19:50Z"}],"graph_snapshots":[{"event_id":"sha256:20ff51ebe80877d7943f2902129fccb713be6ae883a4fd39b0c738c980eb71ce","target":"graph","created_at":"2026-07-05T11:19:50Z","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/2411.18553/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current language models (LMs) use a fixed, static subword tokenizer. This default choice typically results in degraded efficiency and language capabilities, especially in languages other than English. To address this issue, we challenge the static design and propose retrofitting LMs with dynamic tokenization: a way to dynamically decide on token boundaries based on the input text via a subword-merging algorithm inspired by byte-pair encoding. We merge frequent subword sequences in a batch, then apply a pre-trained embedding-prediction hypernetwork to compute the token embeddings on-the-fly. Fo","authors_text":"Benjamin Minixhofer, Darius Feher, Ivan Vuli\\'c","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-27T17:51:58Z","title":"Retrofitting Large Language Models with Dynamic Tokenization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18553","kind":"arxiv","version":3},"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":"sha256:70694e16f2809ae674ab6876a3de623139035e784081d014acb83c48340ad0ff","target":"record","created_at":"2026-07-05T11:19:50Z","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":"c3eb755b130a8c96cf3d7b1d0fad1514afcda39a662c614a3707606f0b8c7522","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-27T17:51:58Z","title_canon_sha256":"b6a23a53fa0e20ae580430d03c883ae180fa50faf904938eebc2dfcd8b4ca8e2"},"schema_version":"1.0","source":{"id":"2411.18553","kind":"arxiv","version":3}},"canonical_sha256":"6fa9d5cc152d06cb363a37125c05733eb0fb94af655c7b26ae9923a9eac7efc7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6fa9d5cc152d06cb363a37125c05733eb0fb94af655c7b26ae9923a9eac7efc7","first_computed_at":"2026-07-05T11:19:50.145511Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:50.145511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sNzTVUZ8VpCjIapRBuA4PhwiH9Ra6qIjOQRNYb8/wpXalC5QxeIoKnUbLgoTba5Id+QMhbR4JwYXuhBu2jvqAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:50.146085Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.18553","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70694e16f2809ae674ab6876a3de623139035e784081d014acb83c48340ad0ff","sha256:20ff51ebe80877d7943f2902129fccb713be6ae883a4fd39b0c738c980eb71ce"],"state_sha256":"9949fd243017f4faf56b5d9f28133d624722e75879505945a6927b2187a88546"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9gjYF2xllRpNK9Qh8DguRiMwJ274W74ct0FT4Q2ZWfUfqgFvhF8EdsRDI30XcFq5NXuoxNxWcXxkboHKeHqPCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T23:17:27.498363Z","bundle_sha256":"b72a0e92fc327bb1f7b658fd46493c120199d8e99e53f95ed1d11060daf22f39"}}