{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:37ZSFA6IGGGQKRKCTN5NR3CT4D","short_pith_number":"pith:37ZSFA6I","canonical_record":{"source":{"id":"2406.19223","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T14:49:08Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"af6ec28ccd51d49ef021d983c875f9f78fff8810af9788ce889764431478ed9e","abstract_canon_sha256":"eb61d637a268e75a46082a2dde7668bd3c5911cf3947502e227a1e4d16d333ad"},"schema_version":"1.0"},"canonical_sha256":"dff32283c8318d0545429b7ad8ec53e0d9d1d9048ef1ee0d5097d767c4a14840","source":{"kind":"arxiv","id":"2406.19223","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.19223","created_at":"2026-07-05T09:57:43Z"},{"alias_kind":"arxiv_version","alias_value":"2406.19223v2","created_at":"2026-07-05T09:57:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19223","created_at":"2026-07-05T09:57:43Z"},{"alias_kind":"pith_short_12","alias_value":"37ZSFA6IGGGQ","created_at":"2026-07-05T09:57:43Z"},{"alias_kind":"pith_short_16","alias_value":"37ZSFA6IGGGQKRKC","created_at":"2026-07-05T09:57:43Z"},{"alias_kind":"pith_short_8","alias_value":"37ZSFA6I","created_at":"2026-07-05T09:57:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:37ZSFA6IGGGQKRKCTN5NR3CT4D","target":"record","payload":{"canonical_record":{"source":{"id":"2406.19223","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T14:49:08Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"af6ec28ccd51d49ef021d983c875f9f78fff8810af9788ce889764431478ed9e","abstract_canon_sha256":"eb61d637a268e75a46082a2dde7668bd3c5911cf3947502e227a1e4d16d333ad"},"schema_version":"1.0"},"canonical_sha256":"dff32283c8318d0545429b7ad8ec53e0d9d1d9048ef1ee0d5097d767c4a14840","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:43.839237Z","signature_b64":"Pqa0/2C62YaSFzxqlxT3pXM8hvuvlH4fHkaQx5CTtJ2p3bXgxS4Cb2mV5vuNBaSSHt6laJFyDa6/zolVAVq6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dff32283c8318d0545429b7ad8ec53e0d9d1d9048ef1ee0d5097d767c4a14840","last_reissued_at":"2026-07-05T09:57:43.838743Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:43.838743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.19223","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:57:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VdTHsD+EZGnUu2hDCYH7VxwcZGSu6gPVoFe8dPGUDFtl10hZYbw+NFv7EXEJ/fDy4BEh9sEi4HRnixDPaQKvAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T04:53:12.494405Z"},"content_sha256":"3dbf1d7063fbf43f317bf2894b3467d20c6eada0f814ea44071baf62e98533d4","schema_version":"1.0","event_id":"sha256:3dbf1d7063fbf43f317bf2894b3467d20c6eada0f814ea44071baf62e98533d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:37ZSFA6IGGGQKRKCTN5NR3CT4D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"T-FREE: Subword Tokenizer-Free Generative LLMs via Sparse Representations for Memory-Efficient Embeddings","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bj\\\"orn Deiseroth, Kristian Kersting, Manuel Brack, Patrick Schramowski, Samuel Weinbach","submitted_at":"2024-06-27T14:49:08Z","abstract_excerpt":"Tokenizers are crucial for encoding information in Large Language Models, but their development has recently stagnated, and they contain inherent weaknesses. Major limitations include computational overhead, ineffective vocabulary use, and unnecessarily large embedding and head layers. Additionally, their performance is biased towards a reference corpus, leading to reduced effectiveness for underrepresented languages.\n  To remedy these issues, we propose T-FREE, which directly embeds words through sparse activation patterns over character triplets, and does not require a reference corpus. T-FR"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19223","kind":"arxiv","version":2},"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/2406.19223/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":"2026-07-05T09:57:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eodgg++CRXy+7+u8jRvd5rfJoLTYf0hZKHy4pSyxxtzyEQ3pvfG1zsjZvzO/XrcypkxDVFifkoJatS77F+41CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T04:53:12.495218Z"},"content_sha256":"e44d52a4c3231a9c0e58cfebfe0c0e60be8ae80fc862df3c6fc0b30414947cbf","schema_version":"1.0","event_id":"sha256:e44d52a4c3231a9c0e58cfebfe0c0e60be8ae80fc862df3c6fc0b30414947cbf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/37ZSFA6IGGGQKRKCTN5NR3CT4D/bundle.json","state_url":"https://pith.science/pith/37ZSFA6IGGGQKRKCTN5NR3CT4D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/37ZSFA6IGGGQKRKCTN5NR3CT4D/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":"2026-08-11T04:53:12Z","links":{"resolver":"https://pith.science/pith/37ZSFA6IGGGQKRKCTN5NR3CT4D","bundle":"https://pith.science/pith/37ZSFA6IGGGQKRKCTN5NR3CT4D/bundle.json","state":"https://pith.science/pith/37ZSFA6IGGGQKRKCTN5NR3CT4D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/37ZSFA6IGGGQKRKCTN5NR3CT4D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:37ZSFA6IGGGQKRKCTN5NR3CT4D","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":"eb61d637a268e75a46082a2dde7668bd3c5911cf3947502e227a1e4d16d333ad","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T14:49:08Z","title_canon_sha256":"af6ec28ccd51d49ef021d983c875f9f78fff8810af9788ce889764431478ed9e"},"schema_version":"1.0","source":{"id":"2406.19223","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.19223","created_at":"2026-07-05T09:57:43Z"},{"alias_kind":"arxiv_version","alias_value":"2406.19223v2","created_at":"2026-07-05T09:57:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19223","created_at":"2026-07-05T09:57:43Z"},{"alias_kind":"pith_short_12","alias_value":"37ZSFA6IGGGQ","created_at":"2026-07-05T09:57:43Z"},{"alias_kind":"pith_short_16","alias_value":"37ZSFA6IGGGQKRKC","created_at":"2026-07-05T09:57:43Z"},{"alias_kind":"pith_short_8","alias_value":"37ZSFA6I","created_at":"2026-07-05T09:57:43Z"}],"graph_snapshots":[{"event_id":"sha256:e44d52a4c3231a9c0e58cfebfe0c0e60be8ae80fc862df3c6fc0b30414947cbf","target":"graph","created_at":"2026-07-05T09:57:43Z","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/2406.19223/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tokenizers are crucial for encoding information in Large Language Models, but their development has recently stagnated, and they contain inherent weaknesses. Major limitations include computational overhead, ineffective vocabulary use, and unnecessarily large embedding and head layers. Additionally, their performance is biased towards a reference corpus, leading to reduced effectiveness for underrepresented languages.\n  To remedy these issues, we propose T-FREE, which directly embeds words through sparse activation patterns over character triplets, and does not require a reference corpus. T-FR","authors_text":"Bj\\\"orn Deiseroth, Kristian Kersting, Manuel Brack, Patrick Schramowski, Samuel Weinbach","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T14:49:08Z","title":"T-FREE: Subword Tokenizer-Free Generative LLMs via Sparse Representations for Memory-Efficient Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19223","kind":"arxiv","version":2},"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":"sha256:3dbf1d7063fbf43f317bf2894b3467d20c6eada0f814ea44071baf62e98533d4","target":"record","created_at":"2026-07-05T09:57:43Z","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":"eb61d637a268e75a46082a2dde7668bd3c5911cf3947502e227a1e4d16d333ad","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T14:49:08Z","title_canon_sha256":"af6ec28ccd51d49ef021d983c875f9f78fff8810af9788ce889764431478ed9e"},"schema_version":"1.0","source":{"id":"2406.19223","kind":"arxiv","version":2}},"canonical_sha256":"dff32283c8318d0545429b7ad8ec53e0d9d1d9048ef1ee0d5097d767c4a14840","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dff32283c8318d0545429b7ad8ec53e0d9d1d9048ef1ee0d5097d767c4a14840","first_computed_at":"2026-07-05T09:57:43.838743Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:57:43.838743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Pqa0/2C62YaSFzxqlxT3pXM8hvuvlH4fHkaQx5CTtJ2p3bXgxS4Cb2mV5vuNBaSSHt6laJFyDa6/zolVAVq6AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:57:43.839237Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.19223","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3dbf1d7063fbf43f317bf2894b3467d20c6eada0f814ea44071baf62e98533d4","sha256:e44d52a4c3231a9c0e58cfebfe0c0e60be8ae80fc862df3c6fc0b30414947cbf"],"state_sha256":"4581d1805df7476a60fb1d4e450c07a7f9b82b096d9cc2a24e10d8a87f004ea2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JlpFxwPaUkSrNkXu4wxazLYZ71dEDy1QKGgLuVF08Pvy++kNz8W4QXCb6zZCb1lUM2DjAFnPlr0OqBXhIi3SCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T04:53:12.502075Z","bundle_sha256":"25ce0fb12700a5c3b36242ef372547b90ddff1b4371095efe731c05d4c6407a4"}}