{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FDJSPYAUAEUHI52VKHHQFIX4Y5","short_pith_number":"pith:FDJSPYAU","canonical_record":{"source":{"id":"2411.17669","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-26T18:30:20Z","cross_cats_sorted":["q-bio.QM"],"title_canon_sha256":"3aa6eeee015da142d14a5f1bcbe408e2d54c726f44fea7ffce8096b143e215c6","abstract_canon_sha256":"b24a0a9e1ba7164b31a9974bd0862482c7474c4737357a5f9c8a65055f30c965"},"schema_version":"1.0"},"canonical_sha256":"28d327e014012874775551cf02a2fcc76fcc315e6e81bd3fb994d62b18acf55c","source":{"kind":"arxiv","id":"2411.17669","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17669","created_at":"2026-07-05T09:40:50Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17669v1","created_at":"2026-07-05T09:40:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17669","created_at":"2026-07-05T09:40:50Z"},{"alias_kind":"pith_short_12","alias_value":"FDJSPYAUAEUH","created_at":"2026-07-05T09:40:50Z"},{"alias_kind":"pith_short_16","alias_value":"FDJSPYAUAEUHI52V","created_at":"2026-07-05T09:40:50Z"},{"alias_kind":"pith_short_8","alias_value":"FDJSPYAU","created_at":"2026-07-05T09:40:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FDJSPYAUAEUHI52VKHHQFIX4Y5","target":"record","payload":{"canonical_record":{"source":{"id":"2411.17669","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-26T18:30:20Z","cross_cats_sorted":["q-bio.QM"],"title_canon_sha256":"3aa6eeee015da142d14a5f1bcbe408e2d54c726f44fea7ffce8096b143e215c6","abstract_canon_sha256":"b24a0a9e1ba7164b31a9974bd0862482c7474c4737357a5f9c8a65055f30c965"},"schema_version":"1.0"},"canonical_sha256":"28d327e014012874775551cf02a2fcc76fcc315e6e81bd3fb994d62b18acf55c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:50.220725Z","signature_b64":"3GESrgIP8osk3PcKbG2lyVZPOinXSeZth2f+v7USqY0pHDOxS8oYAxl+tYaiowK2lQ8rFd0czuY8p0/AqBzBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28d327e014012874775551cf02a2fcc76fcc315e6e81bd3fb994d62b18acf55c","last_reissued_at":"2026-07-05T09:40:50.220206Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:50.220206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.17669","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":"2026-07-05T09:40:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kzVJJSgn+pAwAEaD1o+tFNg0Ib4IioC3y1xufijYTrD3/cHujvCtrzB5ycXEiIduzlnXdQxM9v/8r4XAdmNFDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T03:45:12.569497Z"},"content_sha256":"8b664142270d21c4c283caf93d941813d7921a3f3d31f760b3f02834b5dec77f","schema_version":"1.0","event_id":"sha256:8b664142270d21c4c283caf93d941813d7921a3f3d31f760b3f02834b5dec77f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FDJSPYAUAEUHI52VKHHQFIX4Y5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Linguistic Laws Meet Protein Sequences: A Comparative Analysis of Subword Tokenization Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.CL","authors_text":"Arzucan \\\"Ozg\\\"ur, Burak Suyunu, Enes Taylan","submitted_at":"2024-11-26T18:30:20Z","abstract_excerpt":"Tokenization is a crucial step in processing protein sequences for machine learning models, as proteins are complex sequences of amino acids that require meaningful segmentation to capture their functional and structural properties. However, existing subword tokenization methods, developed primarily for human language, may be inadequate for protein sequences, which have unique patterns and constraints. This study evaluates three prominent tokenization approaches, Byte-Pair Encoding (BPE), WordPiece, and SentencePiece, across varying vocabulary sizes (400-6400), analyzing their effectiveness in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17669","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/2411.17669/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":"2026-07-05T09:40:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/pZVbgJJEneFPb2wx9ym1QFheIVm9Rgq1awtkh94H270oYsUQHb1WEzFdZ41S1ZmmL6O+OqwJnrxJfF90+l2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T03:45:12.569876Z"},"content_sha256":"01128e52583d49619239593e67011298b4996ea03ece6e245d8b860ae3a5b385","schema_version":"1.0","event_id":"sha256:01128e52583d49619239593e67011298b4996ea03ece6e245d8b860ae3a5b385"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FDJSPYAUAEUHI52VKHHQFIX4Y5/bundle.json","state_url":"https://pith.science/pith/FDJSPYAUAEUHI52VKHHQFIX4Y5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FDJSPYAUAEUHI52VKHHQFIX4Y5/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":"2026-08-13T03:45:12Z","links":{"resolver":"https://pith.science/pith/FDJSPYAUAEUHI52VKHHQFIX4Y5","bundle":"https://pith.science/pith/FDJSPYAUAEUHI52VKHHQFIX4Y5/bundle.json","state":"https://pith.science/pith/FDJSPYAUAEUHI52VKHHQFIX4Y5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FDJSPYAUAEUHI52VKHHQFIX4Y5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FDJSPYAUAEUHI52VKHHQFIX4Y5","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":"b24a0a9e1ba7164b31a9974bd0862482c7474c4737357a5f9c8a65055f30c965","cross_cats_sorted":["q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-26T18:30:20Z","title_canon_sha256":"3aa6eeee015da142d14a5f1bcbe408e2d54c726f44fea7ffce8096b143e215c6"},"schema_version":"1.0","source":{"id":"2411.17669","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17669","created_at":"2026-07-05T09:40:50Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17669v1","created_at":"2026-07-05T09:40:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17669","created_at":"2026-07-05T09:40:50Z"},{"alias_kind":"pith_short_12","alias_value":"FDJSPYAUAEUH","created_at":"2026-07-05T09:40:50Z"},{"alias_kind":"pith_short_16","alias_value":"FDJSPYAUAEUHI52V","created_at":"2026-07-05T09:40:50Z"},{"alias_kind":"pith_short_8","alias_value":"FDJSPYAU","created_at":"2026-07-05T09:40:50Z"}],"graph_snapshots":[{"event_id":"sha256:01128e52583d49619239593e67011298b4996ea03ece6e245d8b860ae3a5b385","target":"graph","created_at":"2026-07-05T09:40:50Z","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/2411.17669/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tokenization is a crucial step in processing protein sequences for machine learning models, as proteins are complex sequences of amino acids that require meaningful segmentation to capture their functional and structural properties. However, existing subword tokenization methods, developed primarily for human language, may be inadequate for protein sequences, which have unique patterns and constraints. This study evaluates three prominent tokenization approaches, Byte-Pair Encoding (BPE), WordPiece, and SentencePiece, across varying vocabulary sizes (400-6400), analyzing their effectiveness in","authors_text":"Arzucan \\\"Ozg\\\"ur, Burak Suyunu, Enes Taylan","cross_cats":["q-bio.QM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-26T18:30:20Z","title":"Linguistic Laws Meet Protein Sequences: A Comparative Analysis of Subword Tokenization Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17669","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":"sha256:8b664142270d21c4c283caf93d941813d7921a3f3d31f760b3f02834b5dec77f","target":"record","created_at":"2026-07-05T09:40:50Z","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":"b24a0a9e1ba7164b31a9974bd0862482c7474c4737357a5f9c8a65055f30c965","cross_cats_sorted":["q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-26T18:30:20Z","title_canon_sha256":"3aa6eeee015da142d14a5f1bcbe408e2d54c726f44fea7ffce8096b143e215c6"},"schema_version":"1.0","source":{"id":"2411.17669","kind":"arxiv","version":1}},"canonical_sha256":"28d327e014012874775551cf02a2fcc76fcc315e6e81bd3fb994d62b18acf55c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28d327e014012874775551cf02a2fcc76fcc315e6e81bd3fb994d62b18acf55c","first_computed_at":"2026-07-05T09:40:50.220206Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:40:50.220206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3GESrgIP8osk3PcKbG2lyVZPOinXSeZth2f+v7USqY0pHDOxS8oYAxl+tYaiowK2lQ8rFd0czuY8p0/AqBzBAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:40:50.220725Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.17669","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b664142270d21c4c283caf93d941813d7921a3f3d31f760b3f02834b5dec77f","sha256:01128e52583d49619239593e67011298b4996ea03ece6e245d8b860ae3a5b385"],"state_sha256":"d2be3252831f34865e89fbe6ff55e8774fcdf672252fddf3cc484bffc81b1bc0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h6oZ9QlCsUKxAS9AfsA0j936tb1LEqGPLZiPsuu8OFf4iDLPibR1cPkq+mFsyroFYdtEAygcc6uT08D+jMJ5AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T03:45:12.572203Z","bundle_sha256":"014bb0992c6dc9dc99a8d32c95609a1a828308a89db3c3fe497fc0a20dfe51ce"}}