{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VI6YR47BAAT67QRZ635WWWJQT4","short_pith_number":"pith:VI6YR47B","canonical_record":{"source":{"id":"2310.17415","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-26T14:20:44Z","cross_cats_sorted":["cs.AI","q-bio.BM"],"title_canon_sha256":"a6cc160a34094bff1e6c0d5c097620cef91fd1ef78149273a6c5dc0949e428d3","abstract_canon_sha256":"e886e68c349d71e20f7040b113c965de12192c398ad83b7845fd0e4332a64d69"},"schema_version":"1.0"},"canonical_sha256":"aa3d88f3e10027efc239f6fb6b59309f1f8bce20991f24931abc1495f8d35c76","source":{"kind":"arxiv","id":"2310.17415","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17415","created_at":"2026-07-05T07:05:33Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17415v1","created_at":"2026-07-05T07:05:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17415","created_at":"2026-07-05T07:05:33Z"},{"alias_kind":"pith_short_12","alias_value":"VI6YR47BAAT6","created_at":"2026-07-05T07:05:33Z"},{"alias_kind":"pith_short_16","alias_value":"VI6YR47BAAT67QRZ","created_at":"2026-07-05T07:05:33Z"},{"alias_kind":"pith_short_8","alias_value":"VI6YR47B","created_at":"2026-07-05T07:05:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VI6YR47BAAT67QRZ635WWWJQT4","target":"record","payload":{"canonical_record":{"source":{"id":"2310.17415","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-26T14:20:44Z","cross_cats_sorted":["cs.AI","q-bio.BM"],"title_canon_sha256":"a6cc160a34094bff1e6c0d5c097620cef91fd1ef78149273a6c5dc0949e428d3","abstract_canon_sha256":"e886e68c349d71e20f7040b113c965de12192c398ad83b7845fd0e4332a64d69"},"schema_version":"1.0"},"canonical_sha256":"aa3d88f3e10027efc239f6fb6b59309f1f8bce20991f24931abc1495f8d35c76","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:33.460113Z","signature_b64":"7VD032FlK9URk5VMWAvFVUDniYjV4j1Wtx1V5QXD47FBpRfAa0m8nMh7QBeRHgpbNo/ptHa/oxV4NuXRAvbyAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa3d88f3e10027efc239f6fb6b59309f1f8bce20991f24931abc1495f8d35c76","last_reissued_at":"2026-07-05T07:05:33.459569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:33.459569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.17415","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":"2026-07-05T07:05:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cLJU0gaOj7TjcMJOksOQmk0JFRJOQggdiV/yIYa8GLmhYDD4TcLuPGum9akI7dSC4zN6aHR9fefoqFPbkoXjCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:54:11.264114Z"},"content_sha256":"84bc48e76fb8cebdf7b3e7f91cebb24f521159eded2002b652362a56db74805a","schema_version":"1.0","event_id":"sha256:84bc48e76fb8cebdf7b3e7f91cebb24f521159eded2002b652362a56db74805a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VI6YR47BAAT67QRZ635WWWJQT4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PETA: Evaluating the Impact of Protein Transfer Learning with Sub-word Tokenization on Downstream Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.BM"],"primary_cat":"cs.CL","authors_text":"Guisheng Fan, Huiqun Yu, Liang Hong, Mingchen Li, Pan Tan, Yang Tan, Ziyi Zhou","submitted_at":"2023-10-26T14:20:44Z","abstract_excerpt":"Large protein language models are adept at capturing the underlying evolutionary information in primary structures, offering significant practical value for protein engineering. Compared to natural language models, protein amino acid sequences have a smaller data volume and a limited combinatorial space. Choosing an appropriate vocabulary size to optimize the pre-trained model is a pivotal issue. Moreover, despite the wealth of benchmarks and studies in the natural language community, there remains a lack of a comprehensive benchmark for systematically evaluating protein language model quality"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17415","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/2310.17415/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":"2026-07-05T07:05:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WHJ21+fAhuBMjrNoSgTE1ifhF3LyqlQbNJSP2UDqiziK20K8zQnKnOqU6M49htbEjR7KgJK5SlsiFk/2ooH0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:54:11.264508Z"},"content_sha256":"934498dbbefc8db9cbc654db34375d50ee832e30f13947bb10f58a28dc12c4a2","schema_version":"1.0","event_id":"sha256:934498dbbefc8db9cbc654db34375d50ee832e30f13947bb10f58a28dc12c4a2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VI6YR47BAAT67QRZ635WWWJQT4/bundle.json","state_url":"https://pith.science/pith/VI6YR47BAAT67QRZ635WWWJQT4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VI6YR47BAAT67QRZ635WWWJQT4/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":"2026-07-06T20:54:11Z","links":{"resolver":"https://pith.science/pith/VI6YR47BAAT67QRZ635WWWJQT4","bundle":"https://pith.science/pith/VI6YR47BAAT67QRZ635WWWJQT4/bundle.json","state":"https://pith.science/pith/VI6YR47BAAT67QRZ635WWWJQT4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VI6YR47BAAT67QRZ635WWWJQT4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VI6YR47BAAT67QRZ635WWWJQT4","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":"e886e68c349d71e20f7040b113c965de12192c398ad83b7845fd0e4332a64d69","cross_cats_sorted":["cs.AI","q-bio.BM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-26T14:20:44Z","title_canon_sha256":"a6cc160a34094bff1e6c0d5c097620cef91fd1ef78149273a6c5dc0949e428d3"},"schema_version":"1.0","source":{"id":"2310.17415","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17415","created_at":"2026-07-05T07:05:33Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17415v1","created_at":"2026-07-05T07:05:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17415","created_at":"2026-07-05T07:05:33Z"},{"alias_kind":"pith_short_12","alias_value":"VI6YR47BAAT6","created_at":"2026-07-05T07:05:33Z"},{"alias_kind":"pith_short_16","alias_value":"VI6YR47BAAT67QRZ","created_at":"2026-07-05T07:05:33Z"},{"alias_kind":"pith_short_8","alias_value":"VI6YR47B","created_at":"2026-07-05T07:05:33Z"}],"graph_snapshots":[{"event_id":"sha256:934498dbbefc8db9cbc654db34375d50ee832e30f13947bb10f58a28dc12c4a2","target":"graph","created_at":"2026-07-05T07:05:33Z","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/2310.17415/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large protein language models are adept at capturing the underlying evolutionary information in primary structures, offering significant practical value for protein engineering. Compared to natural language models, protein amino acid sequences have a smaller data volume and a limited combinatorial space. Choosing an appropriate vocabulary size to optimize the pre-trained model is a pivotal issue. Moreover, despite the wealth of benchmarks and studies in the natural language community, there remains a lack of a comprehensive benchmark for systematically evaluating protein language model quality","authors_text":"Guisheng Fan, Huiqun Yu, Liang Hong, Mingchen Li, Pan Tan, Yang Tan, Ziyi Zhou","cross_cats":["cs.AI","q-bio.BM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-26T14:20:44Z","title":"PETA: Evaluating the Impact of Protein Transfer Learning with Sub-word Tokenization on Downstream Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17415","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":"sha256:84bc48e76fb8cebdf7b3e7f91cebb24f521159eded2002b652362a56db74805a","target":"record","created_at":"2026-07-05T07:05:33Z","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":"e886e68c349d71e20f7040b113c965de12192c398ad83b7845fd0e4332a64d69","cross_cats_sorted":["cs.AI","q-bio.BM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-26T14:20:44Z","title_canon_sha256":"a6cc160a34094bff1e6c0d5c097620cef91fd1ef78149273a6c5dc0949e428d3"},"schema_version":"1.0","source":{"id":"2310.17415","kind":"arxiv","version":1}},"canonical_sha256":"aa3d88f3e10027efc239f6fb6b59309f1f8bce20991f24931abc1495f8d35c76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa3d88f3e10027efc239f6fb6b59309f1f8bce20991f24931abc1495f8d35c76","first_computed_at":"2026-07-05T07:05:33.459569Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:33.459569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7VD032FlK9URk5VMWAvFVUDniYjV4j1Wtx1V5QXD47FBpRfAa0m8nMh7QBeRHgpbNo/ptHa/oxV4NuXRAvbyAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:33.460113Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.17415","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84bc48e76fb8cebdf7b3e7f91cebb24f521159eded2002b652362a56db74805a","sha256:934498dbbefc8db9cbc654db34375d50ee832e30f13947bb10f58a28dc12c4a2"],"state_sha256":"7c9d69dd86e9ce8636ca0b5fdcc86810b7a6f6357d2cd03522a666eed99761a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VgigCBfS8UiEzIlJqnyDBhViHXRVs4E1xMB14a4YJ5Zzlfx33ATNWF+0Bh/Z3Tdg+W2JVieTSf8i8PKbelvTAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:54:11.266458Z","bundle_sha256":"aea7d693b8924c1da37b78302af19f6da64f821074cd05a1172c088369d0d289"}}