{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Q6EW6AJRFUEP732QMA37S2KRXL","short_pith_number":"pith:Q6EW6AJR","canonical_record":{"source":{"id":"2507.13077","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-07-16T00:29:22Z","cross_cats_sorted":[],"title_canon_sha256":"4cbe88529ecf7732447794a648fb64f90d849cfbb0561d6ee672b4265cb7fd47","abstract_canon_sha256":"90a1c12030594bae2e2ce3f85c941302deaa58e71fd8e60315ce7426c0e2b64a"},"schema_version":"1.0"},"canonical_sha256":"87896f01312d08ffef506037f96951bad2b72da4100826d07838077dc82b9f6a","source":{"kind":"arxiv","id":"2507.13077","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13077","created_at":"2026-07-05T11:38:54Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13077v1","created_at":"2026-07-05T11:38:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13077","created_at":"2026-07-05T11:38:54Z"},{"alias_kind":"pith_short_12","alias_value":"Q6EW6AJRFUEP","created_at":"2026-07-05T11:38:54Z"},{"alias_kind":"pith_short_16","alias_value":"Q6EW6AJRFUEP732Q","created_at":"2026-07-05T11:38:54Z"},{"alias_kind":"pith_short_8","alias_value":"Q6EW6AJR","created_at":"2026-07-05T11:38:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Q6EW6AJRFUEP732QMA37S2KRXL","target":"record","payload":{"canonical_record":{"source":{"id":"2507.13077","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-07-16T00:29:22Z","cross_cats_sorted":[],"title_canon_sha256":"4cbe88529ecf7732447794a648fb64f90d849cfbb0561d6ee672b4265cb7fd47","abstract_canon_sha256":"90a1c12030594bae2e2ce3f85c941302deaa58e71fd8e60315ce7426c0e2b64a"},"schema_version":"1.0"},"canonical_sha256":"87896f01312d08ffef506037f96951bad2b72da4100826d07838077dc82b9f6a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:54.280856Z","signature_b64":"d2Ef7BXRj6upQTYLkpzuG5xpS+gKjQRERiagqc+AcMrQytZjyVVHNpZnDWDD0l5ytd73vJFMb+xPA96MGbDgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87896f01312d08ffef506037f96951bad2b72da4100826d07838077dc82b9f6a","last_reissued_at":"2026-07-05T11:38:54.280378Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:54.280378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.13077","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":"2026-07-05T11:38:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eH1xWYFNKK8YcnEW/4HNNFiYfNqrGErsJL5205J4RdEWW6uv9Ph2L9Z39URkqK6LuspsZfdDWe4IhsakWHv/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T05:41:21.806939Z"},"content_sha256":"31c662bfe5a9037a97b4fa17a59e3a858a06d697e3eec31715b3337e731590f8","schema_version":"1.0","event_id":"sha256:31c662bfe5a9037a97b4fa17a59e3a858a06d697e3eec31715b3337e731590f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Q6EW6AJRFUEP732QMA37S2KRXL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Continued domain-specific pre-training of protein language models for pMHC-I binding prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.QM","authors_text":"Ariel Espinoza Weinberger, Nilah M. Ioannidis, Sergio E. Mares","submitted_at":"2025-07-16T00:29:22Z","abstract_excerpt":"Predicting peptide--major histocompatibility complex I (pMHC-I) binding affinity remains challenging due to extreme allelic diversity ($\\sim$30,000 HLA alleles), severe data scarcity for most alleles, and noisy experimental measurements. Current methods particularly struggle with underrepresented alleles and quantitative binding prediction. We test whether domain-specific continued pre-training of protein language models is beneficial for their application to pMHC-I binding affinity prediction. Starting from ESM Cambrian (300M parameters), we perform masked-language modeling (MLM)-based contin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13077","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/2507.13077/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":"2026-07-05T11:38:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2m2P7KC5B+hkEwWiv9F9C6zcjLr01a2Pobg2lQl49qK8pUYYdPxWtFPmL3Yfwtbgb1etANVhANO+sHxlBi3gDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T05:41:21.807775Z"},"content_sha256":"942d4ea2b383d00fce2570102de0da1b2246baf977f52e8466cdabc1d68ea2ab","schema_version":"1.0","event_id":"sha256:942d4ea2b383d00fce2570102de0da1b2246baf977f52e8466cdabc1d68ea2ab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q6EW6AJRFUEP732QMA37S2KRXL/bundle.json","state_url":"https://pith.science/pith/Q6EW6AJRFUEP732QMA37S2KRXL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q6EW6AJRFUEP732QMA37S2KRXL/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":"2026-08-22T05:41:21Z","links":{"resolver":"https://pith.science/pith/Q6EW6AJRFUEP732QMA37S2KRXL","bundle":"https://pith.science/pith/Q6EW6AJRFUEP732QMA37S2KRXL/bundle.json","state":"https://pith.science/pith/Q6EW6AJRFUEP732QMA37S2KRXL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q6EW6AJRFUEP732QMA37S2KRXL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Q6EW6AJRFUEP732QMA37S2KRXL","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":"90a1c12030594bae2e2ce3f85c941302deaa58e71fd8e60315ce7426c0e2b64a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-07-16T00:29:22Z","title_canon_sha256":"4cbe88529ecf7732447794a648fb64f90d849cfbb0561d6ee672b4265cb7fd47"},"schema_version":"1.0","source":{"id":"2507.13077","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13077","created_at":"2026-07-05T11:38:54Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13077v1","created_at":"2026-07-05T11:38:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13077","created_at":"2026-07-05T11:38:54Z"},{"alias_kind":"pith_short_12","alias_value":"Q6EW6AJRFUEP","created_at":"2026-07-05T11:38:54Z"},{"alias_kind":"pith_short_16","alias_value":"Q6EW6AJRFUEP732Q","created_at":"2026-07-05T11:38:54Z"},{"alias_kind":"pith_short_8","alias_value":"Q6EW6AJR","created_at":"2026-07-05T11:38:54Z"}],"graph_snapshots":[{"event_id":"sha256:942d4ea2b383d00fce2570102de0da1b2246baf977f52e8466cdabc1d68ea2ab","target":"graph","created_at":"2026-07-05T11:38:54Z","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/2507.13077/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Predicting peptide--major histocompatibility complex I (pMHC-I) binding affinity remains challenging due to extreme allelic diversity ($\\sim$30,000 HLA alleles), severe data scarcity for most alleles, and noisy experimental measurements. Current methods particularly struggle with underrepresented alleles and quantitative binding prediction. We test whether domain-specific continued pre-training of protein language models is beneficial for their application to pMHC-I binding affinity prediction. Starting from ESM Cambrian (300M parameters), we perform masked-language modeling (MLM)-based contin","authors_text":"Ariel Espinoza Weinberger, Nilah M. Ioannidis, Sergio E. Mares","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-07-16T00:29:22Z","title":"Continued domain-specific pre-training of protein language models for pMHC-I binding prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13077","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":"sha256:31c662bfe5a9037a97b4fa17a59e3a858a06d697e3eec31715b3337e731590f8","target":"record","created_at":"2026-07-05T11:38:54Z","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":"90a1c12030594bae2e2ce3f85c941302deaa58e71fd8e60315ce7426c0e2b64a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-07-16T00:29:22Z","title_canon_sha256":"4cbe88529ecf7732447794a648fb64f90d849cfbb0561d6ee672b4265cb7fd47"},"schema_version":"1.0","source":{"id":"2507.13077","kind":"arxiv","version":1}},"canonical_sha256":"87896f01312d08ffef506037f96951bad2b72da4100826d07838077dc82b9f6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87896f01312d08ffef506037f96951bad2b72da4100826d07838077dc82b9f6a","first_computed_at":"2026-07-05T11:38:54.280378Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:54.280378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d2Ef7BXRj6upQTYLkpzuG5xpS+gKjQRERiagqc+AcMrQytZjyVVHNpZnDWDD0l5ytd73vJFMb+xPA96MGbDgCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:54.280856Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.13077","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31c662bfe5a9037a97b4fa17a59e3a858a06d697e3eec31715b3337e731590f8","sha256:942d4ea2b383d00fce2570102de0da1b2246baf977f52e8466cdabc1d68ea2ab"],"state_sha256":"349def65dce98ff68a6b327138f7440a82cfdd260a2b7399537852f35b97a984"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KYkQ5xbsp7MlRI+6Qq8bjzJoTZz1750FarR+xQgLj8hlO5bCDa3y2TXWgCZ4AUA2N+ro/4Ib/vD0YTb60weTBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T05:41:21.812400Z","bundle_sha256":"6a8ab880e5399cabcb438a7c7354965d8d180f32263cdccc73647e017827377d"}}