{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7YTZTMFS74NOQ7EM2KSF2KOCUA","short_pith_number":"pith:7YTZTMFS","canonical_record":{"source":{"id":"2406.07249","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2024-06-11T13:32:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b97360bd8f7d74e814fb3894aa362964a91d96d27b89627c6f3ce95cd7dddd29","abstract_canon_sha256":"d2d0213baae3b6c4ab632c1dd0ead35ffd30193f316c6a60d47e88145cedd2da"},"schema_version":"1.0"},"canonical_sha256":"fe2799b0b2ff1ae87c8cd2a45d29c2a02a178591c374cc249958182ade6d5495","source":{"kind":"arxiv","id":"2406.07249","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07249","created_at":"2026-07-05T08:36:48Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07249v2","created_at":"2026-07-05T08:36:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07249","created_at":"2026-07-05T08:36:48Z"},{"alias_kind":"pith_short_12","alias_value":"7YTZTMFS74NO","created_at":"2026-07-05T08:36:48Z"},{"alias_kind":"pith_short_16","alias_value":"7YTZTMFS74NOQ7EM","created_at":"2026-07-05T08:36:48Z"},{"alias_kind":"pith_short_8","alias_value":"7YTZTMFS","created_at":"2026-07-05T08:36:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7YTZTMFS74NOQ7EM2KSF2KOCUA","target":"record","payload":{"canonical_record":{"source":{"id":"2406.07249","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2024-06-11T13:32:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b97360bd8f7d74e814fb3894aa362964a91d96d27b89627c6f3ce95cd7dddd29","abstract_canon_sha256":"d2d0213baae3b6c4ab632c1dd0ead35ffd30193f316c6a60d47e88145cedd2da"},"schema_version":"1.0"},"canonical_sha256":"fe2799b0b2ff1ae87c8cd2a45d29c2a02a178591c374cc249958182ade6d5495","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:48.441752Z","signature_b64":"sqMFksXEcmIOgaJf89F2rq9L36GLj39ZjxVyqzH6uzWQF697wDB0k2/kmJ23RYLeIDfz+GIWhSsWoHlyJ9ZSAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe2799b0b2ff1ae87c8cd2a45d29c2a02a178591c374cc249958182ade6d5495","last_reissued_at":"2026-07-05T08:36:48.441347Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:48.441347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.07249","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":"2026-07-05T08:36:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MbTIaqv0QZiik3tsThTNpH0/irwJk0q/0ggzFVd5upbOpFx8z2OsCmuK1nAEBoGPbMT6vnaq9DFfroidO3yXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T21:12:18.008525Z"},"content_sha256":"cc60d5f8ff12d0929b5f62401534add08e26664bc1dc52d92b1795accce716bb","schema_version":"1.0","event_id":"sha256:cc60d5f8ff12d0929b5f62401534add08e26664bc1dc52d92b1795accce716bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7YTZTMFS74NOQ7EM2KSF2KOCUA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Are Protein Language Models Compute Optimal?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"q-bio.BM","authors_text":"Alexis Molina, \\'Alvaro Ciudad, Yaiza Serrano","submitted_at":"2024-06-11T13:32:11Z","abstract_excerpt":"While protein language models (pLMs) have transformed biological research, the scaling laws governing their improvement remain underexplored. By adapting methodologies from NLP scaling laws, we investigated the optimal ratio between model parameters and training tokens within a fixed compute budget. Our study reveals that pLM sizes scale sublinearly with compute budget, showing diminishing returns in performance as model size increases, and we identify a performance plateau in training loss comparable to the one found in relevant works in the field. Our findings suggest that widely-used pLMs m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07249","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/2406.07249/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":"2026-07-05T08:36:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4x4Wr9lvlheax8RgsZ2hZQckkDkxe5zzxIiUBQinGtWqoJUXna2fyc94gt1PQattt2yLxaaRtWBOaNetv2xnBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T21:12:18.008896Z"},"content_sha256":"7f15e01c7b40296fe67de7bc04056b8256e14aa024b52b2a346599ad468ffcd2","schema_version":"1.0","event_id":"sha256:7f15e01c7b40296fe67de7bc04056b8256e14aa024b52b2a346599ad468ffcd2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7YTZTMFS74NOQ7EM2KSF2KOCUA/bundle.json","state_url":"https://pith.science/pith/7YTZTMFS74NOQ7EM2KSF2KOCUA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7YTZTMFS74NOQ7EM2KSF2KOCUA/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":"2026-07-06T21:12:18Z","links":{"resolver":"https://pith.science/pith/7YTZTMFS74NOQ7EM2KSF2KOCUA","bundle":"https://pith.science/pith/7YTZTMFS74NOQ7EM2KSF2KOCUA/bundle.json","state":"https://pith.science/pith/7YTZTMFS74NOQ7EM2KSF2KOCUA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7YTZTMFS74NOQ7EM2KSF2KOCUA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7YTZTMFS74NOQ7EM2KSF2KOCUA","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":"d2d0213baae3b6c4ab632c1dd0ead35ffd30193f316c6a60d47e88145cedd2da","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2024-06-11T13:32:11Z","title_canon_sha256":"b97360bd8f7d74e814fb3894aa362964a91d96d27b89627c6f3ce95cd7dddd29"},"schema_version":"1.0","source":{"id":"2406.07249","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07249","created_at":"2026-07-05T08:36:48Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07249v2","created_at":"2026-07-05T08:36:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07249","created_at":"2026-07-05T08:36:48Z"},{"alias_kind":"pith_short_12","alias_value":"7YTZTMFS74NO","created_at":"2026-07-05T08:36:48Z"},{"alias_kind":"pith_short_16","alias_value":"7YTZTMFS74NOQ7EM","created_at":"2026-07-05T08:36:48Z"},{"alias_kind":"pith_short_8","alias_value":"7YTZTMFS","created_at":"2026-07-05T08:36:48Z"}],"graph_snapshots":[{"event_id":"sha256:7f15e01c7b40296fe67de7bc04056b8256e14aa024b52b2a346599ad468ffcd2","target":"graph","created_at":"2026-07-05T08:36:48Z","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/2406.07249/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While protein language models (pLMs) have transformed biological research, the scaling laws governing their improvement remain underexplored. By adapting methodologies from NLP scaling laws, we investigated the optimal ratio between model parameters and training tokens within a fixed compute budget. Our study reveals that pLM sizes scale sublinearly with compute budget, showing diminishing returns in performance as model size increases, and we identify a performance plateau in training loss comparable to the one found in relevant works in the field. Our findings suggest that widely-used pLMs m","authors_text":"Alexis Molina, \\'Alvaro Ciudad, Yaiza Serrano","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2024-06-11T13:32:11Z","title":"Are Protein Language Models Compute Optimal?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07249","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:cc60d5f8ff12d0929b5f62401534add08e26664bc1dc52d92b1795accce716bb","target":"record","created_at":"2026-07-05T08:36:48Z","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":"d2d0213baae3b6c4ab632c1dd0ead35ffd30193f316c6a60d47e88145cedd2da","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2024-06-11T13:32:11Z","title_canon_sha256":"b97360bd8f7d74e814fb3894aa362964a91d96d27b89627c6f3ce95cd7dddd29"},"schema_version":"1.0","source":{"id":"2406.07249","kind":"arxiv","version":2}},"canonical_sha256":"fe2799b0b2ff1ae87c8cd2a45d29c2a02a178591c374cc249958182ade6d5495","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe2799b0b2ff1ae87c8cd2a45d29c2a02a178591c374cc249958182ade6d5495","first_computed_at":"2026-07-05T08:36:48.441347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:48.441347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sqMFksXEcmIOgaJf89F2rq9L36GLj39ZjxVyqzH6uzWQF697wDB0k2/kmJ23RYLeIDfz+GIWhSsWoHlyJ9ZSAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:48.441752Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07249","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc60d5f8ff12d0929b5f62401534add08e26664bc1dc52d92b1795accce716bb","sha256:7f15e01c7b40296fe67de7bc04056b8256e14aa024b52b2a346599ad468ffcd2"],"state_sha256":"65afc4da41767ff2f6b77d8452ac274437850716e8c7381a31e58aa2905f39e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c7X6RrZ0j3RPJVYAtYIgOj3bwsPTBXfT9PH5wO9EUPuHwVKujdf5sPPaXjDGTWHkXB8Xpl4EN67qHP4eKrV3Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T21:12:18.010816Z","bundle_sha256":"9e3b768339d66c20bb1c6d2a0de7bf922d733662973596306cfcd289e9df9b52"}}