{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SG7PUDWVUPQHAC3VRTVZAFSKZI","short_pith_number":"pith:SG7PUDWV","canonical_record":{"source":{"id":"2410.12459","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T11:16:47Z","cross_cats_sorted":["cs.CE"],"title_canon_sha256":"84cd0bcea00721bdb4e42956282c759795eff5dd9afcda12f4ecb60303b73153","abstract_canon_sha256":"f732500bd9bdb7a0cf65bdd21bf52ca856e8736a5f4ac0d1989af8db170fc842"},"schema_version":"1.0"},"canonical_sha256":"91befa0ed5a3e0700b758ceb90164aca051891d9cde41c511dcb55fc89ede422","source":{"kind":"arxiv","id":"2410.12459","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12459","created_at":"2026-07-05T10:29:25Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12459v2","created_at":"2026-07-05T10:29:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12459","created_at":"2026-07-05T10:29:25Z"},{"alias_kind":"pith_short_12","alias_value":"SG7PUDWVUPQH","created_at":"2026-07-05T10:29:25Z"},{"alias_kind":"pith_short_16","alias_value":"SG7PUDWVUPQHAC3V","created_at":"2026-07-05T10:29:25Z"},{"alias_kind":"pith_short_8","alias_value":"SG7PUDWV","created_at":"2026-07-05T10:29:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SG7PUDWVUPQHAC3VRTVZAFSKZI","target":"record","payload":{"canonical_record":{"source":{"id":"2410.12459","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T11:16:47Z","cross_cats_sorted":["cs.CE"],"title_canon_sha256":"84cd0bcea00721bdb4e42956282c759795eff5dd9afcda12f4ecb60303b73153","abstract_canon_sha256":"f732500bd9bdb7a0cf65bdd21bf52ca856e8736a5f4ac0d1989af8db170fc842"},"schema_version":"1.0"},"canonical_sha256":"91befa0ed5a3e0700b758ceb90164aca051891d9cde41c511dcb55fc89ede422","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:25.033382Z","signature_b64":"dy+NgycXjk8xJ8JKN1SQTamM/xymwP8VugkyeQgrJrcCrvhiQ6HnsZPVKnFcxtz3kpBRLeMnz245dprr3qnFBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91befa0ed5a3e0700b758ceb90164aca051891d9cde41c511dcb55fc89ede422","last_reissued_at":"2026-07-05T10:29:25.032272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:25.032272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.12459","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":"2026-07-05T10:29:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YKsUr+oTZF96x00q/eqAhp4vopPHyy1PPgCFlhIiI+SyNZ/VO1yGDcQPNqQfXqPiXpYP4hlcsTHjHYKEngUBAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T05:27:02.715255Z"},"content_sha256":"1401efa31b377ea23a8fb1dcf0a178efdd25e040f88cbadcb0f451683a1f4064","schema_version":"1.0","event_id":"sha256:1401efa31b377ea23a8fb1dcf0a178efdd25e040f88cbadcb0f451683a1f4064"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SG7PUDWVUPQHAC3VRTVZAFSKZI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HELM: Hierarchical Encoding for mRNA Language Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CE"],"primary_cat":"cs.LG","authors_text":"Artem Moskalev, Mangal Prakash, Mehdi Yazdani-Jahromi, Rui Liao, Tommaso Mansi","submitted_at":"2024-10-16T11:16:47Z","abstract_excerpt":"Messenger RNA (mRNA) plays a crucial role in protein synthesis, with its codon structure directly impacting biological properties. While Language Models (LMs) have shown promise in analyzing biological sequences, existing approaches fail to account for the hierarchical nature of mRNA's codon structure. We introduce Hierarchical Encoding for mRNA Language Modeling (HELM), a novel pre-training strategy that incorporates codon-level hierarchical structure into language model training. HELM modulates the loss function based on codon synonymity, aligning the model's learning process with the biolog"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12459","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/2410.12459/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":"2026-07-05T10:29:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Oxe87e4QIzv09gNBrm5v1WKFxoH+GMTgQbpbuccyAI6FwNQ2NBY5atw2N+8KDaSvY/MzQDemXKIUXL+/Va8eBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T05:27:02.715628Z"},"content_sha256":"26be5aa98544782f2e6a31714828f9da919fbe45fdeb0c5f2d99ef80a92fdddd","schema_version":"1.0","event_id":"sha256:26be5aa98544782f2e6a31714828f9da919fbe45fdeb0c5f2d99ef80a92fdddd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SG7PUDWVUPQHAC3VRTVZAFSKZI/bundle.json","state_url":"https://pith.science/pith/SG7PUDWVUPQHAC3VRTVZAFSKZI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SG7PUDWVUPQHAC3VRTVZAFSKZI/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":"2026-07-24T05:27:02Z","links":{"resolver":"https://pith.science/pith/SG7PUDWVUPQHAC3VRTVZAFSKZI","bundle":"https://pith.science/pith/SG7PUDWVUPQHAC3VRTVZAFSKZI/bundle.json","state":"https://pith.science/pith/SG7PUDWVUPQHAC3VRTVZAFSKZI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SG7PUDWVUPQHAC3VRTVZAFSKZI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SG7PUDWVUPQHAC3VRTVZAFSKZI","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":"f732500bd9bdb7a0cf65bdd21bf52ca856e8736a5f4ac0d1989af8db170fc842","cross_cats_sorted":["cs.CE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T11:16:47Z","title_canon_sha256":"84cd0bcea00721bdb4e42956282c759795eff5dd9afcda12f4ecb60303b73153"},"schema_version":"1.0","source":{"id":"2410.12459","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12459","created_at":"2026-07-05T10:29:25Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12459v2","created_at":"2026-07-05T10:29:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12459","created_at":"2026-07-05T10:29:25Z"},{"alias_kind":"pith_short_12","alias_value":"SG7PUDWVUPQH","created_at":"2026-07-05T10:29:25Z"},{"alias_kind":"pith_short_16","alias_value":"SG7PUDWVUPQHAC3V","created_at":"2026-07-05T10:29:25Z"},{"alias_kind":"pith_short_8","alias_value":"SG7PUDWV","created_at":"2026-07-05T10:29:25Z"}],"graph_snapshots":[{"event_id":"sha256:26be5aa98544782f2e6a31714828f9da919fbe45fdeb0c5f2d99ef80a92fdddd","target":"graph","created_at":"2026-07-05T10:29:25Z","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/2410.12459/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Messenger RNA (mRNA) plays a crucial role in protein synthesis, with its codon structure directly impacting biological properties. While Language Models (LMs) have shown promise in analyzing biological sequences, existing approaches fail to account for the hierarchical nature of mRNA's codon structure. We introduce Hierarchical Encoding for mRNA Language Modeling (HELM), a novel pre-training strategy that incorporates codon-level hierarchical structure into language model training. HELM modulates the loss function based on codon synonymity, aligning the model's learning process with the biolog","authors_text":"Artem Moskalev, Mangal Prakash, Mehdi Yazdani-Jahromi, Rui Liao, Tommaso Mansi","cross_cats":["cs.CE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T11:16:47Z","title":"HELM: Hierarchical Encoding for mRNA Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12459","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":"sha256:1401efa31b377ea23a8fb1dcf0a178efdd25e040f88cbadcb0f451683a1f4064","target":"record","created_at":"2026-07-05T10:29:25Z","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":"f732500bd9bdb7a0cf65bdd21bf52ca856e8736a5f4ac0d1989af8db170fc842","cross_cats_sorted":["cs.CE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T11:16:47Z","title_canon_sha256":"84cd0bcea00721bdb4e42956282c759795eff5dd9afcda12f4ecb60303b73153"},"schema_version":"1.0","source":{"id":"2410.12459","kind":"arxiv","version":2}},"canonical_sha256":"91befa0ed5a3e0700b758ceb90164aca051891d9cde41c511dcb55fc89ede422","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91befa0ed5a3e0700b758ceb90164aca051891d9cde41c511dcb55fc89ede422","first_computed_at":"2026-07-05T10:29:25.032272Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:29:25.032272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dy+NgycXjk8xJ8JKN1SQTamM/xymwP8VugkyeQgrJrcCrvhiQ6HnsZPVKnFcxtz3kpBRLeMnz245dprr3qnFBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:29:25.033382Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12459","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1401efa31b377ea23a8fb1dcf0a178efdd25e040f88cbadcb0f451683a1f4064","sha256:26be5aa98544782f2e6a31714828f9da919fbe45fdeb0c5f2d99ef80a92fdddd"],"state_sha256":"6faf6c01ab09527e355facee1406d72e9380d956d4a61a59e33388b03ccf8edc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"31sjKb7uM+D3ci8KNJvM4yBkURf0x/FlVj+7Hcx0P56qyvXPEPRI6hed9pH8N4I5HhPUF+gTa51xwgDnFjNyDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T05:27:02.717956Z","bundle_sha256":"4dbdff6402613921a3b648722cc0b96b2844ce206172eff8ee2c760f0584bd25"}}