{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WI3MW6BKTQE3575RUMOMSKSYS6","short_pith_number":"pith:WI3MW6BK","canonical_record":{"source":{"id":"2404.15805","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-04-24T11:09:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"89521cb93e99326392c25a59ee41bd2f544a93b2ead165437a2c66602ae5a295","abstract_canon_sha256":"25c57e6340b06740283b001256cbac4a261c4e9abe08b7b0ede2f76e7e6f42d7"},"schema_version":"1.0"},"canonical_sha256":"b236cb782a9c09beffb1a31cc92a5897b72ab6aff7a601729b2bc8f96e2c67d4","source":{"kind":"arxiv","id":"2404.15805","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.15805","created_at":"2026-07-05T08:11:45Z"},{"alias_kind":"arxiv_version","alias_value":"2404.15805v1","created_at":"2026-07-05T08:11:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15805","created_at":"2026-07-05T08:11:45Z"},{"alias_kind":"pith_short_12","alias_value":"WI3MW6BKTQE3","created_at":"2026-07-05T08:11:45Z"},{"alias_kind":"pith_short_16","alias_value":"WI3MW6BKTQE3575R","created_at":"2026-07-05T08:11:45Z"},{"alias_kind":"pith_short_8","alias_value":"WI3MW6BK","created_at":"2026-07-05T08:11:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WI3MW6BKTQE3575RUMOMSKSYS6","target":"record","payload":{"canonical_record":{"source":{"id":"2404.15805","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-04-24T11:09:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"89521cb93e99326392c25a59ee41bd2f544a93b2ead165437a2c66602ae5a295","abstract_canon_sha256":"25c57e6340b06740283b001256cbac4a261c4e9abe08b7b0ede2f76e7e6f42d7"},"schema_version":"1.0"},"canonical_sha256":"b236cb782a9c09beffb1a31cc92a5897b72ab6aff7a601729b2bc8f96e2c67d4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:45.619130Z","signature_b64":"w3MRz5cPFj7iRjVIMsG6ZdjyyXKT/Pi3M5RhmEjpnJ0fxHDinJqRKOB48EbSi3P5sGxvFe2WOL2U7gp8I35PDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b236cb782a9c09beffb1a31cc92a5897b72ab6aff7a601729b2bc8f96e2c67d4","last_reissued_at":"2026-07-05T08:11:45.618721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:45.618721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.15805","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":"2026-07-05T08:11:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kZXQbxYUVac/KLIibTx+E8O05oy28jonGzG80a+XlPnDD3rJeGkTWGL2dZxcgcYg/nNpyW7y/Ftf9Thj66R2DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:50:55.541660Z"},"content_sha256":"459259a9a37b945105d34528dd708a1c1f5305c80877d14329dccb542414f62e","schema_version":"1.0","event_id":"sha256:459259a9a37b945105d34528dd708a1c1f5305c80877d14329dccb542414f62e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WI3MW6BKTQE3575RUMOMSKSYS6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond ESM2: Graph-Enhanced Protein Sequence Modeling with Efficient Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Bingxuan Li, Jiajie Peng, Lei Wang, Shujian Jiao, Wei Chen, Xiaojin Zhang, Zhongyu Wei","submitted_at":"2024-04-24T11:09:43Z","abstract_excerpt":"Proteins are essential to life's processes, underpinning evolution and diversity. Advances in sequencing technology have revealed millions of proteins, underscoring the need for sophisticated pre-trained protein models for biological analysis and AI development. Facebook's ESM2, the most advanced protein language model to date, leverages a masked prediction task for unsupervised learning, crafting amino acid representations with notable biochemical accuracy. Yet, it lacks in delivering functional protein insights, signaling an opportunity for enhancing representation quality.Our study addresse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15805","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/2404.15805/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":"2026-07-05T08:11:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0PcHfjVK8CyEhXGj+bfXNNpvnmtDz2fisDW+y99Vt3MglOFXb5m/ndvSmdEYK017Qha24qZYn4V1yBHWEGYQDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:50:55.542610Z"},"content_sha256":"e5417b4e8dd937d69bf6be317b7f39669b176c084c15391fc86804c46f8234ea","schema_version":"1.0","event_id":"sha256:e5417b4e8dd937d69bf6be317b7f39669b176c084c15391fc86804c46f8234ea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WI3MW6BKTQE3575RUMOMSKSYS6/bundle.json","state_url":"https://pith.science/pith/WI3MW6BKTQE3575RUMOMSKSYS6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WI3MW6BKTQE3575RUMOMSKSYS6/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":"2026-08-09T18:50:55Z","links":{"resolver":"https://pith.science/pith/WI3MW6BKTQE3575RUMOMSKSYS6","bundle":"https://pith.science/pith/WI3MW6BKTQE3575RUMOMSKSYS6/bundle.json","state":"https://pith.science/pith/WI3MW6BKTQE3575RUMOMSKSYS6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WI3MW6BKTQE3575RUMOMSKSYS6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WI3MW6BKTQE3575RUMOMSKSYS6","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":"25c57e6340b06740283b001256cbac4a261c4e9abe08b7b0ede2f76e7e6f42d7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-04-24T11:09:43Z","title_canon_sha256":"89521cb93e99326392c25a59ee41bd2f544a93b2ead165437a2c66602ae5a295"},"schema_version":"1.0","source":{"id":"2404.15805","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.15805","created_at":"2026-07-05T08:11:45Z"},{"alias_kind":"arxiv_version","alias_value":"2404.15805v1","created_at":"2026-07-05T08:11:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15805","created_at":"2026-07-05T08:11:45Z"},{"alias_kind":"pith_short_12","alias_value":"WI3MW6BKTQE3","created_at":"2026-07-05T08:11:45Z"},{"alias_kind":"pith_short_16","alias_value":"WI3MW6BKTQE3575R","created_at":"2026-07-05T08:11:45Z"},{"alias_kind":"pith_short_8","alias_value":"WI3MW6BK","created_at":"2026-07-05T08:11:45Z"}],"graph_snapshots":[{"event_id":"sha256:e5417b4e8dd937d69bf6be317b7f39669b176c084c15391fc86804c46f8234ea","target":"graph","created_at":"2026-07-05T08:11:45Z","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/2404.15805/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Proteins are essential to life's processes, underpinning evolution and diversity. Advances in sequencing technology have revealed millions of proteins, underscoring the need for sophisticated pre-trained protein models for biological analysis and AI development. Facebook's ESM2, the most advanced protein language model to date, leverages a masked prediction task for unsupervised learning, crafting amino acid representations with notable biochemical accuracy. Yet, it lacks in delivering functional protein insights, signaling an opportunity for enhancing representation quality.Our study addresse","authors_text":"Bingxuan Li, Jiajie Peng, Lei Wang, Shujian Jiao, Wei Chen, Xiaojin Zhang, Zhongyu Wei","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-04-24T11:09:43Z","title":"Beyond ESM2: Graph-Enhanced Protein Sequence Modeling with Efficient Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15805","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":"sha256:459259a9a37b945105d34528dd708a1c1f5305c80877d14329dccb542414f62e","target":"record","created_at":"2026-07-05T08:11:45Z","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":"25c57e6340b06740283b001256cbac4a261c4e9abe08b7b0ede2f76e7e6f42d7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-04-24T11:09:43Z","title_canon_sha256":"89521cb93e99326392c25a59ee41bd2f544a93b2ead165437a2c66602ae5a295"},"schema_version":"1.0","source":{"id":"2404.15805","kind":"arxiv","version":1}},"canonical_sha256":"b236cb782a9c09beffb1a31cc92a5897b72ab6aff7a601729b2bc8f96e2c67d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b236cb782a9c09beffb1a31cc92a5897b72ab6aff7a601729b2bc8f96e2c67d4","first_computed_at":"2026-07-05T08:11:45.618721Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:11:45.618721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w3MRz5cPFj7iRjVIMsG6ZdjyyXKT/Pi3M5RhmEjpnJ0fxHDinJqRKOB48EbSi3P5sGxvFe2WOL2U7gp8I35PDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:11:45.619130Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.15805","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:459259a9a37b945105d34528dd708a1c1f5305c80877d14329dccb542414f62e","sha256:e5417b4e8dd937d69bf6be317b7f39669b176c084c15391fc86804c46f8234ea"],"state_sha256":"84a335d5cddf695aef1e48f5b3bee47d3f678a6b6563a739bd476083c369045f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kwg98F/DYb8ZYcqdznwiOGqOvWHNHyI5PJVeu8riU9UKWDbx4VUTTHAge/jHpaO2UQCWcPF/oubLMXaTp8HgCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:50:55.549560Z","bundle_sha256":"e9938b9240d845f831917d58e9542ad07fc69d6ab84542e3e412c87fa7ba7c65"}}