{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DAXVBFE3KSATVBQIXESGE5BIKC","short_pith_number":"pith:DAXVBFE3","canonical_record":{"source":{"id":"2504.11454","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-15T17:59:43Z","cross_cats_sorted":["cs.AI","q-bio.QM"],"title_canon_sha256":"2ef9a4e42d9f78e473cfb96e0ef72f00d82ea82d84f9b9674ad52d54b03edaad","abstract_canon_sha256":"19ba7a0cec4c2d98f4de88da78a3797d74b6a778e05fa2858065360bcb092901"},"schema_version":"1.0"},"canonical_sha256":"182f50949b54813a8608b9246274285099350c607e0b08b3ad166b85b7ba5beb","source":{"kind":"arxiv","id":"2504.11454","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.11454","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"arxiv_version","alias_value":"2504.11454v3","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11454","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"pith_short_12","alias_value":"DAXVBFE3KSAT","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"pith_short_16","alias_value":"DAXVBFE3KSATVBQI","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"pith_short_8","alias_value":"DAXVBFE3","created_at":"2026-07-05T11:20:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DAXVBFE3KSATVBQIXESGE5BIKC","target":"record","payload":{"canonical_record":{"source":{"id":"2504.11454","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-15T17:59:43Z","cross_cats_sorted":["cs.AI","q-bio.QM"],"title_canon_sha256":"2ef9a4e42d9f78e473cfb96e0ef72f00d82ea82d84f9b9674ad52d54b03edaad","abstract_canon_sha256":"19ba7a0cec4c2d98f4de88da78a3797d74b6a778e05fa2858065360bcb092901"},"schema_version":"1.0"},"canonical_sha256":"182f50949b54813a8608b9246274285099350c607e0b08b3ad166b85b7ba5beb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:11.417092Z","signature_b64":"x6uKZoMeZpvQN4LxUbRcRuzcBYEJlHjxLQyzBTxUTvsb4GH36I7QcJqmygM62ck2hW76Ofe4uRZz/6tQJ8UqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"182f50949b54813a8608b9246274285099350c607e0b08b3ad166b85b7ba5beb","last_reissued_at":"2026-07-05T11:20:11.416486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:11.416486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.11454","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:20:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DAJdq+YSllkqIYUjjGV3bUMQJDCYP8Gbp+0lA9pX7lplPaBTOmIvr0Deeptykq6UbThcfcRsU+rOKSwJEQhTAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:42:01.005246Z"},"content_sha256":"2dbcefb41120d743e5d6d84ee74c0f342c4e98699e614942a5c736eb69b4c5ac","schema_version":"1.0","event_id":"sha256:2dbcefb41120d743e5d6d84ee74c0f342c4e98699e614942a5c736eb69b4c5ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DAXVBFE3KSATVBQIXESGE5BIKC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Elucidating the Design Space of Multimodal Protein Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Cheng-Yen Hsieh, Daiheng Zhang, Dongyu Xue, Fei Ye, Quanquan Gu, Shujian Huang, Xinyou Wang, Zaixiang Zheng","submitted_at":"2025-04-15T17:59:43Z","abstract_excerpt":"Multimodal protein language models (PLMs) integrate sequence and token-based structural information, serving as a powerful foundation for protein modeling, generation, and design. However, the reliance on tokenizing 3D structures into discrete tokens causes substantial loss of fidelity about fine-grained structural details and correlations. In this paper, we systematically elucidate the design space of multimodal PLMs to overcome their limitations. We identify tokenization loss and inaccurate structure token predictions by the PLMs as major bottlenecks. To address these, our proposed design sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11454","kind":"arxiv","version":3},"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/2504.11454/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":"2026-07-05T11:20:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TOMnwrPtgFMvxNBg8FaPe/iXnFGYhGykEXZOLhW8J7vNxHbxVgTNX6kXJVH620Dit/ge3ccPNehdNt7IqCoeAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:42:01.006143Z"},"content_sha256":"a47f56e76b8367ea8be2bc68567965858c65a7a04783290b2bbe73b8fcce7956","schema_version":"1.0","event_id":"sha256:a47f56e76b8367ea8be2bc68567965858c65a7a04783290b2bbe73b8fcce7956"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DAXVBFE3KSATVBQIXESGE5BIKC/bundle.json","state_url":"https://pith.science/pith/DAXVBFE3KSATVBQIXESGE5BIKC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DAXVBFE3KSATVBQIXESGE5BIKC/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":"2026-08-04T16:42:01Z","links":{"resolver":"https://pith.science/pith/DAXVBFE3KSATVBQIXESGE5BIKC","bundle":"https://pith.science/pith/DAXVBFE3KSATVBQIXESGE5BIKC/bundle.json","state":"https://pith.science/pith/DAXVBFE3KSATVBQIXESGE5BIKC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DAXVBFE3KSATVBQIXESGE5BIKC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DAXVBFE3KSATVBQIXESGE5BIKC","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":"19ba7a0cec4c2d98f4de88da78a3797d74b6a778e05fa2858065360bcb092901","cross_cats_sorted":["cs.AI","q-bio.QM"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-15T17:59:43Z","title_canon_sha256":"2ef9a4e42d9f78e473cfb96e0ef72f00d82ea82d84f9b9674ad52d54b03edaad"},"schema_version":"1.0","source":{"id":"2504.11454","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.11454","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"arxiv_version","alias_value":"2504.11454v3","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11454","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"pith_short_12","alias_value":"DAXVBFE3KSAT","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"pith_short_16","alias_value":"DAXVBFE3KSATVBQI","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"pith_short_8","alias_value":"DAXVBFE3","created_at":"2026-07-05T11:20:11Z"}],"graph_snapshots":[{"event_id":"sha256:a47f56e76b8367ea8be2bc68567965858c65a7a04783290b2bbe73b8fcce7956","target":"graph","created_at":"2026-07-05T11:20:11Z","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/2504.11454/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal protein language models (PLMs) integrate sequence and token-based structural information, serving as a powerful foundation for protein modeling, generation, and design. However, the reliance on tokenizing 3D structures into discrete tokens causes substantial loss of fidelity about fine-grained structural details and correlations. In this paper, we systematically elucidate the design space of multimodal PLMs to overcome their limitations. We identify tokenization loss and inaccurate structure token predictions by the PLMs as major bottlenecks. To address these, our proposed design sp","authors_text":"Cheng-Yen Hsieh, Daiheng Zhang, Dongyu Xue, Fei Ye, Quanquan Gu, Shujian Huang, Xinyou Wang, Zaixiang Zheng","cross_cats":["cs.AI","q-bio.QM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-15T17:59:43Z","title":"Elucidating the Design Space of Multimodal Protein Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11454","kind":"arxiv","version":3},"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":"sha256:2dbcefb41120d743e5d6d84ee74c0f342c4e98699e614942a5c736eb69b4c5ac","target":"record","created_at":"2026-07-05T11:20:11Z","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":"19ba7a0cec4c2d98f4de88da78a3797d74b6a778e05fa2858065360bcb092901","cross_cats_sorted":["cs.AI","q-bio.QM"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-15T17:59:43Z","title_canon_sha256":"2ef9a4e42d9f78e473cfb96e0ef72f00d82ea82d84f9b9674ad52d54b03edaad"},"schema_version":"1.0","source":{"id":"2504.11454","kind":"arxiv","version":3}},"canonical_sha256":"182f50949b54813a8608b9246274285099350c607e0b08b3ad166b85b7ba5beb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"182f50949b54813a8608b9246274285099350c607e0b08b3ad166b85b7ba5beb","first_computed_at":"2026-07-05T11:20:11.416486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:11.416486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x6uKZoMeZpvQN4LxUbRcRuzcBYEJlHjxLQyzBTxUTvsb4GH36I7QcJqmygM62ck2hW76Ofe4uRZz/6tQJ8UqCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:11.417092Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.11454","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2dbcefb41120d743e5d6d84ee74c0f342c4e98699e614942a5c736eb69b4c5ac","sha256:a47f56e76b8367ea8be2bc68567965858c65a7a04783290b2bbe73b8fcce7956"],"state_sha256":"4c255415939c8ff939bb8bca29769cda9a8746ebc76c88cd0fdc3fcd0f2bf351"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mEBpOTfMu00t6kpPqoqC79YBHILddN9clUZCWTSecxEHI12qPbfl7M1k5BPpO4r2rXo32wj6hcaHTxti3O9+Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T16:42:01.013877Z","bundle_sha256":"cd1599a5b67089cf3df5c06059aef4b3b9ac9100b87b2fcb5d8658f45adb557c"}}