{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AA2YSUITOGFKGXYBQPPNMCAEPS","short_pith_number":"pith:AA2YSUIT","canonical_record":{"source":{"id":"2503.00089","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-02-28T15:14:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f1f29f464c851b9a7d3aec062d717ebef451f024e73618b4409db0d193fc98a0","abstract_canon_sha256":"8f0c88d384b9298a1e407d82ccc7a99848011e72dbe3b779dfdaaf9ca71d6d39"},"schema_version":"1.0"},"canonical_sha256":"0035895113718aa35f0183ded608047c82a9b1d8b50b60088d690cf56433a90a","source":{"kind":"arxiv","id":"2503.00089","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.00089","created_at":"2026-07-05T11:26:48Z"},{"alias_kind":"arxiv_version","alias_value":"2503.00089v2","created_at":"2026-07-05T11:26:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00089","created_at":"2026-07-05T11:26:48Z"},{"alias_kind":"pith_short_12","alias_value":"AA2YSUITOGFK","created_at":"2026-07-05T11:26:48Z"},{"alias_kind":"pith_short_16","alias_value":"AA2YSUITOGFKGXYB","created_at":"2026-07-05T11:26:48Z"},{"alias_kind":"pith_short_8","alias_value":"AA2YSUIT","created_at":"2026-07-05T11:26:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AA2YSUITOGFKGXYBQPPNMCAEPS","target":"record","payload":{"canonical_record":{"source":{"id":"2503.00089","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-02-28T15:14:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f1f29f464c851b9a7d3aec062d717ebef451f024e73618b4409db0d193fc98a0","abstract_canon_sha256":"8f0c88d384b9298a1e407d82ccc7a99848011e72dbe3b779dfdaaf9ca71d6d39"},"schema_version":"1.0"},"canonical_sha256":"0035895113718aa35f0183ded608047c82a9b1d8b50b60088d690cf56433a90a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:48.457348Z","signature_b64":"6gpdn4hHk+5wBMm8knXMX3qflwcxfCtmPzwB68fPk6B7dxFcfrSSlbWoiI9BIVsYzo3vUI4Hug6a8TYrsRLbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0035895113718aa35f0183ded608047c82a9b1d8b50b60088d690cf56433a90a","last_reissued_at":"2026-07-05T11:26:48.456804Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:48.456804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.00089","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":"2026-07-05T11:26:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ggaZ8uuxoEPBZQmXaIUEVsbmoJRMLZIhPwhQTpGBYjP2ViXj+rcuw9ERqiGu7wu0l7sfvoHI4wVrivyl4H3xDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:12:20.942519Z"},"content_sha256":"eea9bc92ab991ec4e7935875a046d1f230384cb84da0bbc58f363f20d9ebee0f","schema_version":"1.0","event_id":"sha256:eea9bc92ab991ec4e7935875a046d1f230384cb84da0bbc58f363f20d9ebee0f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AA2YSUITOGFKGXYBQPPNMCAEPS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Protein Structure Tokenization: Benchmarking and New Recipe","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Huzefa Rangwala, Marcus Collins, Xinyu Yuan, Zichen Wang","submitted_at":"2025-02-28T15:14:33Z","abstract_excerpt":"Recent years have witnessed a surge in the development of protein structural tokenization methods, which chunk protein 3D structures into discrete or continuous representations. Structure tokenization enables the direct application of powerful techniques like language modeling for protein structures, and large multimodal models to integrate structures with protein sequences and functional texts. Despite the progress, the capabilities and limitations of these methods remain poorly understood due to the lack of a unified evaluation framework. We first introduce StructTokenBench, a framework that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00089","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/2503.00089/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":"2026-07-05T11:26:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3dIijoVgo872t0CWv6m5BgsD4LFZn/WlV2fmbh3pKGAQTEQHF3aMrAZAS+WoAEQtymheTMJzG3YRDm/HXKngDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:12:20.943056Z"},"content_sha256":"2270018975074ba0fe3d91cb924a6a42266ec12ebb6e60a0b3f2422da775c164","schema_version":"1.0","event_id":"sha256:2270018975074ba0fe3d91cb924a6a42266ec12ebb6e60a0b3f2422da775c164"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AA2YSUITOGFKGXYBQPPNMCAEPS/bundle.json","state_url":"https://pith.science/pith/AA2YSUITOGFKGXYBQPPNMCAEPS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AA2YSUITOGFKGXYBQPPNMCAEPS/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":"2026-08-08T20:12:20Z","links":{"resolver":"https://pith.science/pith/AA2YSUITOGFKGXYBQPPNMCAEPS","bundle":"https://pith.science/pith/AA2YSUITOGFKGXYBQPPNMCAEPS/bundle.json","state":"https://pith.science/pith/AA2YSUITOGFKGXYBQPPNMCAEPS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AA2YSUITOGFKGXYBQPPNMCAEPS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AA2YSUITOGFKGXYBQPPNMCAEPS","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":"8f0c88d384b9298a1e407d82ccc7a99848011e72dbe3b779dfdaaf9ca71d6d39","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-02-28T15:14:33Z","title_canon_sha256":"f1f29f464c851b9a7d3aec062d717ebef451f024e73618b4409db0d193fc98a0"},"schema_version":"1.0","source":{"id":"2503.00089","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.00089","created_at":"2026-07-05T11:26:48Z"},{"alias_kind":"arxiv_version","alias_value":"2503.00089v2","created_at":"2026-07-05T11:26:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00089","created_at":"2026-07-05T11:26:48Z"},{"alias_kind":"pith_short_12","alias_value":"AA2YSUITOGFK","created_at":"2026-07-05T11:26:48Z"},{"alias_kind":"pith_short_16","alias_value":"AA2YSUITOGFKGXYB","created_at":"2026-07-05T11:26:48Z"},{"alias_kind":"pith_short_8","alias_value":"AA2YSUIT","created_at":"2026-07-05T11:26:48Z"}],"graph_snapshots":[{"event_id":"sha256:2270018975074ba0fe3d91cb924a6a42266ec12ebb6e60a0b3f2422da775c164","target":"graph","created_at":"2026-07-05T11:26:48Z","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/2503.00089/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent years have witnessed a surge in the development of protein structural tokenization methods, which chunk protein 3D structures into discrete or continuous representations. Structure tokenization enables the direct application of powerful techniques like language modeling for protein structures, and large multimodal models to integrate structures with protein sequences and functional texts. Despite the progress, the capabilities and limitations of these methods remain poorly understood due to the lack of a unified evaluation framework. We first introduce StructTokenBench, a framework that","authors_text":"Huzefa Rangwala, Marcus Collins, Xinyu Yuan, Zichen Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-02-28T15:14:33Z","title":"Protein Structure Tokenization: Benchmarking and New Recipe"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00089","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:eea9bc92ab991ec4e7935875a046d1f230384cb84da0bbc58f363f20d9ebee0f","target":"record","created_at":"2026-07-05T11:26:48Z","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":"8f0c88d384b9298a1e407d82ccc7a99848011e72dbe3b779dfdaaf9ca71d6d39","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-02-28T15:14:33Z","title_canon_sha256":"f1f29f464c851b9a7d3aec062d717ebef451f024e73618b4409db0d193fc98a0"},"schema_version":"1.0","source":{"id":"2503.00089","kind":"arxiv","version":2}},"canonical_sha256":"0035895113718aa35f0183ded608047c82a9b1d8b50b60088d690cf56433a90a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0035895113718aa35f0183ded608047c82a9b1d8b50b60088d690cf56433a90a","first_computed_at":"2026-07-05T11:26:48.456804Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:48.456804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6gpdn4hHk+5wBMm8knXMX3qflwcxfCtmPzwB68fPk6B7dxFcfrSSlbWoiI9BIVsYzo3vUI4Hug6a8TYrsRLbCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:48.457348Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.00089","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eea9bc92ab991ec4e7935875a046d1f230384cb84da0bbc58f363f20d9ebee0f","sha256:2270018975074ba0fe3d91cb924a6a42266ec12ebb6e60a0b3f2422da775c164"],"state_sha256":"9d6a11180166b2037c368d5ecb19a9924da04298a9a5afd153a1f75ea9924875"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mioxir92F+lrW4a6c+Vhd+8+/TVg+/LWsVPjHUH2CEYf8szDgZXB1B1FZV+MyrLAI00A6Hola1kN6Mquh6ODBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:12:20.947266Z","bundle_sha256":"a8021de558381d94e67b602b35612f388dba819d0cf50cbc848ad5d909e499db"}}