{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XYK6JPLLPJTHCJVN2ZJMSBCBG6","short_pith_number":"pith:XYK6JPLL","canonical_record":{"source":{"id":"2503.08179","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2025-03-11T08:43:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bc057f669503cea1d4c5b78330af1cce042c3359cc116f399b648cc93b2778eb","abstract_canon_sha256":"faf5df572d021eb0a254c8b6867da826e07baf85aa6c2d32c35475d74952ab7c"},"schema_version":"1.0"},"canonical_sha256":"be15e4bd6b7a667126add652c90441379ea8d5279d95ebd4d4a07b5ec08c2581","source":{"kind":"arxiv","id":"2503.08179","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.08179","created_at":"2026-07-05T10:30:33Z"},{"alias_kind":"arxiv_version","alias_value":"2503.08179v3","created_at":"2026-07-05T10:30:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08179","created_at":"2026-07-05T10:30:33Z"},{"alias_kind":"pith_short_12","alias_value":"XYK6JPLLPJTH","created_at":"2026-07-05T10:30:33Z"},{"alias_kind":"pith_short_16","alias_value":"XYK6JPLLPJTHCJVN","created_at":"2026-07-05T10:30:33Z"},{"alias_kind":"pith_short_8","alias_value":"XYK6JPLL","created_at":"2026-07-05T10:30:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XYK6JPLLPJTHCJVN2ZJMSBCBG6","target":"record","payload":{"canonical_record":{"source":{"id":"2503.08179","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2025-03-11T08:43:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bc057f669503cea1d4c5b78330af1cce042c3359cc116f399b648cc93b2778eb","abstract_canon_sha256":"faf5df572d021eb0a254c8b6867da826e07baf85aa6c2d32c35475d74952ab7c"},"schema_version":"1.0"},"canonical_sha256":"be15e4bd6b7a667126add652c90441379ea8d5279d95ebd4d4a07b5ec08c2581","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:33.403069Z","signature_b64":"hjuDmjhts0Xlwmt459TRwNZndCwL9PmODZIx6KjcWU6n/EmIeQa+SPtQzDInP+M01jt8PrwZAG32n/Wv6IYqBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be15e4bd6b7a667126add652c90441379ea8d5279d95ebd4d4a07b5ec08c2581","last_reissued_at":"2026-07-05T10:30:33.402580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:33.402580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.08179","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":"2026-07-05T10:30:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TG8vwvLc5L0FjDjXduIgon1pBbxPNaRj+w2mlLiXGTyQAXz5xduX5pE4KNi5E8iQV9XHg1KMnpH/rgG9R1E4Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:51:43.199997Z"},"content_sha256":"42e06765c03e82824d7d3f22bf5deb82729f7640ee006f42376747d038e51882","schema_version":"1.0","event_id":"sha256:42e06765c03e82824d7d3f22bf5deb82729f7640ee006f42376747d038e51882"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XYK6JPLLPJTHCJVN2ZJMSBCBG6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ProtTeX: Structure-In-Context Reasoning and Editing of Proteins with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"q-bio.BM","authors_text":"Chuanliu Fan, Jun Zhang, Shihao Feng, Xiaohan Lin, Yanheng Li, Yi Qin Gao, Zhenyu Chen, Zhicong Wang, Zicheng Ma, Ziqiang Cao","submitted_at":"2025-03-11T08:43:05Z","abstract_excerpt":"Large language models have made remarkable progress in the field of molecular science, particularly in understanding and generating functional small molecules. This success is largely attributed to the effectiveness of molecular tokenization strategies. In protein science, the amino acid sequence serves as the sole tokenizer for LLMs. However, many fundamental challenges in protein science are inherently structure-dependent. The absence of structure-aware tokens significantly limits the capabilities of LLMs for comprehensive biomolecular comprehension and multimodal generation. To address thes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08179","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/2503.08179/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":"2026-07-05T10:30:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ox8y4wtLiUmxkAMLCY9lI/Hk1hsM44ZtT4B9zsVAzaiPoK/Cw+pxPOnlvEMLxDnZ4EZBEIHP6gIQAq1eQ/OJAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:51:43.200419Z"},"content_sha256":"5f2296aeb0e9f1868c0cc4df733afe025ccd58157f09316a89809fa618782ef1","schema_version":"1.0","event_id":"sha256:5f2296aeb0e9f1868c0cc4df733afe025ccd58157f09316a89809fa618782ef1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XYK6JPLLPJTHCJVN2ZJMSBCBG6/bundle.json","state_url":"https://pith.science/pith/XYK6JPLLPJTHCJVN2ZJMSBCBG6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XYK6JPLLPJTHCJVN2ZJMSBCBG6/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":"2026-08-03T19:51:43Z","links":{"resolver":"https://pith.science/pith/XYK6JPLLPJTHCJVN2ZJMSBCBG6","bundle":"https://pith.science/pith/XYK6JPLLPJTHCJVN2ZJMSBCBG6/bundle.json","state":"https://pith.science/pith/XYK6JPLLPJTHCJVN2ZJMSBCBG6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XYK6JPLLPJTHCJVN2ZJMSBCBG6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XYK6JPLLPJTHCJVN2ZJMSBCBG6","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":"faf5df572d021eb0a254c8b6867da826e07baf85aa6c2d32c35475d74952ab7c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2025-03-11T08:43:05Z","title_canon_sha256":"bc057f669503cea1d4c5b78330af1cce042c3359cc116f399b648cc93b2778eb"},"schema_version":"1.0","source":{"id":"2503.08179","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.08179","created_at":"2026-07-05T10:30:33Z"},{"alias_kind":"arxiv_version","alias_value":"2503.08179v3","created_at":"2026-07-05T10:30:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08179","created_at":"2026-07-05T10:30:33Z"},{"alias_kind":"pith_short_12","alias_value":"XYK6JPLLPJTH","created_at":"2026-07-05T10:30:33Z"},{"alias_kind":"pith_short_16","alias_value":"XYK6JPLLPJTHCJVN","created_at":"2026-07-05T10:30:33Z"},{"alias_kind":"pith_short_8","alias_value":"XYK6JPLL","created_at":"2026-07-05T10:30:33Z"}],"graph_snapshots":[{"event_id":"sha256:5f2296aeb0e9f1868c0cc4df733afe025ccd58157f09316a89809fa618782ef1","target":"graph","created_at":"2026-07-05T10:30:33Z","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/2503.08179/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models have made remarkable progress in the field of molecular science, particularly in understanding and generating functional small molecules. This success is largely attributed to the effectiveness of molecular tokenization strategies. In protein science, the amino acid sequence serves as the sole tokenizer for LLMs. However, many fundamental challenges in protein science are inherently structure-dependent. The absence of structure-aware tokens significantly limits the capabilities of LLMs for comprehensive biomolecular comprehension and multimodal generation. To address thes","authors_text":"Chuanliu Fan, Jun Zhang, Shihao Feng, Xiaohan Lin, Yanheng Li, Yi Qin Gao, Zhenyu Chen, Zhicong Wang, Zicheng Ma, Ziqiang Cao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2025-03-11T08:43:05Z","title":"ProtTeX: Structure-In-Context Reasoning and Editing of Proteins with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08179","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":"sha256:42e06765c03e82824d7d3f22bf5deb82729f7640ee006f42376747d038e51882","target":"record","created_at":"2026-07-05T10:30:33Z","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":"faf5df572d021eb0a254c8b6867da826e07baf85aa6c2d32c35475d74952ab7c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2025-03-11T08:43:05Z","title_canon_sha256":"bc057f669503cea1d4c5b78330af1cce042c3359cc116f399b648cc93b2778eb"},"schema_version":"1.0","source":{"id":"2503.08179","kind":"arxiv","version":3}},"canonical_sha256":"be15e4bd6b7a667126add652c90441379ea8d5279d95ebd4d4a07b5ec08c2581","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be15e4bd6b7a667126add652c90441379ea8d5279d95ebd4d4a07b5ec08c2581","first_computed_at":"2026-07-05T10:30:33.402580Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:30:33.402580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hjuDmjhts0Xlwmt459TRwNZndCwL9PmODZIx6KjcWU6n/EmIeQa+SPtQzDInP+M01jt8PrwZAG32n/Wv6IYqBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:30:33.403069Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.08179","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42e06765c03e82824d7d3f22bf5deb82729f7640ee006f42376747d038e51882","sha256:5f2296aeb0e9f1868c0cc4df733afe025ccd58157f09316a89809fa618782ef1"],"state_sha256":"b8c77bfb76eba7555c09aa8dbfe6bce8c3ed654601e3503664a45843e12b2867"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pLd/WJcsUw9EJ5om0jyxigdBxQTnxyi/Jgy1/mc5CMw17WUJwvWlYS/hfY5rMmsbLzJGFS7TtAF9pl0YvTKNBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:51:43.203092Z","bundle_sha256":"190a618115aae4e70789cbd6937393333e398fb556289411a99674cf33ad4c34"}}