{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QV4K6KIFKEFUKCKFFEDZYEOG3U","short_pith_number":"pith:QV4K6KIF","canonical_record":{"source":{"id":"2306.08018","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2023-06-13T14:35:34Z","cross_cats_sorted":["cs.AI","cs.CE","cs.CL","cs.IR","cs.LG"],"title_canon_sha256":"cd75909dec5b4932803dc514695a3d572aa1be37743105333b8e8106f6bc2f1a","abstract_canon_sha256":"802f5e3fde39581dffd9e8c0e4942ca51a355942b6c0936ac57751cf0842a9c6"},"schema_version":"1.0"},"canonical_sha256":"8578af2905510b45094529079c11c6dd1afa32fe2ec7e23aa42b4cd3d3a24ed5","source":{"kind":"arxiv","id":"2306.08018","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.08018","created_at":"2026-07-05T07:51:29Z"},{"alias_kind":"arxiv_version","alias_value":"2306.08018v5","created_at":"2026-07-05T07:51:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08018","created_at":"2026-07-05T07:51:29Z"},{"alias_kind":"pith_short_12","alias_value":"QV4K6KIFKEFU","created_at":"2026-07-05T07:51:29Z"},{"alias_kind":"pith_short_16","alias_value":"QV4K6KIFKEFUKCKF","created_at":"2026-07-05T07:51:29Z"},{"alias_kind":"pith_short_8","alias_value":"QV4K6KIF","created_at":"2026-07-05T07:51:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QV4K6KIFKEFUKCKFFEDZYEOG3U","target":"record","payload":{"canonical_record":{"source":{"id":"2306.08018","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2023-06-13T14:35:34Z","cross_cats_sorted":["cs.AI","cs.CE","cs.CL","cs.IR","cs.LG"],"title_canon_sha256":"cd75909dec5b4932803dc514695a3d572aa1be37743105333b8e8106f6bc2f1a","abstract_canon_sha256":"802f5e3fde39581dffd9e8c0e4942ca51a355942b6c0936ac57751cf0842a9c6"},"schema_version":"1.0"},"canonical_sha256":"8578af2905510b45094529079c11c6dd1afa32fe2ec7e23aa42b4cd3d3a24ed5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:29.594648Z","signature_b64":"ER1zt00/rbqhuYH5BmIZE+JMd4mc3Go7SJBJUdUevLvohgZ7fU7Kbg7nf9h8A1RN1gfStJWNcxbtk9Q91/ywDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8578af2905510b45094529079c11c6dd1afa32fe2ec7e23aa42b4cd3d3a24ed5","last_reissued_at":"2026-07-05T07:51:29.594131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:29.594131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.08018","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:51:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QF3TsjwE0VEAagQigtPtoYZjEG1WWg0swJuDdPoO6KMrocE8COdFfDNjqxr/ZmE/0Urm3zoLHRo4UPAFlyFGDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:41:29.398421Z"},"content_sha256":"dbea950128b1852812ee4268f5b32b23120c1daf7bb06a4338ccf680cff9e80c","schema_version":"1.0","event_id":"sha256:dbea950128b1852812ee4268f5b32b23120c1daf7bb06a4338ccf680cff9e80c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QV4K6KIFKEFUKCKFFEDZYEOG3U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.CL","cs.IR","cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Huajun Chen, Kangwei Liu, Ningyu Zhang, Rui Huang, Xiaohui Fan, Xiaozhuan Liang, Yin Fang, Zhuo Chen","submitted_at":"2023-06-13T14:35:34Z","abstract_excerpt":"Large Language Models (LLMs), with their remarkable task-handling capabilities and innovative outputs, have catalyzed significant advancements across a spectrum of fields. However, their proficiency within specialized domains such as biomolecular studies remains limited. To address this challenge, we introduce Mol-Instructions, a comprehensive instruction dataset designed for the biomolecular domain. Mol-Instructions encompasses three key components: molecule-oriented instructions, protein-oriented instructions, and biomolecular text instructions. Each component aims to improve the understandi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08018","kind":"arxiv","version":5},"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/2306.08018/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":"2026-07-05T07:51:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vSpKuagDaesPvO9wt/XPDmN6MGETIDtWxPx/MvABo3e6h1sbm/DxR0NFZDEydqxVzMduoQHaM67g20WNqrZQAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:41:29.398948Z"},"content_sha256":"1cb15b2f9cb595d98d4d7c3061f192b68b01690205edcfa0250799ed24a011dc","schema_version":"1.0","event_id":"sha256:1cb15b2f9cb595d98d4d7c3061f192b68b01690205edcfa0250799ed24a011dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QV4K6KIFKEFUKCKFFEDZYEOG3U/bundle.json","state_url":"https://pith.science/pith/QV4K6KIFKEFUKCKFFEDZYEOG3U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QV4K6KIFKEFUKCKFFEDZYEOG3U/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":"2026-08-14T08:41:29Z","links":{"resolver":"https://pith.science/pith/QV4K6KIFKEFUKCKFFEDZYEOG3U","bundle":"https://pith.science/pith/QV4K6KIFKEFUKCKFFEDZYEOG3U/bundle.json","state":"https://pith.science/pith/QV4K6KIFKEFUKCKFFEDZYEOG3U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QV4K6KIFKEFUKCKFFEDZYEOG3U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QV4K6KIFKEFUKCKFFEDZYEOG3U","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":"802f5e3fde39581dffd9e8c0e4942ca51a355942b6c0936ac57751cf0842a9c6","cross_cats_sorted":["cs.AI","cs.CE","cs.CL","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2023-06-13T14:35:34Z","title_canon_sha256":"cd75909dec5b4932803dc514695a3d572aa1be37743105333b8e8106f6bc2f1a"},"schema_version":"1.0","source":{"id":"2306.08018","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.08018","created_at":"2026-07-05T07:51:29Z"},{"alias_kind":"arxiv_version","alias_value":"2306.08018v5","created_at":"2026-07-05T07:51:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08018","created_at":"2026-07-05T07:51:29Z"},{"alias_kind":"pith_short_12","alias_value":"QV4K6KIFKEFU","created_at":"2026-07-05T07:51:29Z"},{"alias_kind":"pith_short_16","alias_value":"QV4K6KIFKEFUKCKF","created_at":"2026-07-05T07:51:29Z"},{"alias_kind":"pith_short_8","alias_value":"QV4K6KIF","created_at":"2026-07-05T07:51:29Z"}],"graph_snapshots":[{"event_id":"sha256:1cb15b2f9cb595d98d4d7c3061f192b68b01690205edcfa0250799ed24a011dc","target":"graph","created_at":"2026-07-05T07:51:29Z","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/2306.08018/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs), with their remarkable task-handling capabilities and innovative outputs, have catalyzed significant advancements across a spectrum of fields. However, their proficiency within specialized domains such as biomolecular studies remains limited. To address this challenge, we introduce Mol-Instructions, a comprehensive instruction dataset designed for the biomolecular domain. Mol-Instructions encompasses three key components: molecule-oriented instructions, protein-oriented instructions, and biomolecular text instructions. Each component aims to improve the understandi","authors_text":"Huajun Chen, Kangwei Liu, Ningyu Zhang, Rui Huang, Xiaohui Fan, Xiaozhuan Liang, Yin Fang, Zhuo Chen","cross_cats":["cs.AI","cs.CE","cs.CL","cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2023-06-13T14:35:34Z","title":"Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08018","kind":"arxiv","version":5},"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:dbea950128b1852812ee4268f5b32b23120c1daf7bb06a4338ccf680cff9e80c","target":"record","created_at":"2026-07-05T07:51:29Z","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":"802f5e3fde39581dffd9e8c0e4942ca51a355942b6c0936ac57751cf0842a9c6","cross_cats_sorted":["cs.AI","cs.CE","cs.CL","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2023-06-13T14:35:34Z","title_canon_sha256":"cd75909dec5b4932803dc514695a3d572aa1be37743105333b8e8106f6bc2f1a"},"schema_version":"1.0","source":{"id":"2306.08018","kind":"arxiv","version":5}},"canonical_sha256":"8578af2905510b45094529079c11c6dd1afa32fe2ec7e23aa42b4cd3d3a24ed5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8578af2905510b45094529079c11c6dd1afa32fe2ec7e23aa42b4cd3d3a24ed5","first_computed_at":"2026-07-05T07:51:29.594131Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:29.594131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ER1zt00/rbqhuYH5BmIZE+JMd4mc3Go7SJBJUdUevLvohgZ7fU7Kbg7nf9h8A1RN1gfStJWNcxbtk9Q91/ywDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:29.594648Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.08018","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbea950128b1852812ee4268f5b32b23120c1daf7bb06a4338ccf680cff9e80c","sha256:1cb15b2f9cb595d98d4d7c3061f192b68b01690205edcfa0250799ed24a011dc"],"state_sha256":"90d9c743f0491bab8cc0681c8a484e92f613e4e77b89e685eca911e798fe2558"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p2uoTbWXS4Q5jP9gEbp2Ebe153rhoIy4STQk6NKhkUFgJITSILTCdHC/sT3nPCoqVAkp4C7BgZWBHnj/MAiVDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T08:41:29.404320Z","bundle_sha256":"3f4b22e5b831f90a95e070b6e04c68b0bbc4d66257412fa92ea14ab3f90574d3"}}