{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RU2XKVNM47AHZXB3XM4366K5WQ","short_pith_number":"pith:RU2XKVNM","canonical_record":{"source":{"id":"2403.00791","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T20:11:24Z","cross_cats_sorted":["cs.AI","q-bio.BM","q-bio.QM"],"title_canon_sha256":"63227982eb1ecc0be26bf4d2792164352f959a3ba5ab86e886dd8e1c51eaea41","abstract_canon_sha256":"7834d0dac9ca6645be37e3a6065d416945bccf435b74b038f6d4d2cf0bae0d9b"},"schema_version":"1.0"},"canonical_sha256":"8d357555ace7c07cdc3bbb39bf795db43cfc0238bdeb1caaaf108ee9d4efc31e","source":{"kind":"arxiv","id":"2403.00791","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.00791","created_at":"2026-07-05T08:40:14Z"},{"alias_kind":"arxiv_version","alias_value":"2403.00791v2","created_at":"2026-07-05T08:40:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00791","created_at":"2026-07-05T08:40:14Z"},{"alias_kind":"pith_short_12","alias_value":"RU2XKVNM47AH","created_at":"2026-07-05T08:40:14Z"},{"alias_kind":"pith_short_16","alias_value":"RU2XKVNM47AHZXB3","created_at":"2026-07-05T08:40:14Z"},{"alias_kind":"pith_short_8","alias_value":"RU2XKVNM","created_at":"2026-07-05T08:40:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RU2XKVNM47AHZXB3XM4366K5WQ","target":"record","payload":{"canonical_record":{"source":{"id":"2403.00791","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T20:11:24Z","cross_cats_sorted":["cs.AI","q-bio.BM","q-bio.QM"],"title_canon_sha256":"63227982eb1ecc0be26bf4d2792164352f959a3ba5ab86e886dd8e1c51eaea41","abstract_canon_sha256":"7834d0dac9ca6645be37e3a6065d416945bccf435b74b038f6d4d2cf0bae0d9b"},"schema_version":"1.0"},"canonical_sha256":"8d357555ace7c07cdc3bbb39bf795db43cfc0238bdeb1caaaf108ee9d4efc31e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:14.314999Z","signature_b64":"PbARKSbaneIlCk77sCzxm+hBeWxxgEysuvKM/XfGwvW753duhFPp1mUF5wor9EUcqq1teUKsOCxnbnWZjtjyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d357555ace7c07cdc3bbb39bf795db43cfc0238bdeb1caaaf108ee9d4efc31e","last_reissued_at":"2026-07-05T08:40:14.314498Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:14.314498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.00791","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":"2026-07-05T08:40:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v8kLHl91l1oyXIYsoT8mCNajmjDSoQLM81UaG0TZi3OV0abhxudFZc9nlBIypTNPxlO71aR/oOGxjvoFC/mtDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:42:51.239894Z"},"content_sha256":"cdeaaf1cba7bd68788ec8cafa40917d5014844b541d5caa6cb8371e8f56cbfb8","schema_version":"1.0","event_id":"sha256:cdeaaf1cba7bd68788ec8cafa40917d5014844b541d5caa6cb8371e8f56cbfb8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RU2XKVNM47AHZXB3XM4366K5WQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"L+M-24: Building a Dataset for Language + Molecules @ ACL 2024","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-bio.BM","q-bio.QM"],"primary_cat":"cs.CL","authors_text":"Carl Edwards, Heng Ji, Lawrence Zhao, Qingyun Wang","submitted_at":"2024-02-22T20:11:24Z","abstract_excerpt":"Language-molecule models have emerged as an exciting direction for molecular discovery and understanding. However, training these models is challenging due to the scarcity of molecule-language pair datasets. At this point, datasets have been released which are 1) small and scraped from existing databases, 2) large but noisy and constructed by performing entity linking on the scientific literature, and 3) built by converting property prediction datasets to natural language using templates. In this document, we detail the $\\textit{L+M-24}$ dataset, which has been created for the Language + Molec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00791","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/2403.00791/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":"2026-07-05T08:40:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T6WO+3RgDIaV5mfD87KdNBY7fa26lR5B+XxpNY9Cf4uD+jU91xJwC3NzKCbRqiyhynhsdMgCTXpDhKaDlb+PBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:42:51.240491Z"},"content_sha256":"e00a10295c4522ff3a5b9f9fdab3ba584c7ec96375b443f29c2efe69e1948891","schema_version":"1.0","event_id":"sha256:e00a10295c4522ff3a5b9f9fdab3ba584c7ec96375b443f29c2efe69e1948891"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RU2XKVNM47AHZXB3XM4366K5WQ/bundle.json","state_url":"https://pith.science/pith/RU2XKVNM47AHZXB3XM4366K5WQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RU2XKVNM47AHZXB3XM4366K5WQ/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":"2026-08-07T22:42:51Z","links":{"resolver":"https://pith.science/pith/RU2XKVNM47AHZXB3XM4366K5WQ","bundle":"https://pith.science/pith/RU2XKVNM47AHZXB3XM4366K5WQ/bundle.json","state":"https://pith.science/pith/RU2XKVNM47AHZXB3XM4366K5WQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RU2XKVNM47AHZXB3XM4366K5WQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RU2XKVNM47AHZXB3XM4366K5WQ","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":"7834d0dac9ca6645be37e3a6065d416945bccf435b74b038f6d4d2cf0bae0d9b","cross_cats_sorted":["cs.AI","q-bio.BM","q-bio.QM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T20:11:24Z","title_canon_sha256":"63227982eb1ecc0be26bf4d2792164352f959a3ba5ab86e886dd8e1c51eaea41"},"schema_version":"1.0","source":{"id":"2403.00791","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.00791","created_at":"2026-07-05T08:40:14Z"},{"alias_kind":"arxiv_version","alias_value":"2403.00791v2","created_at":"2026-07-05T08:40:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00791","created_at":"2026-07-05T08:40:14Z"},{"alias_kind":"pith_short_12","alias_value":"RU2XKVNM47AH","created_at":"2026-07-05T08:40:14Z"},{"alias_kind":"pith_short_16","alias_value":"RU2XKVNM47AHZXB3","created_at":"2026-07-05T08:40:14Z"},{"alias_kind":"pith_short_8","alias_value":"RU2XKVNM","created_at":"2026-07-05T08:40:14Z"}],"graph_snapshots":[{"event_id":"sha256:e00a10295c4522ff3a5b9f9fdab3ba584c7ec96375b443f29c2efe69e1948891","target":"graph","created_at":"2026-07-05T08:40:14Z","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/2403.00791/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language-molecule models have emerged as an exciting direction for molecular discovery and understanding. However, training these models is challenging due to the scarcity of molecule-language pair datasets. At this point, datasets have been released which are 1) small and scraped from existing databases, 2) large but noisy and constructed by performing entity linking on the scientific literature, and 3) built by converting property prediction datasets to natural language using templates. In this document, we detail the $\\textit{L+M-24}$ dataset, which has been created for the Language + Molec","authors_text":"Carl Edwards, Heng Ji, Lawrence Zhao, Qingyun Wang","cross_cats":["cs.AI","q-bio.BM","q-bio.QM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T20:11:24Z","title":"L+M-24: Building a Dataset for Language + Molecules @ ACL 2024"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00791","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:cdeaaf1cba7bd68788ec8cafa40917d5014844b541d5caa6cb8371e8f56cbfb8","target":"record","created_at":"2026-07-05T08:40:14Z","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":"7834d0dac9ca6645be37e3a6065d416945bccf435b74b038f6d4d2cf0bae0d9b","cross_cats_sorted":["cs.AI","q-bio.BM","q-bio.QM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T20:11:24Z","title_canon_sha256":"63227982eb1ecc0be26bf4d2792164352f959a3ba5ab86e886dd8e1c51eaea41"},"schema_version":"1.0","source":{"id":"2403.00791","kind":"arxiv","version":2}},"canonical_sha256":"8d357555ace7c07cdc3bbb39bf795db43cfc0238bdeb1caaaf108ee9d4efc31e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d357555ace7c07cdc3bbb39bf795db43cfc0238bdeb1caaaf108ee9d4efc31e","first_computed_at":"2026-07-05T08:40:14.314498Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:40:14.314498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PbARKSbaneIlCk77sCzxm+hBeWxxgEysuvKM/XfGwvW753duhFPp1mUF5wor9EUcqq1teUKsOCxnbnWZjtjyBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:40:14.314999Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.00791","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cdeaaf1cba7bd68788ec8cafa40917d5014844b541d5caa6cb8371e8f56cbfb8","sha256:e00a10295c4522ff3a5b9f9fdab3ba584c7ec96375b443f29c2efe69e1948891"],"state_sha256":"c9c34bf1a27aeb93a23e5f94a5aa09c937e72075153f02c97159ee1ea955f2d7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1WlwecO7pAWR5+IN+QGb67Xps6nzgiSqGvieR7zPeal0BJvmDzUotaWAl71MPt99ftp7FmMQuIMOamOrolFRDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:42:51.244549Z","bundle_sha256":"c0c41f82239f15cfc60c90465dc5f0fe3f51c9370ec2b3a78f5198568713be83"}}