{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LBMKFRIQ7HJRQVQXF2KFKOCEXT","short_pith_number":"pith:LBMKFRIQ","canonical_record":{"source":{"id":"2312.04881","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-08T07:40:59Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"4ac665f3f65ba057faaf65d9f7cb632778d32a50f5cbbd3ac41e5701595499b6","abstract_canon_sha256":"2e0d7cdacb84b5e1a72018ccebc72635a4508a8784b7c45354fe3e3ec1911b79"},"schema_version":"1.0"},"canonical_sha256":"5858a2c510f9d31856172e94553844bcfaca353c006c16305e49f8132d6dd45e","source":{"kind":"arxiv","id":"2312.04881","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.04881","created_at":"2026-07-05T07:21:53Z"},{"alias_kind":"arxiv_version","alias_value":"2312.04881v1","created_at":"2026-07-05T07:21:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04881","created_at":"2026-07-05T07:21:53Z"},{"alias_kind":"pith_short_12","alias_value":"LBMKFRIQ7HJR","created_at":"2026-07-05T07:21:53Z"},{"alias_kind":"pith_short_16","alias_value":"LBMKFRIQ7HJRQVQX","created_at":"2026-07-05T07:21:53Z"},{"alias_kind":"pith_short_8","alias_value":"LBMKFRIQ","created_at":"2026-07-05T07:21:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LBMKFRIQ7HJRQVQXF2KFKOCEXT","target":"record","payload":{"canonical_record":{"source":{"id":"2312.04881","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-08T07:40:59Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"4ac665f3f65ba057faaf65d9f7cb632778d32a50f5cbbd3ac41e5701595499b6","abstract_canon_sha256":"2e0d7cdacb84b5e1a72018ccebc72635a4508a8784b7c45354fe3e3ec1911b79"},"schema_version":"1.0"},"canonical_sha256":"5858a2c510f9d31856172e94553844bcfaca353c006c16305e49f8132d6dd45e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:53.746604Z","signature_b64":"Zy5Kq5DXtpGKoH+pKY6LVb3ZAFQfGsjHZqKFWndWLVY2rU/qKwavO9CairD0aG3HW7E7hgjAwKj5llPB1SrfCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5858a2c510f9d31856172e94553844bcfaca353c006c16305e49f8132d6dd45e","last_reissued_at":"2026-07-05T07:21:53.746136Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:53.746136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.04881","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:21:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vY7pSPS8OEOSriZT3jvUuBadBIYBGcrkDUFTwg105k3obcoDLTINMGgJmCLVBIdJmRQvHyEGoJXyYAcy9H79Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T18:12:41.061058Z"},"content_sha256":"f4d9ca71b3624d42afecde550915431fab5de4c7ea0d47a22163c681436225a0","schema_version":"1.0","event_id":"sha256:f4d9ca71b3624d42afecde550915431fab5de4c7ea0d47a22163c681436225a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LBMKFRIQ7HJRQVQXF2KFKOCEXT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Predictive Chemistry Augmented with Text Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Connor W. Coley, Regina Barzilay, Yujie Qian, Zhengkai Tu, Zhening Li","submitted_at":"2023-12-08T07:40:59Z","abstract_excerpt":"This paper focuses on using natural language descriptions to enhance predictive models in the chemistry field. Conventionally, chemoinformatics models are trained with extensive structured data manually extracted from the literature. In this paper, we introduce TextReact, a novel method that directly augments predictive chemistry with texts retrieved from the literature. TextReact retrieves text descriptions relevant for a given chemical reaction, and then aligns them with the molecular representation of the reaction. This alignment is enhanced via an auxiliary masked LM objective incorporated"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04881","kind":"arxiv","version":1},"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/2312.04881/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":"2026-07-05T07:21:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s5gILb9CmZj1/Rdh0/rSAcKYhADK9zZw1IGVEsWz8gXH/mzvrlX2cezh9gGu/ZAK1FYcwoCGg7QjveEPL0ExBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T18:12:41.061434Z"},"content_sha256":"3de49007eaab20ad92fadbf73c3927e9b9385ad3112a0ad85e1559902decc755","schema_version":"1.0","event_id":"sha256:3de49007eaab20ad92fadbf73c3927e9b9385ad3112a0ad85e1559902decc755"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LBMKFRIQ7HJRQVQXF2KFKOCEXT/bundle.json","state_url":"https://pith.science/pith/LBMKFRIQ7HJRQVQXF2KFKOCEXT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LBMKFRIQ7HJRQVQXF2KFKOCEXT/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":"2026-07-08T18:12:41Z","links":{"resolver":"https://pith.science/pith/LBMKFRIQ7HJRQVQXF2KFKOCEXT","bundle":"https://pith.science/pith/LBMKFRIQ7HJRQVQXF2KFKOCEXT/bundle.json","state":"https://pith.science/pith/LBMKFRIQ7HJRQVQXF2KFKOCEXT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LBMKFRIQ7HJRQVQXF2KFKOCEXT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LBMKFRIQ7HJRQVQXF2KFKOCEXT","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":"2e0d7cdacb84b5e1a72018ccebc72635a4508a8784b7c45354fe3e3ec1911b79","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-08T07:40:59Z","title_canon_sha256":"4ac665f3f65ba057faaf65d9f7cb632778d32a50f5cbbd3ac41e5701595499b6"},"schema_version":"1.0","source":{"id":"2312.04881","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.04881","created_at":"2026-07-05T07:21:53Z"},{"alias_kind":"arxiv_version","alias_value":"2312.04881v1","created_at":"2026-07-05T07:21:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04881","created_at":"2026-07-05T07:21:53Z"},{"alias_kind":"pith_short_12","alias_value":"LBMKFRIQ7HJR","created_at":"2026-07-05T07:21:53Z"},{"alias_kind":"pith_short_16","alias_value":"LBMKFRIQ7HJRQVQX","created_at":"2026-07-05T07:21:53Z"},{"alias_kind":"pith_short_8","alias_value":"LBMKFRIQ","created_at":"2026-07-05T07:21:53Z"}],"graph_snapshots":[{"event_id":"sha256:3de49007eaab20ad92fadbf73c3927e9b9385ad3112a0ad85e1559902decc755","target":"graph","created_at":"2026-07-05T07:21:53Z","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/2312.04881/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper focuses on using natural language descriptions to enhance predictive models in the chemistry field. Conventionally, chemoinformatics models are trained with extensive structured data manually extracted from the literature. In this paper, we introduce TextReact, a novel method that directly augments predictive chemistry with texts retrieved from the literature. TextReact retrieves text descriptions relevant for a given chemical reaction, and then aligns them with the molecular representation of the reaction. This alignment is enhanced via an auxiliary masked LM objective incorporated","authors_text":"Connor W. Coley, Regina Barzilay, Yujie Qian, Zhengkai Tu, Zhening Li","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-08T07:40:59Z","title":"Predictive Chemistry Augmented with Text Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04881","kind":"arxiv","version":1},"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:f4d9ca71b3624d42afecde550915431fab5de4c7ea0d47a22163c681436225a0","target":"record","created_at":"2026-07-05T07:21:53Z","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":"2e0d7cdacb84b5e1a72018ccebc72635a4508a8784b7c45354fe3e3ec1911b79","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-08T07:40:59Z","title_canon_sha256":"4ac665f3f65ba057faaf65d9f7cb632778d32a50f5cbbd3ac41e5701595499b6"},"schema_version":"1.0","source":{"id":"2312.04881","kind":"arxiv","version":1}},"canonical_sha256":"5858a2c510f9d31856172e94553844bcfaca353c006c16305e49f8132d6dd45e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5858a2c510f9d31856172e94553844bcfaca353c006c16305e49f8132d6dd45e","first_computed_at":"2026-07-05T07:21:53.746136Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:21:53.746136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zy5Kq5DXtpGKoH+pKY6LVb3ZAFQfGsjHZqKFWndWLVY2rU/qKwavO9CairD0aG3HW7E7hgjAwKj5llPB1SrfCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:21:53.746604Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.04881","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4d9ca71b3624d42afecde550915431fab5de4c7ea0d47a22163c681436225a0","sha256:3de49007eaab20ad92fadbf73c3927e9b9385ad3112a0ad85e1559902decc755"],"state_sha256":"95eada1731375c953acf658142a2b1c8989ccefe015bf0115d498b8c797db323"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QBgntlxDWfIgzzP3GY0IB41B4cWnSZdwqRWwwLc9DUH392CpxKBdMns68Yss8fCksXbZyv8C9by7eHXgTX4+DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T18:12:41.063722Z","bundle_sha256":"90fc970aaa784a3c265b3186a4a552f09dacdb886f402c4d73ffd385effa939f"}}