{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BQF5LUQEBWFX6EVSJK5WF532C6","short_pith_number":"pith:BQF5LUQE","schema_version":"1.0","canonical_sha256":"0c0bd5d2040d8b7f12b24abb62f77a17997879fb70226b41fea4ade535091bf1","source":{"kind":"arxiv","id":"2406.13193","version":1},"attestation_state":"computed","paper":{"title":"PRESTO: Progressive Pretraining Enhances Synthetic Chemistry Outcomes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","physics.chem-ph"],"primary_cat":"cs.LG","authors_text":"He Cao, Xiangru Tang, Yanjun Shao, Yuan Yao, Yu Li, Zhiyuan Liu, Zijing Liu","submitted_at":"2024-06-19T03:59:46Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have seen growing adoption across various scientific disciplines. These advancements encourage the investigation of molecule-text modeling within synthetic chemistry, a field dedicated to designing and conducting chemical reactions to synthesize new compounds with desired properties and applications. Current approaches, however, often neglect the critical role of multiple molecule graph interaction in understanding chemical reactions, leading to suboptimal performance in synthetic chemistry tasks. This study introduces PRESTO(Progressive Pretraining Enh"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.13193","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-19T03:59:46Z","cross_cats_sorted":["cs.AI","cs.CL","physics.chem-ph"],"title_canon_sha256":"c3cd177acc64e7645d0e14d5187c09368e08c0bd340ba502d9a6a3b8c4f8769a","abstract_canon_sha256":"166431a5a2a1a0374fed9667ec2352fa1e577e680b201332955a05df8915decc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:26.545352Z","signature_b64":"hYhQH+wD+zB2lKpZoWNFdcnjNOXAQ3Pos2DV4fA5tzP79VhNljXq06FUAm8hUz+l9JBz82IgGxZRocAbaN25Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c0bd5d2040d8b7f12b24abb62f77a17997879fb70226b41fea4ade535091bf1","last_reissued_at":"2026-07-05T08:34:26.544890Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:26.544890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PRESTO: Progressive Pretraining Enhances Synthetic Chemistry Outcomes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","physics.chem-ph"],"primary_cat":"cs.LG","authors_text":"He Cao, Xiangru Tang, Yanjun Shao, Yuan Yao, Yu Li, Zhiyuan Liu, Zijing Liu","submitted_at":"2024-06-19T03:59:46Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have seen growing adoption across various scientific disciplines. These advancements encourage the investigation of molecule-text modeling within synthetic chemistry, a field dedicated to designing and conducting chemical reactions to synthesize new compounds with desired properties and applications. Current approaches, however, often neglect the critical role of multiple molecule graph interaction in understanding chemical reactions, leading to suboptimal performance in synthetic chemistry tasks. This study introduces PRESTO(Progressive Pretraining Enh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13193","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/2406.13193/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.13193","created_at":"2026-07-05T08:34:26.544958+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13193v1","created_at":"2026-07-05T08:34:26.544958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13193","created_at":"2026-07-05T08:34:26.544958+00:00"},{"alias_kind":"pith_short_12","alias_value":"BQF5LUQEBWFX","created_at":"2026-07-05T08:34:26.544958+00:00"},{"alias_kind":"pith_short_16","alias_value":"BQF5LUQEBWFX6EVS","created_at":"2026-07-05T08:34:26.544958+00:00"},{"alias_kind":"pith_short_8","alias_value":"BQF5LUQE","created_at":"2026-07-05T08:34:26.544958+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18652","citing_title":"MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BQF5LUQEBWFX6EVSJK5WF532C6","json":"https://pith.science/pith/BQF5LUQEBWFX6EVSJK5WF532C6.json","graph_json":"https://pith.science/api/pith-number/BQF5LUQEBWFX6EVSJK5WF532C6/graph.json","events_json":"https://pith.science/api/pith-number/BQF5LUQEBWFX6EVSJK5WF532C6/events.json","paper":"https://pith.science/paper/BQF5LUQE"},"agent_actions":{"view_html":"https://pith.science/pith/BQF5LUQEBWFX6EVSJK5WF532C6","download_json":"https://pith.science/pith/BQF5LUQEBWFX6EVSJK5WF532C6.json","view_paper":"https://pith.science/paper/BQF5LUQE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13193&json=true","fetch_graph":"https://pith.science/api/pith-number/BQF5LUQEBWFX6EVSJK5WF532C6/graph.json","fetch_events":"https://pith.science/api/pith-number/BQF5LUQEBWFX6EVSJK5WF532C6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BQF5LUQEBWFX6EVSJK5WF532C6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BQF5LUQEBWFX6EVSJK5WF532C6/action/storage_attestation","attest_author":"https://pith.science/pith/BQF5LUQEBWFX6EVSJK5WF532C6/action/author_attestation","sign_citation":"https://pith.science/pith/BQF5LUQEBWFX6EVSJK5WF532C6/action/citation_signature","submit_replication":"https://pith.science/pith/BQF5LUQEBWFX6EVSJK5WF532C6/action/replication_record"}},"created_at":"2026-07-05T08:34:26.544958+00:00","updated_at":"2026-07-05T08:34:26.544958+00:00"}