{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EBZQBDKCKLIKJUZL73PUH3MZIX","short_pith_number":"pith:EBZQBDKC","schema_version":"1.0","canonical_sha256":"2073008d4252d0a4d32bfedf43ed9945c5ad12b7ea5f3cbde118dbaac25c767e","source":{"kind":"arxiv","id":"2208.00859","version":2},"attestation_state":"computed","paper":{"title":"Learning from flowsheets: A generative transformer model for autocompletion of flowsheets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Artur M. Schweidtmann, Gabriel Vogel, Lukas Schulze Balhorn","submitted_at":"2022-08-01T13:43:58Z","abstract_excerpt":"We propose a novel method enabling autocompletion of chemical flowsheets. This idea is inspired by the autocompletion of text. We represent flowsheets as strings using the text-based SFILES 2.0 notation and learn the grammatical structure of the SFILES 2.0 language and common patterns in flowsheets using a transformer-based language model. We pre-train our model on synthetically generated flowsheet topologies to learn the flowsheet language grammar. Then, we fine-tune our model in a transfer learning step on real flowsheet topologies. Finally, we use the trained model for causal language model"},"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":"2208.00859","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-01T13:43:58Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"aec1c56bbe2f9fe9051362fb60dc9ad151de3599601500dfb620b3323a6f3571","abstract_canon_sha256":"553015f46156d68a2736cac5c8425c539b0120fdf092c0aaab7d55b212f99bde"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:24.711946Z","signature_b64":"0hCGE8yVQvPNMfDCD3+Dp3Odg181e0Me6LXCC6fH2ZdvCo7PBzHEqc72SQmWhr/67peOVIWOHFIL3Vw4FHusBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2073008d4252d0a4d32bfedf43ed9945c5ad12b7ea5f3cbde118dbaac25c767e","last_reissued_at":"2026-06-09T02:08:24.711028Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:24.711028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from flowsheets: A generative transformer model for autocompletion of flowsheets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Artur M. Schweidtmann, Gabriel Vogel, Lukas Schulze Balhorn","submitted_at":"2022-08-01T13:43:58Z","abstract_excerpt":"We propose a novel method enabling autocompletion of chemical flowsheets. This idea is inspired by the autocompletion of text. We represent flowsheets as strings using the text-based SFILES 2.0 notation and learn the grammatical structure of the SFILES 2.0 language and common patterns in flowsheets using a transformer-based language model. We pre-train our model on synthetically generated flowsheet topologies to learn the flowsheet language grammar. Then, we fine-tune our model in a transfer learning step on real flowsheet topologies. Finally, we use the trained model for causal language model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.00859","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/2208.00859/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":"2208.00859","created_at":"2026-06-09T02:08:24.711189+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.00859v2","created_at":"2026-06-09T02:08:24.711189+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.00859","created_at":"2026-06-09T02:08:24.711189+00:00"},{"alias_kind":"pith_short_12","alias_value":"EBZQBDKCKLIK","created_at":"2026-06-09T02:08:24.711189+00:00"},{"alias_kind":"pith_short_16","alias_value":"EBZQBDKCKLIKJUZL","created_at":"2026-06-09T02:08:24.711189+00:00"},{"alias_kind":"pith_short_8","alias_value":"EBZQBDKC","created_at":"2026-06-09T02:08:24.711189+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EBZQBDKCKLIKJUZL73PUH3MZIX","json":"https://pith.science/pith/EBZQBDKCKLIKJUZL73PUH3MZIX.json","graph_json":"https://pith.science/api/pith-number/EBZQBDKCKLIKJUZL73PUH3MZIX/graph.json","events_json":"https://pith.science/api/pith-number/EBZQBDKCKLIKJUZL73PUH3MZIX/events.json","paper":"https://pith.science/paper/EBZQBDKC"},"agent_actions":{"view_html":"https://pith.science/pith/EBZQBDKCKLIKJUZL73PUH3MZIX","download_json":"https://pith.science/pith/EBZQBDKCKLIKJUZL73PUH3MZIX.json","view_paper":"https://pith.science/paper/EBZQBDKC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.00859&json=true","fetch_graph":"https://pith.science/api/pith-number/EBZQBDKCKLIKJUZL73PUH3MZIX/graph.json","fetch_events":"https://pith.science/api/pith-number/EBZQBDKCKLIKJUZL73PUH3MZIX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EBZQBDKCKLIKJUZL73PUH3MZIX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EBZQBDKCKLIKJUZL73PUH3MZIX/action/storage_attestation","attest_author":"https://pith.science/pith/EBZQBDKCKLIKJUZL73PUH3MZIX/action/author_attestation","sign_citation":"https://pith.science/pith/EBZQBDKCKLIKJUZL73PUH3MZIX/action/citation_signature","submit_replication":"https://pith.science/pith/EBZQBDKCKLIKJUZL73PUH3MZIX/action/replication_record"}},"created_at":"2026-06-09T02:08:24.711189+00:00","updated_at":"2026-06-09T02:08:24.711189+00:00"}