{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QYZHTCMSZTYIZHFKVE5RK7C3CD","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":"efee410f7132209f6858c3fd0af3641e000c34b6632f4649eda05fa86c07d291","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T19:27:01Z","title_canon_sha256":"e80cbc36f7c861e320df05616abae2574915a210c825a0b3e18d5ec20e6327cf"},"schema_version":"1.0","source":{"id":"2605.15354","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15354","created_at":"2026-05-20T00:00:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15354v1","created_at":"2026-05-20T00:00:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15354","created_at":"2026-05-20T00:00:54Z"},{"alias_kind":"pith_short_12","alias_value":"QYZHTCMSZTYI","created_at":"2026-05-20T00:00:54Z"},{"alias_kind":"pith_short_16","alias_value":"QYZHTCMSZTYIZHFK","created_at":"2026-05-20T00:00:54Z"},{"alias_kind":"pith_short_8","alias_value":"QYZHTCMS","created_at":"2026-05-20T00:00:54Z"}],"graph_snapshots":[{"event_id":"sha256:d445586640538f8f4a3e7ba6cb7f6722d415171ed587ef6644f841804362ef3c","target":"graph","created_at":"2026-05-20T00:00:54Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Across three heterogeneous benchmarks spanning materials and drug discovery, CoMole ranks first in controllability on all nine targets, reduces MAE by up to 48.2% relative to the strongest baselines, and maintains validity above 0.94 without rule-based correction or post-hoc filtering."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The central premise that learning a motif-aware graph space successfully transfers pretrained structural priors into controllable generation and enables RL to optimize conditional reverse policies over chemically meaningful decisions without the bottlenecks of atom-level action spaces."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CoMole uses a motif-aware graph diffusion pipeline with RL to rank first in controllability on nine targets across materials and drug benchmarks while keeping validity above 0.94 without post-processing."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Molecular generation gains reliable control by operating on motifs rather than atoms in a diffusion process."}],"snapshot_sha256":"8cb680b513078cca04fc7cab049b86e8bd2653ad3ed2c642d1fa052be965f5b1"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8c2cb68b3458c821a9eda5f5ed717b5df3443abaab3f1e42789997b89f628310"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T16:01:18.091265Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T15:41:03.329573Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.200138Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.747162Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.15354/integrity.json","findings":[],"snapshot_sha256":"92c9470d412117c32bd6744bb69f63e09c79755a2a4dc73371cedf4679d7ca9f","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the success of foundation models in language and vision, molecular graph generation still lacks a unified framework for heterogeneous design tasks with reliable controllability. While reinforcement learning (RL) offers a natural post-training mechanism for task-specific optimization, applying it to graph generative models is hindered by the vast atom-wise action spaces and chemically invalid intermediate states. We propose \\textbf{Co}ntrollable \\textbf{Mole}cular Generative Foundation Models (CoMole), built with a unified motif-aware graph diffusion pipeline. By learning a motif-aware ","authors_text":"Meng Jiang, Tengfei Luo, Weijiang Li, Yihan Zhu, Yuhan Liu","cross_cats":[],"headline":"Molecular generation gains reliable control by operating on motifs rather than atoms in a diffusion process.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T19:27:01Z","title":"Controllable Molecular Generative Foundation Models"},"references":{"count":38,"internal_anchors":1,"resolved_work":38,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"DiGress: Discrete Denoising diffusion for graph generation , author=. 2023 , eprint=","work_id":"e13fa227-cf9a-4b55-9487-57aa23b92c17","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Conditional Diffusion Based on Discrete Graph Structures for Molecular Graph Generation , author=. 2023 , eprint=","work_id":"41a68084-5d9f-404f-bad1-5ebcee6bfc27","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Graph Diffusion Transformers for Multi-Conditional Molecular Generation , author=. 2024 , eprint=","work_id":"dfaadffa-9654-4e72-989e-e40fd4416029","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Junction Tree Variational Autoencoder for Molecular Graph Generation , author=. 2019 , eprint=","work_id":"6282d275-9c4c-4993-b1a8-58280b469f40","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Advances in Neural Information Processing Systems , volume=","work_id":"133d8876-939a-45a3-b693-8d3a1d71022b","year":null}],"snapshot_sha256":"7397bf3417dcc746a983dc6c00eb56fc18b9586048fa26f9c2fa0f4036489080"},"source":{"id":"2605.15354","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T15:33:22.937303Z","id":"2d56abb1-3329-4c64-ae1a-7f676981fcea","model_set":{"reader":"grok-4.3"},"one_line_summary":"CoMole uses a motif-aware graph diffusion pipeline with RL to rank first in controllability on nine targets across materials and drug benchmarks while keeping validity above 0.94 without post-processing.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Molecular generation gains reliable control by operating on motifs rather than atoms in a diffusion process.","strongest_claim":"Across three heterogeneous benchmarks spanning materials and drug discovery, CoMole ranks first in controllability on all nine targets, reduces MAE by up to 48.2% relative to the strongest baselines, and maintains validity above 0.94 without rule-based correction or post-hoc filtering.","weakest_assumption":"The central premise that learning a motif-aware graph space successfully transfers pretrained structural priors into controllable generation and enables RL to optimize conditional reverse policies over chemically meaningful decisions without the bottlenecks of atom-level action spaces."}},"verdict_id":"2d56abb1-3329-4c64-ae1a-7f676981fcea"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0f1c431261deea0b347da74250ae44fdde5e4713941d29ea6a892360affadc5d","target":"record","created_at":"2026-05-20T00:00:54Z","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":"efee410f7132209f6858c3fd0af3641e000c34b6632f4649eda05fa86c07d291","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T19:27:01Z","title_canon_sha256":"e80cbc36f7c861e320df05616abae2574915a210c825a0b3e18d5ec20e6327cf"},"schema_version":"1.0","source":{"id":"2605.15354","kind":"arxiv","version":1}},"canonical_sha256":"8632798992ccf08c9caaa93b157c5b10f8dd6790accc1480086f4ff25c0fc3a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8632798992ccf08c9caaa93b157c5b10f8dd6790accc1480086f4ff25c0fc3a7","first_computed_at":"2026-05-20T00:00:54.077691Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:54.077691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"acSE1h2XDjKnnpPMeCEevdAwwqt2D6fIMtjARIPtuaVRm27lGx9L7aMYjHx0GbqKJozOlo0vRhO58almlZWRDg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:54.078477Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15354","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f1c431261deea0b347da74250ae44fdde5e4713941d29ea6a892360affadc5d","sha256:d445586640538f8f4a3e7ba6cb7f6722d415171ed587ef6644f841804362ef3c"],"state_sha256":"6fbba2530e8328ed6f2ebbff01eb164c69d36c1bc2429a01f86068d2b0980dd8"}