{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2CQ4YTAB5HXBPXSAKM6YH3G5OZ","short_pith_number":"pith:2CQ4YTAB","canonical_record":{"source":{"id":"2607.19044","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T12:34:59Z","cross_cats_sorted":[],"title_canon_sha256":"53799378e3f0d061d434756affecb4d922d4c5057a021ddcf2c054ba33e611fd","abstract_canon_sha256":"aaec13a2fd2fe07f762890a68daf6aa914bbec57bb9c74eb4b8a7b626364cf6f"},"schema_version":"1.0"},"canonical_sha256":"d0a1cc4c01e9ee17de40533d83ecdd76619c662ceac59b80284fed67508ce673","source":{"kind":"arxiv","id":"2607.19044","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.19044","created_at":"2026-07-22T01:24:05Z"},{"alias_kind":"arxiv_version","alias_value":"2607.19044v1","created_at":"2026-07-22T01:24:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19044","created_at":"2026-07-22T01:24:05Z"},{"alias_kind":"pith_short_12","alias_value":"2CQ4YTAB5HXB","created_at":"2026-07-22T01:24:05Z"},{"alias_kind":"pith_short_16","alias_value":"2CQ4YTAB5HXBPXSA","created_at":"2026-07-22T01:24:05Z"},{"alias_kind":"pith_short_8","alias_value":"2CQ4YTAB","created_at":"2026-07-22T01:24:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2CQ4YTAB5HXBPXSAKM6YH3G5OZ","target":"record","payload":{"canonical_record":{"source":{"id":"2607.19044","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T12:34:59Z","cross_cats_sorted":[],"title_canon_sha256":"53799378e3f0d061d434756affecb4d922d4c5057a021ddcf2c054ba33e611fd","abstract_canon_sha256":"aaec13a2fd2fe07f762890a68daf6aa914bbec57bb9c74eb4b8a7b626364cf6f"},"schema_version":"1.0"},"canonical_sha256":"d0a1cc4c01e9ee17de40533d83ecdd76619c662ceac59b80284fed67508ce673","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T01:24:05.681447Z","signature_b64":"lGjsrLcoXtpH6PE4g4IX9alPfjJRHiM9Yca3thowscfydkuzjCGP9UCv+j0W1uCi21WTlif7cHE1xta0W54XDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0a1cc4c01e9ee17de40533d83ecdd76619c662ceac59b80284fed67508ce673","last_reissued_at":"2026-07-22T01:24:05.680734Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T01:24:05.680734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.19044","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":"2026-07-22T01:24:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XxCfuNiquF8W/dGgwqhiZQmoG3Ul7s20g4qqEWsVZ16kxVnsSETFPD1KCq9y67KVhY7OIoluKCD+7b6bpL9JBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:20:35.946712Z"},"content_sha256":"8ede3b269a93c564a25d9664e6f7e6eed363d0722cbbf8603933121409a9cc7b","schema_version":"1.0","event_id":"sha256:8ede3b269a93c564a25d9664e6f7e6eed363d0722cbbf8603933121409a9cc7b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2CQ4YTAB5HXBPXSAKM6YH3G5OZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adopting Reinforcement Learning with Verifiable Rewards for Molecular Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hao Lan, Mingxuan Ouyang, Wanyu Lin","submitted_at":"2026-07-21T12:34:59Z","abstract_excerpt":"Leveraging large language models (LLMs) for molecular generation has shown remarkable potential in chemical and drug design. Current methods primarily rely on supervised training or fine-tuning with limited datasets, which are insufficient to capture complex molecular design objectives. While some approaches attempt to guide generation toward specific goals, they often lack direct optimization mechanisms, making it difficult to align generated molecules with desired properties. To tackle these challenges, we propose \\textbf{LLMol}, a principled reinforcement learning framework that directly in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19044","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/2607.19044/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":"2026-07-22T01:24:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wSicsO0kmQ24Q9kbfG8VtFL3q+CNkk2ueVGo6WnnbKauTj4UPxtYifSyY5SE+CjMp73FvCizU4sJzDQBCjsuBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:20:35.947100Z"},"content_sha256":"650d988cfb0c3b1f18ca38f5d040b0518111446ec3fd2a1b1b20c1671739efb9","schema_version":"1.0","event_id":"sha256:650d988cfb0c3b1f18ca38f5d040b0518111446ec3fd2a1b1b20c1671739efb9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2CQ4YTAB5HXBPXSAKM6YH3G5OZ/bundle.json","state_url":"https://pith.science/pith/2CQ4YTAB5HXBPXSAKM6YH3G5OZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2CQ4YTAB5HXBPXSAKM6YH3G5OZ/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":"2026-08-04T07:20:35Z","links":{"resolver":"https://pith.science/pith/2CQ4YTAB5HXBPXSAKM6YH3G5OZ","bundle":"https://pith.science/pith/2CQ4YTAB5HXBPXSAKM6YH3G5OZ/bundle.json","state":"https://pith.science/pith/2CQ4YTAB5HXBPXSAKM6YH3G5OZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2CQ4YTAB5HXBPXSAKM6YH3G5OZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2CQ4YTAB5HXBPXSAKM6YH3G5OZ","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":"aaec13a2fd2fe07f762890a68daf6aa914bbec57bb9c74eb4b8a7b626364cf6f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T12:34:59Z","title_canon_sha256":"53799378e3f0d061d434756affecb4d922d4c5057a021ddcf2c054ba33e611fd"},"schema_version":"1.0","source":{"id":"2607.19044","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.19044","created_at":"2026-07-22T01:24:05Z"},{"alias_kind":"arxiv_version","alias_value":"2607.19044v1","created_at":"2026-07-22T01:24:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19044","created_at":"2026-07-22T01:24:05Z"},{"alias_kind":"pith_short_12","alias_value":"2CQ4YTAB5HXB","created_at":"2026-07-22T01:24:05Z"},{"alias_kind":"pith_short_16","alias_value":"2CQ4YTAB5HXBPXSA","created_at":"2026-07-22T01:24:05Z"},{"alias_kind":"pith_short_8","alias_value":"2CQ4YTAB","created_at":"2026-07-22T01:24:05Z"}],"graph_snapshots":[{"event_id":"sha256:650d988cfb0c3b1f18ca38f5d040b0518111446ec3fd2a1b1b20c1671739efb9","target":"graph","created_at":"2026-07-22T01:24:05Z","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/2607.19044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Leveraging large language models (LLMs) for molecular generation has shown remarkable potential in chemical and drug design. Current methods primarily rely on supervised training or fine-tuning with limited datasets, which are insufficient to capture complex molecular design objectives. While some approaches attempt to guide generation toward specific goals, they often lack direct optimization mechanisms, making it difficult to align generated molecules with desired properties. To tackle these challenges, we propose \\textbf{LLMol}, a principled reinforcement learning framework that directly in","authors_text":"Hao Lan, Mingxuan Ouyang, Wanyu Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T12:34:59Z","title":"Adopting Reinforcement Learning with Verifiable Rewards for Molecular Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19044","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":"sha256:8ede3b269a93c564a25d9664e6f7e6eed363d0722cbbf8603933121409a9cc7b","target":"record","created_at":"2026-07-22T01:24:05Z","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":"aaec13a2fd2fe07f762890a68daf6aa914bbec57bb9c74eb4b8a7b626364cf6f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T12:34:59Z","title_canon_sha256":"53799378e3f0d061d434756affecb4d922d4c5057a021ddcf2c054ba33e611fd"},"schema_version":"1.0","source":{"id":"2607.19044","kind":"arxiv","version":1}},"canonical_sha256":"d0a1cc4c01e9ee17de40533d83ecdd76619c662ceac59b80284fed67508ce673","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0a1cc4c01e9ee17de40533d83ecdd76619c662ceac59b80284fed67508ce673","first_computed_at":"2026-07-22T01:24:05.680734Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T01:24:05.680734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lGjsrLcoXtpH6PE4g4IX9alPfjJRHiM9Yca3thowscfydkuzjCGP9UCv+j0W1uCi21WTlif7cHE1xta0W54XDw==","signature_status":"signed_v1","signed_at":"2026-07-22T01:24:05.681447Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.19044","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ede3b269a93c564a25d9664e6f7e6eed363d0722cbbf8603933121409a9cc7b","sha256:650d988cfb0c3b1f18ca38f5d040b0518111446ec3fd2a1b1b20c1671739efb9"],"state_sha256":"5b647b1947f81080754e44fa40a5f580357cf515fd9a35e9698b883eecc65f88"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NzMSaeVm8TOUxvKOGgqPzUdlbSv09LS9pTJx3/G9mHFQe8lWpsXwHFR4JdsFB1XpmjsJpYM61nR9BCBvbnOUBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T07:20:35.949449Z","bundle_sha256":"2e7d0f12909cc94f2d51c1a5f1cbf61b1ab9db9dee1e20a01ecd87eb2fea095f"}}