{"as_of":"2026-08-10T22:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9238d30e88c86fbe3cca41ea99a47bc26a9754052e9df0235868c268c7d51dc4","coverage":[{"denominator":38,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":38,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T04:23:54.881662Z","state":"measured"},{"denominator":38,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":38,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2608.06582/citation-record","integrity":"/paper/2608.06582/integrity","json":"/paper/2608.06582/citation-record.json","paper":"/paper/2608.06582"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.511884Z","title":"Crystal structure generation with autoregressive large lan- guage modeling.Nature Communications, 15(1):10570,","venue":null,"work_id":"cc32faa6-a9bd-4d97-a6a6-3fb1f3abdb8a","year":null},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.633587Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:439141489713be25e5acb58da58e80dd1e49da54bcac449af3b4eaa279f00dc8","observation_id":"17b784ae-dc61-43f3-b349-4ddb7a407a88","resolution":{"observed_at":"2026-08-10T04:23:55.515824Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.499424Z","title":"A foundation model for atomistic materials chemistry.The Journal of chemical physics, 163(18), 2025","venue":null,"work_id":"ba05d97b-37a3-475e-a1ac-ed5b50b5bcf7","year":2025},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.639543Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:7c2199cc0268c09a1d01c29907440b4ebc35cf5fdd7820622f3a00a56041d6ed","observation_id":"d81cfd15-9157-4061-91a5-7437e03e087f","resolution":{"observed_at":"2026-08-10T04:23:55.504452Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13301","last_updated":"2024-01-04T19:11:25Z","snapshot_observed_at":"2026-08-09T16:20:23.732146Z","submitted_at":"2023-05-22T17:57:41Z","title":"Training Diffusion Models with Reinforcement Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.13301","snapshot_observed_at":"2026-08-10T04:23:54.646822Z","title":"Training diffusion models with reinforce- ment learning.arXiv preprint arXiv:2305.13301, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.646822Z"},"links":{"cited_paper":"/paper/2305.13301","citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:9866a74d11b48502b407e9aa6cc5b659f40e7e9de95f962b6d27dd0451cf1ff4","observation_id":"9bbf9776-c120-4cda-9075-6eea90afd06a","resolution":{"observed_at":"2026-08-10T04:23:54.646822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.485859Z","title":"Matinvent: Reinforcement learning for 3d crystal diffusion generation","venue":null,"work_id":"0cf4eae6-d79a-427c-b6d4-ebdc50990d9e","year":2025},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.651704Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:4ec8af0636d3a2fcb54837f9f336c36faf8c6a42aa6b148df7f9f7861c4f49eb","observation_id":"ebb4992a-6385-4aac-8bb8-fe6e97fa60ef","resolution":{"observed_at":"2026-08-10T04:23:55.492053Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.455378Z","title":"Fine-tuned language models generate stable inorganic ma- terials as text","venue":null,"work_id":"f78e35c7-ca1a-41bc-be37-0d7ea6bfa0d4","year":2024},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.664748Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:8e48fa5c9c7ff7bc3280b7b45dc6ae5ddbe6dad91b1b54a8f5d592d1dd4fbcff","observation_id":"a4e9cb6e-51db-4516-97ed-e82317016c0c","resolution":{"observed_at":"2026-08-10T04:23:55.459297Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.443409Z","title":"Open materials generation with inference-time reinforcement learning","venue":null,"work_id":"d461d791-638c-4f42-94fb-8163e8e54755","year":null},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.701937Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:88c478e5c9cc2f5854411fa92925a7485c75754da7aba2e602c138d95f027058","observation_id":"bed0d57c-6ce5-4b99-9b84-8776c601e967","resolution":{"observed_at":"2026-08-10T04:23:55.447750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.433822Z","title":"Tadmor, and Stefano Martiniani","venue":null,"work_id":"2c1a85cc-1994-4679-b21e-1e84bc99fee2","year":2025},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.706674Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:955f42b99d071c7001b08bd74564a84debbacc7f89e61fa67760d034ce6f24be","observation_id":"c47e4555-02d8-49b8-a561-1fe5614b3c60","resolution":{"observed_at":"2026-08-10T04:23:55.437379Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.422976Z","title":"Crystal structure prediction by joint equivariant diffusion","venue":null,"work_id":"a156fb0c-fac1-4333-a9ab-5d2aa65838fe","year":2023},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.713130Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:0538d2c50a213f6a59fdbc425dd9ed9d319aca5f5bacf7969be58829fe56d128","observation_id":"0b57a060-a1d2-4ff8-b8cd-ca3d54125fa7","resolution":{"observed_at":"2026-08-10T04:23:55.427267Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03992","last_updated":"2024-04-08T04:44:23Z","snapshot_observed_at":"2026-08-09T05:29:56.541225Z","submitted_at":"2024-02-06T13:45:01Z","title":"Space Group Constrained Crystal Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03992","snapshot_observed_at":"2026-08-10T04:23:54.717071Z","title":"Space group constrained crystal generation.arXiv preprint arXiv:2402.03992, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.717071Z"},"links":{"cited_paper":"/paper/2402.03992","citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:92920ab82f25d1a035b9cf6b165ebba828872d7f1cf6902435f877e534698ebb","observation_id":"11280999-1397-4eaf-8da4-56a484a2743a","resolution":{"observed_at":"2026-08-10T04:23:54.717071Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:54.720950Z","title":"Wyckoffdiff–a generative diffusion model for crystal symmetry.arXiv preprint arXiv:2502.06485, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.720950Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:e4640c2f1ed0e97625fb2519f4b3b67fb971eaadc232c56e245cd011db857e3c","observation_id":"4a0b3320-cc5d-4838-8d9b-db6cf586a6c6","resolution":{"observed_at":"2026-08-10T04:23:54.720950Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.394362Z","title":"Llm meets dif- fusion: a hybrid framework for crystal material generation","venue":null,"work_id":"a9a3e79a-125c-4005-90e7-ffce88b37ee4","year":2026},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.724383Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:3195155aa09a5eeda8eb2f921ca3a0fd7a20692f50f2a291d402076a25686a20","observation_id":"c61185e3-3802-41e8-97e2-a7c34105a85c","resolution":{"observed_at":"2026-08-10T04:23:55.399011Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.378987Z","title":"SymmCD: Symmetry- preserving crystal generation with diffusion models","venue":null,"work_id":"142f0ea2-a579-4ce9-ae22-244ae39db010","year":2025},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.736802Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:e2bcb86994ae5bef199a5147f706741d154ca1482723b8b39ef19445463d1406","observation_id":"1abca9a6-07f0-4954-b957-02dd011bc379","resolution":{"observed_at":"2026-08-10T04:23:55.382682Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.350618Z","title":"Powder diffraction crystal structure determination us- ing generative models.Nature Communications, 16(1):7428,","venue":null,"work_id":"02abf258-436c-4440-a084-f926b37cb485","year":null},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.743248Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:5b218089ebeb7c3241973b18bf9744ef33b37dee7cee008e871ecdc65d705e63","observation_id":"cb898a7e-58c0-4a9f-948b-155040794ec8","resolution":{"observed_at":"2026-08-10T04:23:55.365490Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.328398Z","title":"Flow matching for generative modeling","venue":null,"work_id":"041dcdb2-7403-4542-b1c5-3c3945274122","year":2022},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.747597Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:d8147bd0381bb836bd7742cb08e4e86f72e4dd4e95314c8a8b62755f1ce3781f","observation_id":"a2593708-18c8-4765-bfe8-9ec21b63d9d4","resolution":{"observed_at":"2026-08-10T04:23:55.332855Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.318191Z","title":"Flow-GRPO: Training flow matching models via online RL","venue":null,"work_id":"c84dcb2c-8fc7-4cc7-aa4f-0b9be0544ea0","year":2025},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.755818Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:0f0718698d122241182f359d6b17d9e7dc4d1263897c55d66f88f3770f6d07e8","observation_id":"04ff9146-7a43-4041-8974-a55288505888","resolution":{"observed_at":"2026-08-10T04:23:55.321630Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.306187Z","title":"Crystalflow: a flow-based generative model for crystalline materials.Nature Communications, 16(1):9267, 2025","venue":null,"work_id":"5dd4e0b0-53c5-4c7b-9c37-10b29d644f2d","year":2025},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.769866Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:05c8a04e56e54e237e38fb3185307f05eaab0e20bd8137d8afc4e77dd3600d61","observation_id":"ef4532db-2896-42e5-89a1-13348acb2ea2","resolution":{"observed_at":"2026-08-10T04:23:55.311393Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.296696Z","title":"All that structure matches does not glitter.Advances in Neural Information Processing Systems, 38, 2026","venue":null,"work_id":"7fda16a8-ea9c-4433-9177-8031bc369d85","year":2026},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.773605Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:3d478bcded69f1b334bf1c1b11a2b0ca2797cd3e33036907244692f9c468721a","observation_id":"139722fa-609e-4b3c-b5c2-7f54fc2028bc","resolution":{"observed_at":"2026-08-10T04:23:55.299988Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.285799Z","title":"Genera- tive models for crystalline materials.Advanced Materials, 38(18):e23620, 2026","venue":null,"work_id":"6dd44469-43f1-4611-b126-055c29cb9de4","year":2026},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.786682Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:c78f686ba2f4072cd15e8ac26e7a7de8ad3d5cb663ffc9f6a48b22959422e7d3","observation_id":"854ff117-f71b-456e-826f-9b0b4c6975ee","resolution":{"observed_at":"2026-08-10T04:23:55.289550Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.276452Z","title":null,"venue":null,"work_id":"82b89fc5-4c4f-4283-902a-d7e4e4ffd16b","year":2024},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.790473Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:9f3d7df02302477555acb42a7d71797826eecb885ca57db805790792c8b9752e","observation_id":"bb60e780-07da-4435-a81f-a3c55f162463","resolution":{"observed_at":"2026-08-10T04:23:55.279640Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.264393Z","title":"Reliable crystal structure predictions from first principles.Nature Commu- nications, 13(1):3095, 2022","venue":null,"work_id":"7fafa69c-f9e4-4110-a576-28d63c0a2a6b","year":2022},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.796337Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:260254bda78840deff162def827b543af0b69f8f884aee952117885a3afac78f","observation_id":"5a1fa568-f54e-4616-b3a3-72a20b6c9a40","resolution":{"observed_at":"2026-08-10T04:23:55.269070Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.245635Z","title":"Python materials genomics (pymatgen): A robust, open-source python library for materials analysis.Computa- tional Materials Science, 68:314–319, 2013","venue":null,"work_id":"7022068a-6254-4f04-8775-86c1b8acc551","year":2013},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.799961Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:e72754a263ed259a72edc62137e5604e95aa96b35d15154d532db937b353b602","observation_id":"7054eed9-58cd-47a6-8291-86455421d8e7","resolution":{"observed_at":"2026-08-10T04:23:55.255391Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.234456Z","title":"Guiding generative mod- els to uncover diverse and novel crystals via reinforcement learning.Nature Machine Intelligence, pages 1–13, 2026","venue":null,"work_id":"ff51f50d-7428-4d4e-9962-b4802e8eb43d","year":2026},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.815688Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:32942301107fea744e3e4e846c95417b695c7f1f102624586f8bc5c97e66feea","observation_id":"e48ee655-b63e-4c27-925e-8931533132e2","resolution":{"observed_at":"2026-08-10T04:23:55.238629Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.221515Z","title":"Ai- assisted rapid crystal structure generation towards a target local environment.npj Computational Materials, 2026","venue":null,"work_id":"19426b44-1834-4f00-b972-477b986f3512","year":2026},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.819822Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:e38d76346dcf2058c6627c392e4f5cc97fbe645957fea74b251d3d02795dacd7","observation_id":"0d637131-48c8-412d-b24f-53edf4837533","resolution":{"observed_at":"2026-08-10T04:23:55.225927Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1707.06347","last_updated":"2017-08-28T09:20:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-07-20T02:32:33Z","title":"Proximal Policy Optimization Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.06347","snapshot_observed_at":"2026-08-10T04:23:54.823746Z","title":"Proximal policy optimization algo- rithms.arXiv preprint arXiv:1707.06347, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.823746Z"},"links":{"cited_paper":"/paper/1707.06347","citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:f77511498dbe11676980946844a736deedadbce9f17b89f9f458de625b99f5d5","observation_id":"e7bef633-bcb9-448d-8595-8b4e310dea1b","resolution":{"observed_at":"2026-08-10T04:23:54.823746Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03300","last_updated":"2024-04-27T15:25:53Z","snapshot_observed_at":"2026-08-06T14:58:42.911363Z","submitted_at":"2024-02-05T18:55:32Z","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03300","snapshot_observed_at":"2026-08-10T04:23:54.828112Z","title":"Deepseekmath: Pushing the limits of math- ematical reasoning in open language models.arXiv preprint arXiv:2402.03300, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.828112Z"},"links":{"cited_paper":"/paper/2402.03300","citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:3a3348c8b72ce273b8120342c83dde3d44946d7c849bac54d20f7dc09615db6a","observation_id":"a11357a2-ffc6-47f5-8b2d-cb3376fcfefa","resolution":{"observed_at":"2026-08-10T04:23:54.828112Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.209088Z","title":"Jaakkola, Elsa Olivetti, and Rafael G ´omez-Bombarelli","venue":null,"work_id":"39ab4e2e-8189-4237-93dd-e777504d8cad","year":2026},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.832194Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:74737fd69ec7ac5afe46353522bc7f4d7e92ab77e963ea1d4228671f819213eb","observation_id":"3403ee94-1699-40c6-8edf-bd109577ca05","resolution":{"observed_at":"2026-08-10T04:23:55.213781Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.191067Z","title":"The thermo- dynamic scale of inorganic crystalline metastability.Science advances, 2(11):e1600225, 2016","venue":null,"work_id":"d10ac389-bd32-410b-99b2-8eb99355775a","year":2016},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.837209Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:7f6d7cc26b9e97a396cd4de306e3eaa1768222b3cac45687eeb547a24cb11dbb","observation_id":"90917ed7-dc12-44f8-bc39-6fdfa89abb1b","resolution":{"observed_at":"2026-08-10T04:23:55.200470Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.15194","last_updated":"2024-02-28T09:21:46Z","snapshot_observed_at":"2026-07-06T17:34:28.430476Z","submitted_at":"2024-02-23T08:54:42Z","title":"Fine-Tuning of Continuous-Time Diffusion Models as Entropy-Regularized Control","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.15194","snapshot_observed_at":"2026-08-10T04:23:54.840347Z","title":"Fine- tuning of continuous-time diffusion models as entropy- regularized control.arXiv preprint arXiv:2402.15194, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.840347Z"},"links":{"cited_paper":"/paper/2402.15194","citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:2c80c676a7978663efd13a7a49fe7a2f129791df0f03437b5c699735b80d9558","observation_id":"16c6db0d-ca04-4022-96b2-351604c17d3c","resolution":{"observed_at":"2026-08-10T04:23:54.840347Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.179277Z","title":"Pass@k policy optimization: Solving harder reinforcement learning prob- lems","venue":null,"work_id":"db6d44ac-834e-44dd-8e3b-049561373da7","year":2025},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.845524Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:46fbcf390446229e40a1d8b2d99772f3b37cd436537df1674f61b0f11eb209a6","observation_id":"5b339336-e94f-4a90-9587-d281755b003e","resolution":{"observed_at":"2026-08-10T04:23:55.182967Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.02016","last_updated":"2025-02-04T05:07:13Z","snapshot_observed_at":"2026-08-09T14:33:59.814755Z","submitted_at":"2025-02-04T05:07:13Z","title":"A Periodic Bayesian Flow for Material Generation","version":1},"cited_work":{"arxiv_id":"2502.02016","doi":null,"metadata_source":"pith","pith_arxiv_id":"2502.02016","snapshot_observed_at":"2026-08-10T04:23:54.912024Z","title":"A Periodic Bayesian Flow for Material Generation","venue":"cs.LG","work_id":"a79f6322-9181-45d5-8146-2b3afd49a4c2","year":2025},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.851075Z"},"links":{"cited_paper":"/paper/2502.02016","citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:bd606801c4f2a23d59adbe34e90c821788dab72e65dd2114c20747c811c5ce39","observation_id":"eaeda7ed-e156-44ff-8767-f3f2c30560be","resolution":{"observed_at":"2026-08-10T04:23:54.918452Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.166688Z","title":"Jaakkola","venue":null,"work_id":"b0ba5f72-da75-4386-995d-99fbbd0a2606","year":2022},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.855060Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:de26c37c75403443cc6d9ecb0d895ed44c3dccc385895175eaee74afffc88413","observation_id":"df90b34c-ac09-459c-b3d0-d3fa5450a8b7","resolution":{"observed_at":"2026-08-10T04:23:55.170733Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.155124Z","title":"Does rein- forcement learning really incentivize reasoning capacity in LLMs beyond the base model? InThe Thirty-ninth An- nual Conference on Neural Information Processing Systems,","venue":null,"work_id":"de07fd6a-1431-4263-97f0-cecb67595380","year":null},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.858394Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:9d300c64ef4107933256cc287715d56b772fc1d4db6af66e894b3af42378d872","observation_id":"dc9b1723-a21b-45ab-be15-05405bfb26d6","resolution":{"observed_at":"2026-08-10T04:23:55.159204Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.144388Z","title":"A generative model for inorganic materials design.Nature, 2025","venue":null,"work_id":"bf4d63b1-fc0b-422a-b4c5-1761901e210b","year":2025},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.862035Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:9635b7c892f67c7b11584a389968737f03caf8c6b2732abf61de039108988a0e","observation_id":"b3ffbc10-5c18-4a1d-94da-4017cbe0f1ad","resolution":{"observed_at":"2026-08-10T04:23:55.148152Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.132653Z","title":null,"venue":null,"work_id":"4d8341c9-e34e-48d9-926f-962df37a7f41","year":null},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.865613Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:1b06648ba0745a5253daa05245842d895793ce2e9bb45d7b302945d3f1e540aa","observation_id":"2d42b46e-afd8-4477-b448-1c63275c1833","resolution":{"observed_at":"2026-08-10T04:23:55.136221Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.121739Z","title":null,"venue":null,"work_id":"f7e649bc-0b7f-4dd3-bf0b-fc6229b872e6","year":null},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.870786Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:ca8793a71b989c2d6cff1734b512fc3c1f2ee56c8a58a7b8ff1b04de4c873349","observation_id":"03c017e6-55a7-464f-b928-411c68013926","resolution":{"observed_at":"2026-08-10T04:23:55.125155Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.107898Z","title":"Both variants follow the same on-policy GRPO pipeline, alternating between stochastic rollout collection and policy optimization","venue":null,"work_id":"1934a427-f43c-4a40-9a09-2a454860f292","year":null},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.874970Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:c08021aec857227c4427ec71097192e72941d222d695ee3cf173731efe0f396f","observation_id":"ffcd3e68-46a5-4a4b-b204-466be0991306","resolution":{"observed_at":"2026-08-10T04:23:55.112120Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.095749Z","title":"CSP-aligned Hybrid Reward 3","venue":null,"work_id":"c5296f83-8650-43e3-956d-16ea75928b4e","year":null},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.878428Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:3b100d8d4ac4e688670d8dec29aea5c92bbecb40f0d0db44247fd1b93c10b7fe","observation_id":"0e9e5549-2b69-4978-b0cc-9949812842a4","resolution":{"observed_at":"2026-08-10T04:23:55.099476Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T04:23:55.078562Z","title":"CSP-aligned Hybrid Reward For completeness and reproducibility, we provide the ex- act reward implementation used to obtain the reported re- sults","venue":null,"work_id":"16cf9818-2c78-4b0b-8eaf-0c0192385bdc","year":null},"citing_paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T04:23:54.881662Z"},"links":{"citing_paper":"/paper/2608.06582"},"observation_digest":"sha256:c48bab5ec29e1df6f7bd83af96921166387787dc5103dc01c4af0d11ac47ca99","observation_id":"6a6c5ff2-43c8-4c76-be62-05549f0bc0cb","resolution":{"observed_at":"2026-08-10T04:23:55.085852Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2608.06582","last_updated":"2026-08-06T20:53:00Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T22:10:15.432458Z","submitted_at":"2026-08-06T20:53:00Z","title":"CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction"},"reference_resolution":{"displayed":38,"state_counts":{"malformed_identifier":2,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":1,"verified_fuzzy":27},"total_outbound_references":38},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2608.06582."}