{"as_of":"2026-08-16T12:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:acc25fe01baa222efd3549a5c0bdb08f168c26d4c6a0f5bcc9045e6f64af891f","coverage":[{"denominator":62,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":62,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T16:43:24.893260Z","state":"measured"},{"denominator":62,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":62,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+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/2509.03547/citation-record","integrity":"/paper/2509.03547/integrity","json":"/paper/2509.03547/citation-record.json","paper":"/paper/2509.03547"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:43:27.318453Z","title":"F., Florea, L., De Oliveira, M","venue":null,"work_id":"efda4476-3abd-4b51-a08c-4871e7fb41b0","year":2021},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:23.474722Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:12a95a6ccece6601ac277de2a2f5490089bad131cc82df64214490299f4c93ac","observation_id":"9d039744-1b93-4c4e-ab48-36a7cbf7b9d0","resolution":{"observed_at":"2026-08-15T16:43:27.323542Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:43:23.481597Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:23.481597Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:f98d9262f7ccce43942f9857946176f9800d598c53994e0470614b5e4c86474b","observation_id":"ebaa1990-a538-40b8-bd62-0475eb2538dd","resolution":{"observed_at":"2026-08-15T16:43:23.481597Z","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":"2026-08-15T16:43:27.292351Z","title":"& Buehler, M","venue":null,"work_id":"84e3cde4-5ca5-49c9-b061-7ab093ed1e8d","year":2021},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:23.486637Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:2e200c04f091f9a79d543a0470dfb179225ade9c9a91f082fa4d56ee9e744c68","observation_id":"1e1a46b3-55d3-4bbf-9d50-9650d2365447","resolution":{"observed_at":"2026-08-15T16:43:27.296980Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:27.275725Z","title":"& Rignanese, G","venue":null,"work_id":"3f25df3e-0124-481b-88bd-7afb1a43ffb8","year":2021},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:23.493955Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:2e6513360cc7f6f19b00c7ae206ecb22533cc859e89aaf2c00acceb4ce59fde8","observation_id":"b8c81837-9864-4a4e-b2df-48e758b23659","resolution":{"observed_at":"2026-08-15T16:43:27.281386Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:27.259854Z","title":"& Gao, F","venue":null,"work_id":"337831e6-c200-4c15-85e2-b965f8f8ad87","year":2022},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:23.499789Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:bcfb3e2855abf4d62672fd9c9bae6d4ffbfe701150fcdc1c4f62a30e64149688","observation_id":"cdf4b285-fb9a-405f-8e63-cbd4e70ebc43","resolution":{"observed_at":"2026-08-15T16:43:27.265027Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:27.242318Z","title":null,"venue":null,"work_id":"1cf50ed4-9263-4b7c-b120-2edff436846e","year":2022},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:23.504757Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:6e85c81e6974b21742a9c3b5f1362c33dbd0c4ce1c9a95c3457a4474592473ff","observation_id":"0805c150-e141-4b3a-818e-05a319ede701","resolution":{"observed_at":"2026-08-15T16:43:27.247219Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:27.226653Z","title":null,"venue":null,"work_id":"1bf7de17-06b5-43e3-a586-4d9fe47da44c","year":2018},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:23.510645Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:a0ff6d870e1c027bcb6f0e13a0ff514fe16c1d3d9c9fadc5569b8401fba1c68f","observation_id":"4a1ed434-422c-44bf-8f09-43a8f28c2c04","resolution":{"observed_at":"2026-08-15T16:43:27.231431Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:27.210959Z","title":"A., Brolo, A","venue":null,"work_id":"adc215b9-87f7-4481-bf72-cf46d0ed85b9","year":2024},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:23.523376Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:c4b704ba993cfb455a502198ad97d1234d2c9397d00adb71fbebb5b4c8f92b4a","observation_id":"598e8b9d-e8a8-496d-9b47-a0894dbeec49","resolution":{"observed_at":"2026-08-15T16:43:27.215356Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:27.193953Z","title":null,"venue":null,"work_id":"d32491ea-eb10-413f-bae5-0a7b36ef91f0","year":2022},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:23.558539Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:9f15559a1aa5cc4bc3982aef9952f6a83b1f0a35a15c89843b17ce11a6b86aa1","observation_id":"ee6a5860-122d-4a5f-bdc1-9d5efd40c465","resolution":{"observed_at":"2026-08-15T16:43:27.199406Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:27.123104Z","title":"& Ko, D.-H","venue":null,"work_id":"0ad7ba72-e85f-4eea-9996-8983caf5863d","year":2023},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:23.590175Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:c4e45a066c4a254a06d097ee20bc6aaf5763f124d542a4716652530dfac27d16","observation_id":"13be1d1f-19ae-463f-a853-55fb5fa221d3","resolution":{"observed_at":"2026-08-15T16:43:27.151715Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:27.052521Z","title":null,"venue":null,"work_id":"26d867ad-a3ec-48a6-8e18-5230e48bf23d","year":2022},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:23.648536Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:75cc98b1c718448d85a3931f9f3c8775abf3531bcc65675c7fc92d4972e19e7a","observation_id":"2fe57e69-0e94-4ad9-9b26-6321167ffdb4","resolution":{"observed_at":"2026-08-15T16:43:27.089344Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:26.968211Z","title":"MatBench Leaderboard","venue":null,"work_id":"f90d677e-f359-4d77-970c-e7de11666182","year":2024},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:23.704790Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:e065b878f0ba1d7756d7dec19cfbe18a3727ee7b42d09f2770bed5acfaaa6e4f","observation_id":"ae616755-4255-4c08-988f-9027fefffccd","resolution":{"observed_at":"2026-08-15T16:43:27.012644Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:26.925506Z","title":null,"venue":null,"work_id":"d309cb00-5f23-4264-8b7b-2b28b97333f9","year":2025},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:23.758449Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:7076bc9239b220fedb6cb8843b8b250fd0d2d9ea185de418753471e80a5d92dc","observation_id":"f64e4697-f650-4ab6-b9e6-4791a18bb2a8","resolution":{"observed_at":"2026-08-15T16:43:26.930561Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:43:23.823171Z","title":"P., Kondor, R","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:23.823171Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:932683ca9f4a31a75af838cbae0a1b2095eaa3b876e3b1583e12c15105cdc382","observation_id":"6e3b49f8-96f4-4688-bd5c-0567736fc1ab","resolution":{"observed_at":"2026-08-15T16:43:23.823171Z","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":"2026-08-15T16:43:23.837714Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:23.837714Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:86c71d7c6998c8084ad41e66e560811fc8908929cc8e6a64a36a8f084536d833","observation_id":"987e9050-1b65-477f-a5ac-9bf637c09c25","resolution":{"observed_at":"2026-08-15T16:43:23.837714Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07442","last_updated":"2020-12-09T05:00:33Z","snapshot_observed_at":"2026-08-14T12:13:16.010101Z","submitted_at":"2019-08-20T15:46:53Z","title":"TabNet: Attentive Interpretable Tabular Learning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.07442","snapshot_observed_at":"2026-08-15T16:43:23.846799Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:23.846799Z"},"links":{"cited_paper":"/paper/1908.07442","citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:c900d0b35cd2bf76431c711c36f0c7038b0a429e3a7043054c845eb87d6d7998","observation_id":"5b5a540d-e9c7-4c2a-9955-bee94c0fdbd6","resolution":{"observed_at":"2026-08-15T16:43:23.846799Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.14102","last_updated":"2023-08-09T15:05:42Z","snapshot_observed_at":"2026-08-13T12:35:52.666122Z","submitted_at":"2023-02-27T19:26:48Z","title":"Connectivity Optimized Nested Graph Networks for Crystal Structures","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.14102","snapshot_observed_at":"2026-08-15T16:43:23.937473Z","title":"& Friederich, P","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:23.937473Z"},"links":{"cited_paper":"/paper/2302.14102","citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:c989dea597117b0228436dbc6ca4548b40bd1408914104ae0344030b1a133806","observation_id":"8a3985d7-9cd1-46f3-88a8-457785abb883","resolution":{"observed_at":"2026-08-15T16:43:23.937473Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.03837","last_updated":"2025-03-05T19:03:21Z","snapshot_observed_at":"2026-08-07T17:26:41.806123Z","submitted_at":"2025-03-05T19:03:21Z","title":"Materials Graph Library (MatGL), an open-source graph deep learning library for materials science and chemistry","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.03837","snapshot_observed_at":"2026-08-15T16:43:23.994793Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:23.994793Z"},"links":{"cited_paper":"/paper/2503.03837","citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:89566075607ed3099fef9fce8ef14e2d68468377b49a4fa73622c982431a8e63","observation_id":"f92b4ab6-e342-4e76-a839-4133b01dcbc0","resolution":{"observed_at":"2026-08-15T16:43:23.994793Z","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":"2026-08-15T16:43:26.881035Z","title":null,"venue":null,"work_id":"ae24c710-c681-4d80-b263-144827e7cc34","year":2020},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.001563Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:0b38aa4e15f9d22ce2f817caf66fb7d9072f2aec494f194154621c0e52a1c417","observation_id":"b8432578-550b-46fc-a368-3dcd95864d77","resolution":{"observed_at":"2026-08-15T16:43:26.886119Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.06231","last_updated":"2025-04-10T18:13:52Z","snapshot_observed_at":"2026-08-13T07:54:41.534681Z","submitted_at":"2025-04-08T17:27:34Z","title":"Orb-v3: atomistic simulation at scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.06231","snapshot_observed_at":"2026-08-15T16:43:24.007807Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.007807Z"},"links":{"cited_paper":"/paper/2504.06231","citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:b7e7a3acabe23b38e1c0e5951bf96e108584b30930058aa4a3f8ec7542688a11","observation_id":"5b1b1c23-8ec8-46c0-9c9a-253ca9db8ca6","resolution":{"observed_at":"2026-08-15T16:43:24.007807Z","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":"2026-08-15T16:43:26.864850Z","title":"& Mizukami, W","venue":null,"work_id":"abb58f45-623d-4cd9-adea-b463b37d741b","year":2024},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.013959Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:d5ae9b19e900b82247423e3064f233002a6e97febd0b5faf307d7b874719feb8","observation_id":"16d67668-32f8-47b7-ade5-e925f01404e1","resolution":{"observed_at":"2026-08-15T16:43:26.869617Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:26.847455Z","title":null,"venue":null,"work_id":"aec8a40f-afd8-4438-be41-727015e0eec4","year":2024},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.019424Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:2ed4491e383ce85fd3e7ca8644ea4cf163fff1a718c3e772499474f42de6d31b","observation_id":"b4f37826-0cf9-4b50-9e15-fd458c39b062","resolution":{"observed_at":"2026-08-15T16:43:26.853124Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:26.830083Z","title":"M., De Castro, S., Morton, B","venue":null,"work_id":"a3e993be-e508-4136-9447-a34157b203ce","year":2024},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.025655Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:0e75dc902c907ddd5c5d02c6d0456d39e054877b6c1c249c5a926081c02542e9","observation_id":"1c084e62-8b24-44fb-a51d-0c7b110c84a2","resolution":{"observed_at":"2026-08-15T16:43:26.835371Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:26.766212Z","title":null,"venue":null,"work_id":"f4edc80e-9e73-44b1-b2be-4ad7de0b299e","year":2025},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.031497Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:3debdffcd8d1e1ca466dc5fe66aec2179cf8d4c36451a9a6bb71ad3c8d8fe3e7","observation_id":"add74e53-4b32-46f8-b13f-f211fc5dcaed","resolution":{"observed_at":"2026-08-15T16:43:26.814792Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.18497","last_updated":"2025-06-23T10:49:19Z","snapshot_observed_at":"2026-08-15T03:01:55.776513Z","submitted_at":"2025-06-23T10:49:19Z","title":"Leveraging neural network interatomic potentials for a foundation model of chemistry","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.18497","snapshot_observed_at":"2026-08-15T16:43:24.036840Z","title":"Y., Park, Y","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.036840Z"},"links":{"cited_paper":"/paper/2506.18497","citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:7e4e2d51e2ac7afd8aa727a21ad835f192d2cdea75a356927d41470d25b2683c","observation_id":"e98500b3-44d7-4e67-8469-c0fc4240845a","resolution":{"observed_at":"2026-08-15T16:43:24.036840Z","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":"2026-08-15T16:43:26.637647Z","title":"L., Buonassisi, T","venue":null,"work_id":"65e17218-5a0e-40a1-ad83-bb3ce6e3a133","year":2022},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.048554Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:19064b160d5e8b598334cc4ecee58c97b2c1677606775ca71e4a4ed1073782e6","observation_id":"e3e2d4ef-cac1-400c-90b9-6bf0b5295153","resolution":{"observed_at":"2026-08-15T16:43:26.707892Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:26.501415Z","title":"Machine learning in materials science: From explai nable predictions to autonomous design","venue":null,"work_id":"47d60560-f899-48f7-8ead-a9497d65b8d6","year":2021},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.054220Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:c04d3bf2fc2b21c64746411555bebe38dc3c66f5b0d9eaf1ab4f081a05ce0439","observation_id":"dfa530f9-11d9-4b13-94a7-bb6f179379fd","resolution":{"observed_at":"2026-08-15T16:43:26.552484Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:26.444864Z","title":"& Kumacheva, E","venue":null,"work_id":"0e9e2c3d-b58d-466a-b8f5-9ca31fd47b8e","year":2023},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.061273Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:11068423aca8a63bf19b039add23311a81b79c87e031529b5dbb5a1ef7ff7252","observation_id":"285cdd7f-1600-4334-8e3a-61fc0fcb0a64","resolution":{"observed_at":"2026-08-15T16:43:26.449804Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:26.414282Z","title":null,"venue":null,"work_id":"020ad138-db54-432a-b735-819744c58b55","year":2021},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.072516Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:1bf551d75792687fecd2445369f441a059e0c5a52dc67194db23bd4f9c2dcfa6","observation_id":"adc72cb3-3d2b-4bd2-a21c-eedefbfef1d8","resolution":{"observed_at":"2026-08-15T16:43:26.418924Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:26.385442Z","title":"& Tavazza, F","venue":null,"work_id":"ae0061c2-839a-4586-8087-948858875c81","year":2017},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.082722Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:120d641a093a6341d9a941d20b9715828a195e4d9ae2cee4e6fd88f8d4f67e7e","observation_id":"097e7157-f41c-464a-ad67-2325cf4d4d66","resolution":{"observed_at":"2026-08-15T16:43:26.389924Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:26.286895Z","title":null,"venue":null,"work_id":"1a01d6e4-fba7-4c12-9a0c-70dc9ee55ac2","year":2013},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.181970Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:5f590508164f60af3ed3118abd554a1c4403842c0cfa27f9110436aac72572f1","observation_id":"8f59928a-083f-4809-a521-bdab50111784","resolution":{"observed_at":"2026-08-15T16:43:26.325102Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:26.168020Z","title":"& Aihara Jr., T","venue":null,"work_id":"74405487-2e73-446f-b4ec-69ef9d9307d9","year":1997},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.215727Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:624337ca84e956be82cc12f42c66236cc0bc13f54b8cd7d9a52ace73fb2bd7f1","observation_id":"cc52fe4c-5415-40eb-ba90-a79140fde639","resolution":{"observed_at":"2026-08-15T16:43:26.232265Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:26.046584Z","title":"& Wolverton, C","venue":null,"work_id":"65b944c6-7228-465a-a3b1-d4e92c2f5ecd","year":2016},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.324218Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:9c0555ba0ad2d02c8c51b22e8c78ad117a166b20d2a001a40c467ff29d089314","observation_id":"1d68952b-17b5-4295-9fe2-c402b419145e","resolution":{"observed_at":"2026-08-15T16:43:26.113356Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:25.979155Z","title":null,"venue":null,"work_id":"21732a43-b08a-4225-8799-4679c7cd8ceb","year":2015},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.363990Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:72a4f020ec35b82db686eea9f32a979516bc65a31a7d74311591467f1fbb73c9","observation_id":"12e5f69c-4cba-4468-be53-1a9418ff60c4","resolution":{"observed_at":"2026-08-15T16:43:26.007665Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:43:24.412163Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.412163Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:574502c487f67d3ae198658d30cb94181d30562ca762940f7fe9040ed80bb98a","observation_id":"7c3ee00c-9838-4f50-bda4-7b6be7e45674","resolution":{"observed_at":"2026-08-15T16:43:24.412163Z","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":"2026-08-15T16:43:25.932159Z","title":null,"venue":null,"work_id":"8ad5f2ef-0367-4bf9-a3bb-e1e9449dbe95","year":2023},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.417454Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:bdab1c7a181db842f1608dc1e553c92e1b8f7b1a51887c46d63395ca47ca664e","observation_id":"060a0735-c167-496c-8aae-67513f00a3a0","resolution":{"observed_at":"2026-08-15T16:43:25.936874Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.12771","last_updated":"2026-05-20T00:46:02Z","snapshot_observed_at":"2026-08-15T03:47:51.196617Z","submitted_at":"2024-10-16T17:48:34Z","title":"Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.12771","snapshot_observed_at":"2026-08-15T16:43:24.423465Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.423465Z"},"links":{"cited_paper":"/paper/2410.12771","citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:14e4896f9a53e923ca7a1f6fc2e52de1df1369f1a1e0f7da318ebe1a4a4e7cb4","observation_id":"8cc5dcf0-e2e4-4582-9e31-e3bea6a3422d","resolution":{"observed_at":"2026-08-15T16:43:24.423465Z","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":"2026-08-15T16:43:25.916728Z","title":"Materialsproject.org https://matbench.materialsproject.org/Full%20Benchmark%20Data/matbench_v0.1_Meg Net_kgcnn_v2.1.0/ (2020)","venue":null,"work_id":"788e8bc8-a326-4721-b981-238e5e779736","year":2020},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.429590Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:fb066835978f4f78b56b54478da93ce98d5d47ed20c65513416324aed32f4c9c","observation_id":"f47d8fbb-7ff2-46be-8e7b-edca5c3d5dc9","resolution":{"observed_at":"2026-08-15T16:43:25.921579Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:25.801881Z","title":"& Qian, Q","venue":null,"work_id":"7bf58cf7-0b03-4c06-94df-32632fdcdfc8","year":2022},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.433968Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:4788bb3d5ae876fe58d49300e2f9ca5952d16f33f944fc475e5cf776108662af","observation_id":"99a6390a-3143-482a-958c-d90ac6eb9ee0","resolution":{"observed_at":"2026-08-15T16:43:25.906012Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.19209","last_updated":"2024-09-28T02:15:39Z","snapshot_observed_at":"2026-08-12T22:35:39.559478Z","submitted_at":"2024-09-28T02:15:39Z","title":"Boosting SISSO Performance on Small Sample Datasets by Using Random Forests Prescreening for Complex Feature Selection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.19209","snapshot_observed_at":"2026-08-15T16:43:24.438952Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.438952Z"},"links":{"cited_paper":"/paper/2409.19209","citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:f20528151e5f24940e8d6ae56083c39ca3e2bf6bc29cdb391953490a7d2eda10","observation_id":"4ac1a902-56b3-42c9-aa2f-6cbd88799e39","resolution":{"observed_at":"2026-08-15T16:43:24.438952Z","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":"2026-08-15T16:43:25.706892Z","title":null,"venue":null,"work_id":"8847c19c-c1e0-4607-a287-241088bd58cc","year":2022},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.444327Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:7e84bb7d487debd7980c54a265eb17f61eeb36dd63566c0684980da474219765","observation_id":"6ffb7d22-c32d-4307-8692-3ff8fae3bc6a","resolution":{"observed_at":"2026-08-15T16:43:25.711330Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:43:24.449487Z","title":"& Guestrin, C","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.449487Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:c1e44f73f37a592b28f74c9d5cc29b6a88760641721e63c275c1934bba509dec","observation_id":"beabe258-11ad-4bfd-bfc7-b837c4601347","resolution":{"observed_at":"2026-08-15T16:43:24.449487Z","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":"2026-08-15T16:43:25.690650Z","title":"& Ong, S","venue":null,"work_id":"4e9fc480-8bbd-4929-871d-3038eae530bc","year":2019},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.454374Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:7f1e4ac9f84c01ad48064605ff3bcdfec801fafa66ed965d6d6045a086d5790b","observation_id":"6747bf4b-6fbf-45bf-bd48-b083ae569d93","resolution":{"observed_at":"2026-08-15T16:43:25.696905Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:25.672977Z","title":null,"venue":null,"work_id":"33a82a05-5cb9-40aa-a226-88e942ba8bce","year":2023},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.459821Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:a8c17fafcfda102b05aa2660875cb80bd231a65f73dfc2974fc369db9849f8e6","observation_id":"257a9420-9581-4882-bb6e-90e0e7710ca5","resolution":{"observed_at":"2026-08-15T16:43:25.679232Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:25.655999Z","title":"TMetalFraction|transition metal fraction","venue":null,"work_id":"a5b0cdf8-1aef-4b6a-8e82-558651ecbbd9","year":null},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.465171Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:91d13aeb5787dbfd1e25c1899070f27918410b63ab3b5daddc2fc379891cf490","observation_id":"8b373ad3-e738-4e1d-acbe-f3c1ea43a009","resolution":{"observed_at":"2026-08-15T16:43:25.661618Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:26.909013Z","title":null,"venue":null,"work_id":"561c342d-716d-451c-a2d1-1580a0d5bcce","year":2017},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.471937Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:e19c85109085e8841f3a869a097ff861e8819aff9c9cefc953302f1d8ecb4217","observation_id":"1bcadcbf-4a3e-47bd-af54-3978c1785f81","resolution":{"observed_at":"2026-08-15T16:43:26.914162Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:25.519776Z","title":"& Ong, S","venue":null,"work_id":"bf1b23f2-05d4-4de7-b7af-7cbb96366278","year":2019},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.476122Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:d71196ff52e0c38545b546c86d41edab989f9b8389700753ce3b68ba7dc44102","observation_id":"bd1f86a4-2ac3-42ba-960c-3221e6e2b965","resolution":{"observed_at":"2026-08-15T16:43:25.592690Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:26.429525Z","title":"& Jain, A","venue":null,"work_id":"a18e5f8b-9766-4d1b-939b-74dd2062e168","year":2020},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.480189Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:353b3aa35d24d2a6ee2d0907dc6d48d5aba97e841d7f3d4c20f8045b16143c74","observation_id":"d3004be1-3a13-422d-848a-051e854d77a5","resolution":{"observed_at":"2026-08-15T16:43:26.434099Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:25.442213Z","title":null,"venue":null,"work_id":"f461137e-3951-406a-92fc-1c0c90b41baa","year":2015},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.484856Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:4fc6e739a65cdc7d16089d7fa4f8b5adb261d74a6f202a6095fd13112e93aaca","observation_id":"fd4b5963-50e0-4f46-8311-7b92929cac5c","resolution":{"observed_at":"2026-08-15T16:43:25.471266Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:25.385707Z","title":"& Ghiringhelli, L","venue":null,"work_id":"e24ec8f6-0b97-4899-b15e-02f592b4ba12","year":2018},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.504788Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:c9e55bb36801412d2ec236c6bc9d0e0083fdc1484636a082f454affd6ec075ae","observation_id":"2a62367d-fd96-4381-9a08-436441d70312","resolution":{"observed_at":"2026-08-15T16:43:25.406245Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:26.399733Z","title":"Mechanical properties of some steels","venue":null,"work_id":"cd838360-9757-4462-8509-42cd1ec79d69","year":null},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.567780Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:39f5bf6531a15978c093fef8a63f081c8ef30bce5bee070bf6b76269cde0b2b4","observation_id":"93511682-c57d-4855-9089-0c9613a4fe7c","resolution":{"observed_at":"2026-08-15T16:43:26.404073Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:25.366269Z","title":"& Tavazza, F","venue":null,"work_id":"02e82e53-01e5-4c88-b9a9-380ec4526527","year":2017},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.589825Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:9b3b960e018213664470d5d4bfa18da665f73956db1c95699036318b34e1c07b","observation_id":"c31a68e1-b047-4f4f-b541-9a3ccb4cf13f","resolution":{"observed_at":"2026-08-15T16:43:25.372024Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:26.370575Z","title":null,"venue":null,"work_id":"7d0a850e-bdf7-405e-a20a-dcbb643eb416","year":2018},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.619998Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:067c6a863e97f2a7753e619cc0b79adff6e308c1757a75c4deaf9151b200fc0c","observation_id":"2ea8cc65-bf4a-48a4-bdde-b608098e672e","resolution":{"observed_at":"2026-08-15T16:43:26.375026Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:26.354549Z","title":"& Brgoch, J","venue":null,"work_id":"e99be28b-f0b3-4c47-ada9-cd9836e21a47","year":2018},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.632646Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:cc277c87ee77f00a8448aacbdb29beb370291f59c8d3e09082b0b58d81aa2519","observation_id":"7c2b5e63-bd21-4b6e-87a9-f42aa3148404","resolution":{"observed_at":"2026-08-15T16:43:26.359490Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:25.345524Z","title":"& Aihara Jr., T","venue":null,"work_id":"cf636645-db39-46c4-9b7c-c430b82f8734","year":1997},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.649674Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:aea111e2efca5b5b163d52c1b0ae47d67e74b023336db4dc7d14d3c72e61daa1","observation_id":"8a3feff5-8733-4881-a9ea-47d5fa5bc1f8","resolution":{"observed_at":"2026-08-15T16:43:25.352767Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:25.325914Z","title":"& Wolverton, C","venue":null,"work_id":"ef845f5a-1d38-4849-996c-fdb13a4dbb81","year":2016},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.685445Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:9c15de0c7b8cbda70d187f4f6c007794b273efaee53f7e8b8891567934581ab6","observation_id":"8027cf32-4618-4695-917f-eea3dc2b5bc2","resolution":{"observed_at":"2026-08-15T16:43:25.331167Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:26.337032Z","title":null,"venue":null,"work_id":"1eaaf25e-d158-4609-8e15-f61037ee8657","year":2017},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.724999Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:d6a964a01b5996c7ac6b8cbd43e4ca818d6f5ee22a80aee46840c463464b97ac","observation_id":"4810210c-a44d-4dbb-92ae-ce584881be63","resolution":{"observed_at":"2026-08-15T16:43:26.342770Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:25.962992Z","title":null,"venue":null,"work_id":"511eca3c-2bbf-4479-8a79-0afa2618c45f","year":2012},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.774947Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:c21aaf048f839327210f66d92467b7a94656b1db1c2ecfa9a686d59f38d46379","observation_id":"e9ba03be-0c5d-4588-a426-6f0b3a04a8f7","resolution":{"observed_at":"2026-08-15T16:43:25.967858Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:25.309115Z","title":null,"venue":null,"work_id":"0b52f187-b576-440c-a3c3-8b9b41abb551","year":2015},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.841155Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:583edf753cac7b42d6c956f5aa7ea38c53bb2493913ff9fa94a62b137f48db56","observation_id":"716eaa0d-c945-4d66-b42e-17bb2dc247db","resolution":{"observed_at":"2026-08-15T16:43:25.314119Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:25.291456Z","title":null,"venue":null,"work_id":"9756fb90-30c1-495a-bed3-61ce083a256a","year":2013},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.881271Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:afb523ee488945a4b08e8774c4a4a3054dbfef6e26a67f34d1fcab4edfded66e","observation_id":"9ebed9bf-9977-4e68-840f-ae7441c6b74c","resolution":{"observed_at":"2026-08-15T16:43:25.296203Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:25.266989Z","title":null,"venue":null,"work_id":"992c8b41-eb77-47ae-95dc-fc9d2d140574","year":2024},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.886774Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:d37ff1f5541de8159f5a72f2fb369a1acb4f56d307b06bba473cdcf2c6cde2de","observation_id":"2b7f122a-b49e-4732-bafa-96365b9659a4","resolution":{"observed_at":"2026-08-15T16:43:25.274300Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:43:25.243203Z","title":null,"venue":null,"work_id":"b4f901b8-0be9-4124-9109-08e6647be756","year":2017},"citing_paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-15T16:43:24.893260Z"},"links":{"citing_paper":"/paper/2509.03547"},"observation_digest":"sha256:2725159f3b3ef203f5e4a693cc98f644ff45f446fb72f00f04c2b26a95a4f5a1","observation_id":"eb61df4d-d283-46aa-b525-0f0ae1b815c8","resolution":{"observed_at":"2026-08-15T16:43:25.250320Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2509.03547","last_updated":"2025-09-05T16:42:17Z","latest_version":2,"primary_category":"cond-mat.mtrl-sci","snapshot_observed_at":"2026-08-15T16:35:53.082923Z","submitted_at":"2025-09-02T16:45:02Z","title":"Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability"},"reference_resolution":{"displayed":62,"state_counts":{"malformed_identifier":2,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":34,"verified_exact":0,"verified_fuzzy":26},"total_outbound_references":62},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 62 of 62 outbound references and 0 inbound Pith citation observations for arXiv:2509.03547."}