{"as_of":"2026-08-07T09:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:25ab78dbd4aa9bf9557862f09ad50be3e0acaad514586b823f3619a4fed68526","coverage":[{"denominator":77,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":77,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T15:02:42.604007Z","state":"measured"},{"denominator":79,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":79,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T03:20:50.048642Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2607.28098","snapshot_observed_at":"2026-08-03T15:35:12.134758Z","title":"SciDataSailor: Deep Scientific Data Exploring","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.29007","last_updated":"2026-08-03T02:09:53Z","snapshot_observed_at":"2026-08-07T07:20:34.396191Z","submitted_at":"2026-07-31T04:07:58Z","title":"EasyBCI Agent: Towards Universal Neural Data Preprocessing for Brain-Computer Interfaces","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-03T15:35:12.134758Z"},"links":{"cited_paper":"/paper/2607.28098","citing_paper":"/paper/2607.29007"},"observation_digest":"sha256:60e3da521dc9d6d992607440f731e9888385ca5b0ff3ea25cb703e6b60a3b271","observation_id":"4ccd97be-210c-4f91-b4c8-c61fdbf9ce07","resolution":{"observed_at":"2026-08-03T15:35:12.134758Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2607.28098","snapshot_observed_at":"2026-08-04T03:20:50.048642Z","title":"SciDataSailor: Deep Scientific Data Exploring","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.29007","last_updated":"2026-08-03T02:09:53Z","snapshot_observed_at":"2026-08-07T07:20:34.396191Z","submitted_at":"2026-07-31T04:07:58Z","title":"EasyBCI Agent: Towards Universal Neural Data Preprocessing for Brain-Computer Interfaces","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-04T03:20:50.048642Z"},"links":{"cited_paper":"/paper/2607.28098","citing_paper":"/paper/2607.29007"},"observation_digest":"sha256:f65b8eb94d2c08c346b03197f150713b91004d325d27f9de23adc1460ec72839","observation_id":"7f5b0f28-ec26-4c02-8612-193b05ee8d99","resolution":{"observed_at":"2026-08-04T03:20:50.048642Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2607.28098/citation-record","integrity":"/paper/2607.28098/integrity","json":"/paper/2607.28098/citation-record.json","paper":"/paper/2607.28098"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T15:02:35.844070Z","title":"Data mining and knowledge discovery in databases: implications for scientific databases","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:35.844070Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:b1e935d5634652998c6697855b6384edd3a80553839f92256b57838c65008627","observation_id":"a19c0c4d-d261-4b45-8320-ea803f21b9e0","resolution":{"observed_at":"2026-08-01T15:02:35.844070Z","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":"2026-08-01T15:02:35.949271Z","title":"Scidatacopilot: An agentic data preparation framework for agi-driven scientific discovery","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:35.949271Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:e2044062098b1568f74c8b31a12ec3bfd32e7c7675884b5c6ff0d428e766e5f2","observation_id":"f7ec372e-741f-4dab-a31b-50a8596daef3","resolution":{"observed_at":"2026-08-01T15:02:35.949271Z","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":"2026-08-01T15:02:36.046287Z","title":"Cellvoyager: Ai compbio agent generates new insights by autonomously analyzing biological data.Nature Methods, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:36.046287Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:cf7a1b80cc8775c992dda5ba622e5b18e8396672ac169b213de6019f29c16443","observation_id":"c4a75035-a32d-4996-b119-042fa16945cf","resolution":{"observed_at":"2026-08-01T15:02:36.046287Z","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":"2026-08-01T15:02:36.137282Z","title":"scbasecount: an ai agent-curated, uniformly processed, and autonomously updated single cell data repository.bioRxiv, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:36.137282Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:7700e70a826e27f71705a9f10d1fae1b91c857879b4591ffe50d09a09551fbb5","observation_id":"05322c31-f044-4ca5-9c75-a9d67183c6a0","resolution":{"observed_at":"2026-08-01T15:02:36.137282Z","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":"2026-08-01T15:02:36.222309Z","title":"Data harmonization for heterogeneous datasets: a systematic literature review.Applied Sciences, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:36.222309Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:06b0e6f56752746b31e7a1600325342333479a9b2b55e90673327dd888c211b8","observation_id":"b7b13479-2c42-4215-9ba6-ceb72ba058f4","resolution":{"observed_at":"2026-08-01T15:02:36.222309Z","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":"2026-08-01T15:02:36.282273Z","title":"Data integration for heterogenous datasets.Big data, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:36.282273Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:4c8dbfc2c530c7157c1fdec898e9d790a26c719ed8c1c391d033fb70d6b89f9c","observation_id":"4a414705-5232-410d-8538-9d6c127192ee","resolution":{"observed_at":"2026-08-01T15:02:36.282273Z","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":"2026-08-01T15:02:36.366835Z","title":"Does the use of unusual combinations of datasets contribute to greater scientific impact?Proceedings of the National Academy of Sciences, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:36.366835Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:0de0f81c2edc7eba7cdd78dc05be29bbe4023653288fe2699c83a477f9708480","observation_id":"33a33fa6-888d-49dc-8485-f0dd27ee6d10","resolution":{"observed_at":"2026-08-01T15:02:36.366835Z","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":"2026-08-01T15:02:36.435339Z","title":"A repository for the publication and sharing of heterogeneous materials data","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:36.435339Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:e1bc361f5c5085017492ab89e3e59ded8f60168418e38407f93a0bee426f999c","observation_id":"26774ca3-c90e-4879-9b3c-41be4a38f8f3","resolution":{"observed_at":"2026-08-01T15:02:36.435339Z","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":"2026-08-01T15:02:36.510840Z","title":"Hiersearch: A hierarchical enterprise deep search framework integrating local and web searches","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:36.510840Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:9e93d2fb247b1610035af20dd592a05ca7cadd952b40e8d5d34a8299f37c90e2","observation_id":"05e67e9c-8d4a-4eab-96e9-ee07473f383c","resolution":{"observed_at":"2026-08-01T15:02:36.510840Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.09477","last_updated":"2025-07-16T15:44:18Z","snapshot_observed_at":"2026-08-06T17:52:36.083525Z","submitted_at":"2025-07-13T03:29:41Z","title":"Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.09477","snapshot_observed_at":"2026-08-01T15:02:36.593145Z","title":"Towards agentic rag with deep reasoning: A survey of rag-reasoning systems in llms.arXiv preprint arXiv:2507.09477, 2, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:36.593145Z"},"links":{"cited_paper":"/paper/2507.09477","citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:2cf425b8fc99b5a85816dc32d90349a2c9b1027d2c544a891e76a7fd77cd5981","observation_id":"fc4a7b67-4396-4f28-ae68-fda642726d70","resolution":{"observed_at":"2026-08-01T15:02:36.593145Z","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":"2026-08-01T15:02:36.691731Z","title":"A survey of personalization: From rag to agent.ACM Transactions on Information Systems, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:36.691731Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:9aa0d83389885ebaf1df7339c18492e9e91b12fcc87513575e5149f1ed33f543","observation_id":"8705d3e9-149c-4d30-935a-13ff6fe38830","resolution":{"observed_at":"2026-08-01T15:02:36.691731Z","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":"2026-08-01T15:02:36.756510Z","title":"Sqlfixagent: Towards semantic-accurate text-to-sql parsing via consistency-enhanced multi-agent collaboration","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:36.756510Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:89ecdefc81c7ce6b632a8a0015987852eafecf7773ef6904ea8a0c19a96dd6d2","observation_id":"74d290db-bb75-4659-861e-0aa3415d78f6","resolution":{"observed_at":"2026-08-01T15:02:36.756510Z","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":"2026-08-01T15:02:36.819280Z","title":"this is my sql, are you with me?","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:36.819280Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:0aec218be0b2984fa4d113818b7ae978ba161fd15cfc2e7217dc2b6fae148ae4","observation_id":"0b06c174-6040-4f4e-95d9-e6502fa15e3b","resolution":{"observed_at":"2026-08-01T15:02:36.819280Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.18959","last_updated":"2025-07-03T17:48:36Z","snapshot_observed_at":"2026-08-06T23:12:54.314265Z","submitted_at":"2025-06-23T17:27:19Z","title":"From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.18959","snapshot_observed_at":"2026-08-01T15:02:36.884640Z","title":"From web search towards agentic deep research: Incentivizing search with reasoning agents.arXiv preprint arXiv:2506.18959, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:36.884640Z"},"links":{"cited_paper":"/paper/2506.18959","citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:0be74ef8d3359411f22bac5e90ffb8c8d42618d75c320ae92bdaa8f2f49ecd7b","observation_id":"ba7bce7b-deed-4f19-8704-ae117fef9445","resolution":{"observed_at":"2026-08-01T15:02:36.884640Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.18096","last_updated":"2025-09-03T15:32:23Z","snapshot_observed_at":"2026-08-06T23:20:46.744749Z","submitted_at":"2025-06-22T16:52:48Z","title":"Deep Research Agents: A Systematic Examination And Roadmap","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.18096","snapshot_observed_at":"2026-08-01T15:02:36.965352Z","title":"Deep research agents: A systematic examination and roadmap.arXiv preprint arXiv:2506.18096, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:36.965352Z"},"links":{"cited_paper":"/paper/2506.18096","citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:a1c77f4fbd69bc82a10233ff1e6937e4406fd4c3d200cffb82bf03d13c0d9ebc","observation_id":"739c0335-8ff3-4bea-9c35-098ac4939804","resolution":{"observed_at":"2026-08-01T15:02:36.965352Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2603.01152","last_updated":"2026-06-20T09:26:23Z","snapshot_observed_at":"2026-08-07T06:59:58.157969Z","submitted_at":"2026-03-01T15:36:10Z","title":"DeepResearch-9K: A Challenging Benchmark Dataset of Deep-Research Agent","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2603.01152","snapshot_observed_at":"2026-08-01T15:02:37.058668Z","title":"Deepresearch-9k: A challenging benchmark dataset of deep-research agent.arXiv preprint arXiv:2603.01152, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:37.058668Z"},"links":{"cited_paper":"/paper/2603.01152","citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:3b39dc831d5b13d32206477c7e9b19aa2b13bc0c2d63391544f489166f37b5fe","observation_id":"7316b579-fadf-432c-993a-8c296e06f9a3","resolution":{"observed_at":"2026-08-01T15:02:37.058668Z","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":"2026-08-01T15:02:37.144295Z","title":"Deepwidesearch: Benchmarking depth and width in agentic information seeking.arXiv preprint arXiv:2510.20168, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:37.144295Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:7d27b2f9a9ef15d3e8986d0b7b7b4d14fe89ea0713e8a78b01eeb9be206a7b0b","observation_id":"174cd057-33aa-400c-9e30-e778f10878dc","resolution":{"observed_at":"2026-08-01T15:02:37.144295Z","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":"2026-08-01T15:02:37.228103Z","title":"Openseeker: Democ- ratizing frontier search agents by fully open-sourcing training data.arXiv preprint arXiv:2603.15594, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:37.228103Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:85b39676381388b80b3012f79d5f3b1cc540e4d6f9aa6f0e78e5f5545a2e2ec6","observation_id":"148d3df6-dd32-4bdb-b58d-8649efa169ba","resolution":{"observed_at":"2026-08-01T15:02:37.228103Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.02592","last_updated":"2025-07-03T12:59:07Z","snapshot_observed_at":"2026-08-06T06:12:37.171726Z","submitted_at":"2025-07-03T12:59:07Z","title":"WebSailor: Navigating Super-human Reasoning for Web Agent","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.02592","snapshot_observed_at":"2026-08-01T15:02:37.319474Z","title":"Websailor: Navigating super-human reasoning for web agent.arXiv preprint arXiv:2507.02592, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:37.319474Z"},"links":{"cited_paper":"/paper/2507.02592","citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:145f96f595841747d70a019c3c87e51d58bc12ac45694c264a00ae52aa0e0044","observation_id":"4b7a2568-b7df-4f4f-8715-e76b6994cb1b","resolution":{"observed_at":"2026-08-01T15:02:37.319474Z","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":"2026-08-01T15:02:37.402678Z","title":"Websailor-v2: Bridging the chasm to proprietary agents via synthetic data and scalable reinforcement learning.arXiv preprint arXiv:2509.13305, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:37.402678Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:ed5df85d587a1df4bf569a4feda3994b7532cc63d92ceee5e1857b8345bbbc33","observation_id":"28e34892-344b-417f-903b-fb7931de2bbb","resolution":{"observed_at":"2026-08-01T15:02:37.402678Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.20201","last_updated":"2025-03-26T03:51:32Z","snapshot_observed_at":"2026-07-06T20:58:46.814850Z","submitted_at":"2025-03-26T03:51:32Z","title":"Open Deep Search: Democratizing Search with Open-source Reasoning Agents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.20201","snapshot_observed_at":"2026-08-01T15:02:37.488903Z","title":"Open deep search: Democratizing search with open-source reasoning agents.arXiv preprint arXiv:2503.20201, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:37.488903Z"},"links":{"cited_paper":"/paper/2503.20201","citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:584e69d3b65e6b442140b5e57e31c7b4b7d21e339b455d093f33f297dba8eca8","observation_id":"4dad7483-1a9d-443a-bdd5-154efb22a1b4","resolution":{"observed_at":"2026-08-01T15:02:37.488903Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.10362","last_updated":"2024-07-17T17:28:36Z","snapshot_observed_at":"2026-08-06T06:16:43.714786Z","submitted_at":"2024-07-14T23:52:25Z","title":"LAB-Bench: Measuring Capabilities of Language Models for Biology Research","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.10362","snapshot_observed_at":"2026-08-01T15:02:37.574663Z","title":"Lab-bench: Measuring capabilities of language models for biology research.arXiv preprint arXiv:2407.10362, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:37.574663Z"},"links":{"cited_paper":"/paper/2407.10362","citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:52d23314e6cc22ed5348fe53f4f26e1ccfe069472231ebf968d126c9b704cccc","observation_id":"37c8a74a-ced0-4a12-8385-bd36b3640d68","resolution":{"observed_at":"2026-08-01T15:02:37.574663Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.00466","last_updated":"2024-06-29T15:23:28Z","snapshot_observed_at":"2026-07-06T18:38:59.090751Z","submitted_at":"2024-06-29T15:23:28Z","title":"BioKGBench: A Knowledge Graph Checking Benchmark of AI Agent for Biomedical Science","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.00466","snapshot_observed_at":"2026-08-01T15:02:37.658747Z","title":"Biokgbench: A knowledge graph checking benchmark of ai agent for biomedical science.arXiv preprint arXiv:2407.00466, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:37.658747Z"},"links":{"cited_paper":"/paper/2407.00466","citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:7cfa04526a7da59ba08bf6a2d226d7f7f484f16be7c172d45d3e2ecad51a545d","observation_id":"0cc883a2-0f45-4795-b01b-0f8119b96d96","resolution":{"observed_at":"2026-08-01T15:02:37.658747Z","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":"2026-08-01T15:02:37.751577Z","title":"Curie: Evaluating llms on multitask scientific long context understanding and reasoning.International Conference on Learning Representations, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:37.751577Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:0c58b79c95aa13cdd27e0b867f557517d48eb64a6cae9d81e2c8ff10330cc36a","observation_id":"e7b4557f-3ebc-4c7f-bc97-fcf3412c662e","resolution":{"observed_at":"2026-08-01T15:02:37.751577Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.05080","last_updated":"2025-03-31T14:39:44Z","snapshot_observed_at":"2026-07-06T19:29:05.492290Z","submitted_at":"2024-10-07T14:33:50Z","title":"ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.05080","snapshot_observed_at":"2026-08-01T15:02:37.896688Z","title":"Scienceagentbench: Toward rigorous assessment of language agents for data-driven scientific discovery.arXiv preprint arXiv:2410.05080, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:37.896688Z"},"links":{"cited_paper":"/paper/2410.05080","citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:ad212a82aa511b7943d53ae5eff702a8da05df38cdb548afbd485bd06fd70341","observation_id":"487e51cc-4ac0-47cd-a22e-49062cd04b05","resolution":{"observed_at":"2026-08-01T15:02:37.896688Z","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":"2026-08-01T15:02:38.016857Z","title":"Bixbench: a comprehensive bench- mark for llm-based agents in computational biology.arXiv preprint arXiv:2503.00096, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:38.016857Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:52acf5c3af4663d47e02f7dc212bcb4b9b9e3c935cda1cf99534afd37851164c","observation_id":"927f9d1a-8d22-4c19-b73e-2f7e708f489b","resolution":{"observed_at":"2026-08-01T15:02:38.016857Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2601.21800","last_updated":"2026-08-06T06:33:02Z","snapshot_observed_at":"2026-08-07T08:45:29.869084Z","submitted_at":"2026-01-29T14:44:03Z","title":"BioAgent Bench: An AI Agent Evaluation Suite for Bioinformatics","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2601.21800","snapshot_observed_at":"2026-08-01T15:02:38.129421Z","title":"Bioagent bench: An ai agent evaluation suite for bioinformatics.arXiv preprint arXiv:2601.21800, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:38.129421Z"},"links":{"cited_paper":"/paper/2601.21800","citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:5557bf6d28e3d4f904efde47f0f248edba9b1de534320e58b3b813148a918291","observation_id":"6f8118cb-6446-403b-82b9-e8936a1bbc74","resolution":{"observed_at":"2026-08-01T15:02:38.129421Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2606.06473","last_updated":"2026-06-04T17:55:59Z","snapshot_observed_at":"2026-08-01T19:37:15.448610Z","submitted_at":"2026-06-04T17:55:59Z","title":"MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2606.06473","snapshot_observed_at":"2026-08-01T15:02:38.278796Z","title":"Mlevolve: A self-evolving framework for automated machine learning algorithm discovery.arXiv preprint arXiv:2606.06473, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:38.278796Z"},"links":{"cited_paper":"/paper/2606.06473","citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:429e1b482775f232caaf30736add07213f25d3887309d20c3fbd22c3b0940741","observation_id":"0f3c4954-f2f3-4642-97b1-16ba229cbb8b","resolution":{"observed_at":"2026-08-01T15:02:38.278796Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2604.28158","last_updated":"2026-05-01T14:37:29Z","snapshot_observed_at":"2026-07-06T23:13:29.310140Z","submitted_at":"2026-04-30T17:44:55Z","title":"Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2604.28158","snapshot_observed_at":"2026-08-01T15:02:38.393054Z","title":"Intern-atlas: A methodological evolution graph as research infrastructure for ai scientists.arXiv preprint arXiv:2604.28158, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:38.393054Z"},"links":{"cited_paper":"/paper/2604.28158","citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:ee39887d31961b1bafe0dc3c0c46a7adfe503fb3472c615b0678c47cab734a2b","observation_id":"22c622a3-1801-4f22-a4bc-fbbf7305bf7e","resolution":{"observed_at":"2026-08-01T15:02:38.393054Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2606.07297","last_updated":"2026-06-05T14:08:27Z","snapshot_observed_at":"2026-07-06T23:46:55.970997Z","submitted_at":"2026-06-05T14:08:27Z","title":"SWE-Explore: Benchmarking How Coding Agents Explore Repositories","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2606.07297","snapshot_observed_at":"2026-08-01T15:02:38.513880Z","title":"Swe-explore: Benchmarking how coding agents explore repositories","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:38.513880Z"},"links":{"cited_paper":"/paper/2606.07297","citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:b2e71bddcdcc5fd605e74873bd408accdb2ec94dd9e39a7e3bc4efbe634c6cc5","observation_id":"b70495ab-7b58-4906-889c-94aea9c22478","resolution":{"observed_at":"2026-08-01T15:02:38.513880Z","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":"2026-08-01T15:02:38.621060Z","title":"Scaling generalist data-analytic agents.International Conference on Learning Representations, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:38.621060Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:611bc514f40b70dbda6caf97f156d7cb9a5ee79d77424747feb8d3b577f9cd53","observation_id":"9a2e081d-61bc-4ecf-9afe-d7630047f9dd","resolution":{"observed_at":"2026-08-01T15:02:38.621060Z","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":"2026-08-01T15:02:38.710415Z","title":"Agentic reinforced policy optimization","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:38.710415Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:fb2e52dbfd00c1d88e0906741a5729f44791ee4f2e09aec18c2c53ad2888cef7","observation_id":"89f7c97b-322e-4f41-994b-dd5f3834f45c","resolution":{"observed_at":"2026-08-01T15:02:38.710415Z","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":"2026-08-01T15:02:38.798190Z","title":"Deepanalyze: Agentic large language models for autonomous data science.arXiv preprint arXiv:2510.16872, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:38.798190Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:78591dd5a47aeb6e81acb61ea609c437e6953a1bec32a755cdd23e0bf359c432","observation_id":"ff0148fc-781d-433e-b683-d9cb28c8e644","resolution":{"observed_at":"2026-08-01T15:02:38.798190Z","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":"2026-08-01T15:02:38.962537Z","title":"Dataflow: An llm-driven framework for unified data preparation and workflow automation in the era of data-centric ai.arXiv preprint arXiv:2512.16676, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:38.962537Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:248c5ac5936f99db72636ee1e2d6bcfc43d87352b7cb5dcc482271ea2e9ef111","observation_id":"6c5f74a3-41da-416e-8a97-0266af65f451","resolution":{"observed_at":"2026-08-01T15:02:38.962537Z","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":"2026-08-01T15:02:39.049102Z","title":"Dataflex: A unified framework for data-centric dynamic training of large language models.arXiv preprint arXiv:2603.26164, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:39.049102Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:d29582961299876c8a94fbdada24a94425a1163e614157495b2ca901233c8ef5","observation_id":"3a998933-480d-4128-918e-89506824d753","resolution":{"observed_at":"2026-08-01T15:02:39.049102Z","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":"2026-08-01T15:02:39.195033Z","title":"Agentflow: Unified agent data synthesis framework","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:39.195033Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:8de2722f68b8c5216738fb19f37f2fcc9923a1cf0c8ebc3404fbbd742d50ca87","observation_id":"bf1f76ed-b351-47be-98a6-7940aa98e746","resolution":{"observed_at":"2026-08-01T15:02:39.195033Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2606.30616","last_updated":"2026-07-13T13:01:42Z","snapshot_observed_at":"2026-08-05T00:51:27.916299Z","submitted_at":"2026-06-29T17:50:54Z","title":"Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2606.30616","snapshot_observed_at":"2026-08-01T15:02:39.316443Z","title":"Scaling the horizon, not the parameters: Reaching trillion-parameter performance with a 35b agent.arXiv preprint arXiv:2606.30616, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:39.316443Z"},"links":{"cited_paper":"/paper/2606.30616","citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:4092e34528df1ea27b0a66528cf157f7e57b5764b0b7a8b8fece97c9a580a6fa","observation_id":"6a68402e-9a60-42d6-a6e7-32c2b3f9049e","resolution":{"observed_at":"2026-08-01T15:02:39.316443Z","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":"2026-08-01T15:02:39.449995Z","title":"I-mcts: Enhancing agentic automl via introspective monte carlo tree search.Association for Computational Linguistics, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:39.449995Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:e7a6d40d2914f55a5831060a5b48a5120a09605ebffda840cb5cd3117b67f3a5","observation_id":"b0a5e653-bbb4-43ac-b956-20349b224f00","resolution":{"observed_at":"2026-08-01T15:02:39.449995Z","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":"2026-08-01T15:02:39.555595Z","title":"Treerl: Llm reinforcement learning with on-policy tree search","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:39.555595Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:2673310bb018cb45ee0b1f10d386fa66a2aacb99b206626aea4eb359473d09e7","observation_id":"eb495bf5-7b67-421e-8c1c-4cf07baef179","resolution":{"observed_at":"2026-08-01T15:02:39.555595Z","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":"2026-08-01T15:02:39.669378Z","title":"Tooltree: Efficient llm agent tool planning via dual-feedback monte carlo tree search and bidirectional pruning","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:39.669378Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:434dd299da22de7c822777195af0ec64782eaad966353933ffc09ed14b302f39","observation_id":"17ae53a5-edad-4b56-affe-6af51e73bca0","resolution":{"observed_at":"2026-08-01T15:02:39.669378Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.11584","last_updated":"2024-04-17T17:32:41Z","snapshot_observed_at":"2026-08-04T23:37:27.678120Z","submitted_at":"2024-04-17T17:32:41Z","title":"The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.11584","snapshot_observed_at":"2026-08-01T15:02:39.738393Z","title":"The landscape of emerging ai agent architectures for reasoning, planning, and tool calling: A survey.arXiv preprint arXiv:2404.11584, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:39.738393Z"},"links":{"cited_paper":"/paper/2404.11584","citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:808e3f7cbbf6372d0e66be8b7a953db19952ff9bb36e4f823800c73326dfb4d6","observation_id":"394571eb-4e9b-4a67-8f89-8355090c7d86","resolution":{"observed_at":"2026-08-01T15:02:39.738393Z","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":"2026-08-01T15:02:39.810309Z","title":"Menti: Bridging medical calculator and llm agent with nested tool calling","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:39.810309Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:3541c7d7497671ede9f3694a2488ac78ede6d94cc920d5f55ff26774fde167aa","observation_id":"db9ffb9c-b92f-4c91-9959-bd768c2d360c","resolution":{"observed_at":"2026-08-01T15:02:39.810309Z","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":"2026-08-01T15:02:39.883154Z","title":"Re- act: Synergizing reasoning and acting in language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:39.883154Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:f067ce7c2d373c4159c5a184b74cefdb236eacd0e7ecdf87ea91c3825737afaa","observation_id":"36eca45c-45be-4f45-9f20-89aaabf7c07e","resolution":{"observed_at":"2026-08-01T15:02:39.883154Z","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":"2026-08-01T15:02:39.940861Z","title":"Jaap van den Herik, Paolo Ciancarini, and H","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:39.940861Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:71955f33cf1d41ff0eab97e412e9371b252edf3c96cd45129661b191d79882e1","observation_id":"2ae56f04-92bb-42f4-ba89-2ab9abc1db7f","resolution":{"observed_at":"2026-08-01T15:02:39.940861Z","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":"2026-08-01T15:02:39.992441Z","title":"Executable code actions elicit better llm agents","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:39.992441Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:961aa8676c55194f935e81faad05f3807022409fc9be76352cd0a799e58fa25e","observation_id":"ded15bb1-b35f-4e22-bb2a-fcf7a7072e3d","resolution":{"observed_at":"2026-08-01T15:02:39.992441Z","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":"2026-08-01T15:02:40.077490Z","title":"Gpt-5.4 thinking system card","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:40.077490Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:b15e91226d0386b6f832254b179b4eef5c27ffd4e7a3a86f770d5dde276dc4e7","observation_id":"724cee80-1251-4f88-af66-3fbf7e395304","resolution":{"observed_at":"2026-08-01T15:02:40.077490Z","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":"2026-08-01T15:02:40.179936Z","title":"Gemini 3.1 pro model card","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:40.179936Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:92ab339eef2a9aff5196b4566f72143266b5791a8d81a60dd56997c575543e10","observation_id":"ebcc6646-bafd-42c4-a284-f525c3e267e7","resolution":{"observed_at":"2026-08-01T15:02:40.179936Z","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":"2026-08-01T15:02:40.260007Z","title":"System card: Claude opus 4.7","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:40.260007Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:bfc2bc8b8a229b8996e597c445d405024dbce51e1f0c08a428022fe08cbe94e9","observation_id":"e3d1ff6d-4199-4597-af6f-01e0fb270b91","resolution":{"observed_at":"2026-08-01T15:02:40.260007Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2602.15763","last_updated":"2026-02-24T10:44:44Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-02-17T17:50:56Z","title":"GLM-5: from Vibe Coding to Agentic Engineering","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2602.15763","snapshot_observed_at":"2026-08-01T15:02:40.321830Z","title":"Glm-5: From vibe coding to agentic engineering.arXiv preprint arXiv:2602.15763, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:40.321830Z"},"links":{"cited_paper":"/paper/2602.15763","citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:4f92549a9681b1443fd9646fe0fcb4367a39b4d3cb7fedfdedda70f1c088a21e","observation_id":"dab12d05-e896-4429-aef9-324c2d7d3b36","resolution":{"observed_at":"2026-08-01T15:02:40.321830Z","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":"2026-08-01T15:02:40.409897Z","title":"Kimi k2.6 model card.https://www.kimi.com/blog/kimi-k2-6, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:40.409897Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:7e88fc568ac9d6f9921f54486cec20d335c75fbd231d54160499effa941c0cb0","observation_id":"28e413a7-509a-4dce-a491-7dc0507c5a9d","resolution":{"observed_at":"2026-08-01T15:02:40.409897Z","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":"2026-08-01T15:02:40.465430Z","title":"Deepseek-v4: Towards highly efficient million-token context intelligence.arXiv preprint arXiv:2606.19348, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:40.465430Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:ffb4e5f228561f231eda259f1454e6f936fb57047f345e277064631f67fedcc4","observation_id":"97a3612a-aa25-4281-9852-244bcbac5897","resolution":{"observed_at":"2026-08-01T15:02:40.465430Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.10925","last_updated":"2025-08-08T19:24:38Z","snapshot_observed_at":"2026-08-01T16:27:35.664983Z","submitted_at":"2025-08-08T19:24:38Z","title":"gpt-oss-120b & gpt-oss-20b Model Card","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.10925","snapshot_observed_at":"2026-08-01T15:02:40.532302Z","title":"Gpt-oss-120b & gpt-oss-20b model card.arXiv preprint arXiv:2508.10925, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:40.532302Z"},"links":{"cited_paper":"/paper/2508.10925","citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:f634a3809187c3ec48ca64b334a868475f2b52799d034aeb54c1650f3c613f37","observation_id":"97d29354-c353-4edc-8238-27092a2efa3d","resolution":{"observed_at":"2026-08-01T15:02:40.532302Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09388","last_updated":"2025-05-14T13:41:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-14T13:41:34Z","title":"Qwen3 Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.09388","snapshot_observed_at":"2026-08-01T15:02:40.614959Z","title":"Qwen3 technical report.arXiv preprint arXiv:2505.09388, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:40.614959Z"},"links":{"cited_paper":"/paper/2505.09388","citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:19a3e0f5d989499300d677f1f49ea24fecf6645a3b7a178a42e6f85d09671f04","observation_id":"75e42885-91e0-403a-9939-d89ef5d1f780","resolution":{"observed_at":"2026-08-01T15:02:40.614959Z","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":"2026-08-01T15:02:40.691981Z","title":"Qwen3.5: Towards native multimodal agents.https://qwen.ai/blog?id=qwen3.5,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:40.691981Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:4d25a7ca9663d1df3b8c2e2e85ac63d0841be20f3c56bd102e8d428ebfa6b21b","observation_id":"65096b18-990f-4d77-90a6-b228e5225496","resolution":{"observed_at":"2026-08-01T15:02:40.691981Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.05685","last_updated":"2023-12-24T02:01:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-06-09T05:55:52Z","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.05685","snapshot_observed_at":"2026-08-01T15:02:40.858638Z","title":"Xing, Hao Zhang, Joseph E","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:40.858638Z"},"links":{"cited_paper":"/paper/2306.05685","citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:aef457eb4aa56ae0ddb2fb52fb1218460d5937a07b8433be74e1fd384e5a63da","observation_id":"e7700bf8-dc75-461f-bd4b-99226b44a351","resolution":{"observed_at":"2026-08-01T15:02:40.858638Z","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":"2026-08-01T15:02:40.905909Z","title":"Llamafactory: Unified efficient fine-tuning of 100+ language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:40.905909Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:d8401000ca6162c7b7e640834479c23a9340a34c574eea5c8e3014ca370a4b82","observation_id":"a095b0a8-a5a0-434d-af22-9b6e6a1f942d","resolution":{"observed_at":"2026-08-01T15:02:40.905909Z","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":"2026-08-01T15:02:40.963041Z","title":"Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:40.963041Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:3b261bb456f6600da5d568080e1f479499be72a7d87a088531e732bdc3dbbda5","observation_id":"da16be69-7765-4c09-ac29-a496362b4c11","resolution":{"observed_at":"2026-08-01T15:02:40.963041Z","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":"2026-08-01T15:02:41.048192Z","title":"content\":","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:41.048192Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:52e16adb6f903ccf2f6cdb4cea41e43811eeb59b48818130b848ac9049cba478","observation_id":"c08e3cd1-8f54-4c3e-b768-3a5bc103f18b","resolution":{"observed_at":"2026-08-01T15:02:41.048192Z","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":"2026-08-01T15:02:41.571899Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":411,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:41.571899Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:24da562ec868aa39de46e53da79af7c59ba063d1242638db64d7a442da00afde","observation_id":"b4b7bf5b-8f9d-4b06-b7ae-f2edea20812e","resolution":{"observed_at":"2026-08-01T15:02:41.571899Z","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":"2026-08-01T15:02:41.662003Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":422,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:41.662003Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:492972dc4c103099e97b3954b1a97449027152627d5405e20772868246831b54","observation_id":"09d45381-d402-4d37-a493-15ebd6958ecf","resolution":{"observed_at":"2026-08-01T15:02:41.662003Z","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":"2026-08-01T15:02:41.755833Z","title":"{DATASET_ROOT}","venue":null,"work_id":null,"year":2084},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":433,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:41.755833Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:70c68071020c1062dc5eae3ffb1b754a64378893ab8f4d35fb42c82d3ddf09fa","observation_id":"007837b8-6fa4-4e8d-803b-fc46553c99c2","resolution":{"observed_at":"2026-08-01T15:02:41.755833Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-01T15:02:40.775819Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":2026,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:40.775819Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:c8ed78e5796d87e0a2db767d190b14cd0c4427f5e9aa04a36fec0b176af5ed6d","observation_id":"7650578f-cf92-4792-88e7-7fb4f2911628","resolution":{"observed_at":"2026-08-01T15:02:40.775819Z","resolver_source":null,"status":"parse_uncertain"},"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":"2026-08-01T15:02:41.110043Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":5421,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:41.110043Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:a0528629ce381e713b56c1ced2436507562ba3953057a0aa7bc3f4a6b96ae7ce","observation_id":"1158ceb2-5565-4885-b46f-93b59ba4fc63","resolution":{"observed_at":"2026-08-01T15:02:41.110043Z","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":"2026-08-01T15:02:41.212988Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":5452,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:41.212988Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:b643d8281d0aa7e2805736b16f94bd7f5e644329269b12bf2a03256667ae25a4","observation_id":"93b269f6-93d0-4e26-90cf-712983321096","resolution":{"observed_at":"2026-08-01T15:02:41.212988Z","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":"2026-08-01T15:02:41.258878Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":5483,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:41.258878Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:afe8b6b16c8e189265eec6cc05df81e8e6151e6e9c3fba42be95efd8133dea92","observation_id":"f531384d-d9f2-46e6-bebd-de70ad3f913e","resolution":{"observed_at":"2026-08-01T15:02:41.258878Z","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":"2026-08-01T15:02:41.261124Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":5514,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:41.261124Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:c4f461cad184db4d86626706ed9bd270648c805549f40be079f5437ae7f0bb52","observation_id":"4b797739-42f9-4084-8dfd-9a20803d96b8","resolution":{"observed_at":"2026-08-01T15:02:41.261124Z","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":"2026-08-01T15:02:41.326632Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":5555,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:41.326632Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:5016d10ce9598ef75ae3d1b9662894ce88b419b06848744d34710f91aacd4935","observation_id":"3666fa9c-b3ff-4bed-9c32-73a426d874ad","resolution":{"observed_at":"2026-08-01T15:02:41.326632Z","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":"2026-08-01T15:02:41.449235Z","title":"{DATASET_ROOT}","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":5586,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:41.449235Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:0303e9a71424edabb0f55c4fe6a0c2d9f40e84890d9afacb37d770c608ff50fe","observation_id":"1cbf2e34-2430-4b2c-ba7f-456cd05347cb","resolution":{"observed_at":"2026-08-01T15:02:41.449235Z","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":"2026-08-01T15:02:41.842336Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":7281,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:41.842336Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:dc7dc251526bcefe6f57efa83e82f8fbcd55a89fdaa1e7a2ae13d0c41320981c","observation_id":"53d4d444-727b-4ad1-96a2-98546e234e86","resolution":{"observed_at":"2026-08-01T15:02:41.842336Z","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":"2026-08-01T15:02:41.933027Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":7292,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:41.933027Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:f4ae39abe03be8f583fd74e169009f1ddc237326e924655540e4f95bc07c0aa2","observation_id":"e40381c5-1824-4989-a581-4bad1c1132a9","resolution":{"observed_at":"2026-08-01T15:02:41.933027Z","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":"2026-08-01T15:02:41.992951Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":7303,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:41.992951Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:5f282d5048b8642467b00b2930ebec4cc2f60fa0356cb9879118518772f7f110","observation_id":"48208cdc-ae67-41b9-83bc-a6b8f42f417d","resolution":{"observed_at":"2026-08-01T15:02:41.992951Z","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":"2026-08-01T15:02:42.057873Z","title":"{DATASET_ROOT}","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":7314,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:42.057873Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:021203c1481567c65da9a6571574193295e15dd59d5deb2a633aed32355d04fe","observation_id":"c1ae4073-91ce-4ef9-872b-211b48207d54","resolution":{"observed_at":"2026-08-01T15:02:42.057873Z","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":"2026-08-01T15:02:42.100521Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":8051,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:42.100521Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:333c3f2bd3c2f0e71866889bc33e1a74a52352f4ff49c9f6882e93e7f4518022","observation_id":"a2af5b93-3d96-4244-97d4-6e26e3f9550a","resolution":{"observed_at":"2026-08-01T15:02:42.100521Z","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":"2026-08-01T15:02:42.188802Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":8062,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:42.188802Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:3d760150d6fe049364422ebc4bc094a20780c8a2fe8cc9761d8fd3b0896eda1a","observation_id":"4cf1bc8d-b962-4b27-b612-fecef74fca63","resolution":{"observed_at":"2026-08-01T15:02:42.188802Z","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":"2026-08-01T15:02:42.327211Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":8073,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:42.327211Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:91675d90a74b142249c06e2eb1d63cde20075b196321fdded2e0eeffe2611246","observation_id":"09b00c8b-cac0-4990-8635-c06d0103a0df","resolution":{"observed_at":"2026-08-01T15:02:42.327211Z","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":"2026-08-01T15:02:42.478631Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":8084,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:42.478631Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:f8a766af05afe1a6b993919c854d896e0ecb37f8eb29ef626e5263ccdbefa4d4","observation_id":"5ede7e60-10df-4c14-b3da-da9e2e4d8af1","resolution":{"observed_at":"2026-08-01T15:02:42.478631Z","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":"2026-08-01T15:02:42.604007Z","title":"{DATASET_ROOT}","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring","version":1},"reference_index":8155,"source":"pdf_text","source_observed_at":"2026-08-01T15:02:42.604007Z"},"links":{"citing_paper":"/paper/2607.28098"},"observation_digest":"sha256:8260c78a8f53474dc921e9bf0834186fbe7ad8f09d82d8e91701c60780983788","observation_id":"51a496ac-e36a-491f-81e9-32f7b1b9df07","resolution":{"observed_at":"2026-08-01T15:02:42.604007Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.28098","last_updated":"2026-07-29T05:08:21Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-03T00:03:31.143635Z","submitted_at":"2026-07-29T05:08:21Z","title":"SciDataSailor: Deep Scientific Data Exploring"},"reference_resolution":{"displayed":77,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":1,"unresolved":75,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":77},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 77 of 77 outbound references and 2 inbound Pith citation observations for arXiv:2607.28098."}