{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2DMFSJYER5KKDGB6OARVYA6GZT","short_pith_number":"pith:2DMFSJYE","schema_version":"1.0","canonical_sha256":"d0d85927048f54a1983e70235c03c6ccfcf593f846c9a4889de3ea0ca882f61e","source":{"kind":"arxiv","id":"2607.22824","version":1},"attestation_state":"computed","paper":{"title":"Agentic Autoresearch for CT Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"physics.med-ph","authors_text":"Amber Simpson, Andreas Maier, Lucas Kachelriess, Moritz Zaiss, Siming Bayer, Yan Xia, Yixing Huang","submitted_at":"2026-07-24T18:03:21Z","abstract_excerpt":"Comparing CT reconstruction methods fairly is labor-intensive and largely manual, and many benchmarks use idealized data. We ask whether a large language model (LLM) agent can do the labor of reconstruction research on its own, and whether a ranking measured on ideal data predicts behavior under realistic noise.\n  We built an agentic loop: the agent edits a solver, runs a short cluster job, reads one frozen metric, and revises. The metric is a calibrated headroom score against the FBP baseline, inside the field of view; every method shares the same differentiable fan-beam projector. We benchma"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.22824","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.med-ph","submitted_at":"2026-07-24T18:03:21Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"cf5561e519162bf8ea665d7426a1eb88a6e0a3516941c05593b0cc8027c51bca","abstract_canon_sha256":"404aa16dbdef91fb7b267bff936953b5088d88ba6d5ab2fddb86c73161a93d44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:21:56.375564Z","signature_b64":"8LfwgfqulW4qNYPk/GgOPi+LqtUCTIVIdXAGQ7ywptwQxryF9gAgbz5P5sRAkcrrL4bZkT0C/QA/OnqnYgE7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0d85927048f54a1983e70235c03c6ccfcf593f846c9a4889de3ea0ca882f61e","last_reissued_at":"2026-07-28T00:21:56.374543Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:21:56.374543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agentic Autoresearch for CT Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"physics.med-ph","authors_text":"Amber Simpson, Andreas Maier, Lucas Kachelriess, Moritz Zaiss, Siming Bayer, Yan Xia, Yixing Huang","submitted_at":"2026-07-24T18:03:21Z","abstract_excerpt":"Comparing CT reconstruction methods fairly is labor-intensive and largely manual, and many benchmarks use idealized data. We ask whether a large language model (LLM) agent can do the labor of reconstruction research on its own, and whether a ranking measured on ideal data predicts behavior under realistic noise.\n  We built an agentic loop: the agent edits a solver, runs a short cluster job, reads one frozen metric, and revises. The metric is a calibrated headroom score against the FBP baseline, inside the field of view; every method shares the same differentiable fan-beam projector. We benchma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22824","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.22824/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.22824","created_at":"2026-07-28T00:21:56.374984+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22824v1","created_at":"2026-07-28T00:21:56.374984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22824","created_at":"2026-07-28T00:21:56.374984+00:00"},{"alias_kind":"pith_short_12","alias_value":"2DMFSJYER5KK","created_at":"2026-07-28T00:21:56.374984+00:00"},{"alias_kind":"pith_short_16","alias_value":"2DMFSJYER5KKDGB6","created_at":"2026-07-28T00:21:56.374984+00:00"},{"alias_kind":"pith_short_8","alias_value":"2DMFSJYE","created_at":"2026-07-28T00:21:56.374984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2DMFSJYER5KKDGB6OARVYA6GZT","json":"https://pith.science/pith/2DMFSJYER5KKDGB6OARVYA6GZT.json","graph_json":"https://pith.science/api/pith-number/2DMFSJYER5KKDGB6OARVYA6GZT/graph.json","events_json":"https://pith.science/api/pith-number/2DMFSJYER5KKDGB6OARVYA6GZT/events.json","paper":"https://pith.science/paper/2DMFSJYE"},"agent_actions":{"view_html":"https://pith.science/pith/2DMFSJYER5KKDGB6OARVYA6GZT","download_json":"https://pith.science/pith/2DMFSJYER5KKDGB6OARVYA6GZT.json","view_paper":"https://pith.science/paper/2DMFSJYE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22824&json=true","fetch_graph":"https://pith.science/api/pith-number/2DMFSJYER5KKDGB6OARVYA6GZT/graph.json","fetch_events":"https://pith.science/api/pith-number/2DMFSJYER5KKDGB6OARVYA6GZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2DMFSJYER5KKDGB6OARVYA6GZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2DMFSJYER5KKDGB6OARVYA6GZT/action/storage_attestation","attest_author":"https://pith.science/pith/2DMFSJYER5KKDGB6OARVYA6GZT/action/author_attestation","sign_citation":"https://pith.science/pith/2DMFSJYER5KKDGB6OARVYA6GZT/action/citation_signature","submit_replication":"https://pith.science/pith/2DMFSJYER5KKDGB6OARVYA6GZT/action/replication_record"}},"created_at":"2026-07-28T00:21:56.374984+00:00","updated_at":"2026-07-28T00:21:56.374984+00:00"}