{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:AWKGTRI63TI4NLF5BR4HDJRNE4","short_pith_number":"pith:AWKGTRI6","schema_version":"1.0","canonical_sha256":"059469c51edcd1c6acbd0c7871a62d27327cf401ba820744fe3cf50b2d13a94d","source":{"kind":"arxiv","id":"2207.12511","version":2},"attestation_state":"computed","paper":{"title":"Reconstructing Cosmological Initial Conditions from Late-Time Structure with Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["astro-ph.IM"],"primary_cat":"astro-ph.CO","authors_text":"Christopher J. Shallue, Daniel J. Eisenstein","submitted_at":"2022-07-25T20:14:22Z","abstract_excerpt":"We present a method to reconstruct the initial linear-regime matter density field from the late-time non-linearly evolved density field in which we channel the output of standard first-order reconstruction to a convolutional neural network (CNN). Our method shows dramatic improvement over the reconstruction of either component alone. We show why CNNs are not well-suited for reconstructing the initial density directly from the late-time density: CNNs are local models, but the relationship between initial and late-time density is not local. Our method leverages standard reconstruction as a prepr"},"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":"2207.12511","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"astro-ph.CO","submitted_at":"2022-07-25T20:14:22Z","cross_cats_sorted":["astro-ph.IM"],"title_canon_sha256":"b1aa85a1beea4c8adbbf9a48a4fb1d3e03e654521a65aad8648639b229de4b73","abstract_canon_sha256":"e0ed62115fdc7dab0d3511b1c6a2b0214d6c5aded14b2bb1be63bca3b4dcee5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:46.949429Z","signature_b64":"1FGqjvWl8rZ6oBMOhuZ2gO/d3hiHIF0npGQf+eWwarGxiP6ndNqU8DU5y+7NhejiqMO+KVdtJg+Pv13tDtbbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"059469c51edcd1c6acbd0c7871a62d27327cf401ba820744fe3cf50b2d13a94d","last_reissued_at":"2026-07-05T07:02:46.948906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:46.948906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reconstructing Cosmological Initial Conditions from Late-Time Structure with Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["astro-ph.IM"],"primary_cat":"astro-ph.CO","authors_text":"Christopher J. Shallue, Daniel J. Eisenstein","submitted_at":"2022-07-25T20:14:22Z","abstract_excerpt":"We present a method to reconstruct the initial linear-regime matter density field from the late-time non-linearly evolved density field in which we channel the output of standard first-order reconstruction to a convolutional neural network (CNN). Our method shows dramatic improvement over the reconstruction of either component alone. We show why CNNs are not well-suited for reconstructing the initial density directly from the late-time density: CNNs are local models, but the relationship between initial and late-time density is not local. Our method leverages standard reconstruction as a prepr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.12511","kind":"arxiv","version":2},"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/2207.12511/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":"2207.12511","created_at":"2026-07-05T07:02:46.948968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.12511v2","created_at":"2026-07-05T07:02:46.948968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.12511","created_at":"2026-07-05T07:02:46.948968+00:00"},{"alias_kind":"pith_short_12","alias_value":"AWKGTRI63TI4","created_at":"2026-07-05T07:02:46.948968+00:00"},{"alias_kind":"pith_short_16","alias_value":"AWKGTRI63TI4NLF5","created_at":"2026-07-05T07:02:46.948968+00:00"},{"alias_kind":"pith_short_8","alias_value":"AWKGTRI6","created_at":"2026-07-05T07:02:46.948968+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25385","citing_title":"On the Relation Between Field-Level Posteriors, Correlators, and their Likelihoods","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AWKGTRI63TI4NLF5BR4HDJRNE4","json":"https://pith.science/pith/AWKGTRI63TI4NLF5BR4HDJRNE4.json","graph_json":"https://pith.science/api/pith-number/AWKGTRI63TI4NLF5BR4HDJRNE4/graph.json","events_json":"https://pith.science/api/pith-number/AWKGTRI63TI4NLF5BR4HDJRNE4/events.json","paper":"https://pith.science/paper/AWKGTRI6"},"agent_actions":{"view_html":"https://pith.science/pith/AWKGTRI63TI4NLF5BR4HDJRNE4","download_json":"https://pith.science/pith/AWKGTRI63TI4NLF5BR4HDJRNE4.json","view_paper":"https://pith.science/paper/AWKGTRI6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.12511&json=true","fetch_graph":"https://pith.science/api/pith-number/AWKGTRI63TI4NLF5BR4HDJRNE4/graph.json","fetch_events":"https://pith.science/api/pith-number/AWKGTRI63TI4NLF5BR4HDJRNE4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AWKGTRI63TI4NLF5BR4HDJRNE4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AWKGTRI63TI4NLF5BR4HDJRNE4/action/storage_attestation","attest_author":"https://pith.science/pith/AWKGTRI63TI4NLF5BR4HDJRNE4/action/author_attestation","sign_citation":"https://pith.science/pith/AWKGTRI63TI4NLF5BR4HDJRNE4/action/citation_signature","submit_replication":"https://pith.science/pith/AWKGTRI63TI4NLF5BR4HDJRNE4/action/replication_record"}},"created_at":"2026-07-05T07:02:46.948968+00:00","updated_at":"2026-07-05T07:02:46.948968+00:00"}