{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VEROC7JLHQIHPH5EZVQD42OGX5","short_pith_number":"pith:VEROC7JL","schema_version":"1.0","canonical_sha256":"a922e17d2b3c10779fa4cd603e69c6bf7f7a1ce7661307c4ef93ef8478fab300","source":{"kind":"arxiv","id":"2604.04340","version":3},"attestation_state":"computed","paper":{"title":"Replacing Gaussian Processes with Neural Networks in Pulsar Timing Array Inference of the Gravitational-Wave Background","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Probabilistic neural networks can replace Gaussian process interpolators in pulsar timing array analyses of nanohertz gravitational wave backgrounds, producing matching posteriors at lower computational cost.","cross_cats":["physics.data-an"],"primary_cat":"astro-ph.CO","authors_text":"Chris Gordon, Shreyas Tiruvaskar","submitted_at":"2026-04-06T01:18:42Z","abstract_excerpt":"Bayesian inference of nanohertz gravitational-wave background models in pulsar timing array analyses often relies on Gaussian-process interpolators to avoid repeated, computationally expensive strain-spectrum calculations. However, Gaussian-process training becomes a bottleneck for large training sets. We test whether probabilistic neural networks can replace Gaussian processes in this role for both a self-interacting dark matter model and a phenomenological environmental model. We find that neural networks recover consistent posteriors while significantly reducing both training and Markov cha"},"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":"2604.04340","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"astro-ph.CO","submitted_at":"2026-04-06T01:18:42Z","cross_cats_sorted":["physics.data-an"],"title_canon_sha256":"abcbd944433e96746cc934e30bed22b08dcf2e209c7e7ddae0cb8ef39fdc65e2","abstract_canon_sha256":"ff65847a213265ce776fcf11d93585b13ffe9155fb0313bc0c5d795d067a5c9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:39.122633Z","signature_b64":"zocG8OCM51LC3hNBpQj/+PiF0AudjQNx0OpVxidG0qF2sp6330Kkn+kjFhSacgSTXXwREs1o/TnjKGeWQKYMBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a922e17d2b3c10779fa4cd603e69c6bf7f7a1ce7661307c4ef93ef8478fab300","last_reissued_at":"2026-06-01T01:02:39.121282Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:39.121282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Replacing Gaussian Processes with Neural Networks in Pulsar Timing Array Inference of the Gravitational-Wave Background","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Probabilistic neural networks can replace Gaussian process interpolators in pulsar timing array analyses of nanohertz gravitational wave backgrounds, producing matching posteriors at lower computational cost.","cross_cats":["physics.data-an"],"primary_cat":"astro-ph.CO","authors_text":"Chris Gordon, Shreyas Tiruvaskar","submitted_at":"2026-04-06T01:18:42Z","abstract_excerpt":"Bayesian inference of nanohertz gravitational-wave background models in pulsar timing array analyses often relies on Gaussian-process interpolators to avoid repeated, computationally expensive strain-spectrum calculations. However, Gaussian-process training becomes a bottleneck for large training sets. We test whether probabilistic neural networks can replace Gaussian processes in this role for both a self-interacting dark matter model and a phenomenological environmental model. We find that neural networks recover consistent posteriors while significantly reducing both training and Markov cha"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We find that neural networks recover consistent posteriors while significantly reducing both training and Markov chain Monte Carlo runtime, with the largest gains for the more computationally demanding model.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The neural networks, once trained on a finite set of strain-spectrum evaluations, accurately generalize across the full prior volume of the target models without introducing systematic biases into the recovered posteriors.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Probabilistic neural networks recover consistent posteriors to Gaussian processes in PTA gravitational-wave background inference while substantially reducing training and MCMC runtime.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Probabilistic neural networks can replace Gaussian process interpolators in pulsar timing array analyses of nanohertz gravitational wave backgrounds, producing matching posteriors at lower computational cost.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"75cb6209a2d03bccfe7954b731c9b780eae72c48e902fcfb042cd838213d4dfe"},"source":{"id":"2604.04340","kind":"arxiv","version":3},"verdict":{"id":"2875f9e5-ca17-4231-8a94-d664be8ef748","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T20:24:52.576017Z","strongest_claim":"We find that neural networks recover consistent posteriors while significantly reducing both training and Markov chain Monte Carlo runtime, with the largest gains for the more computationally demanding model.","one_line_summary":"Probabilistic neural networks recover consistent posteriors to Gaussian processes in PTA gravitational-wave background inference while substantially reducing training and MCMC runtime.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The neural networks, once trained on a finite set of strain-spectrum evaluations, accurately generalize across the full prior volume of the target models without introducing systematic biases into the recovered posteriors.","pith_extraction_headline":"Probabilistic neural networks can replace Gaussian process interpolators in pulsar timing array analyses of nanohertz gravitational wave backgrounds, producing matching posteriors at lower computational cost."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.04340/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":"2604.04340","created_at":"2026-06-01T01:02:39.121428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.04340v3","created_at":"2026-06-01T01:02:39.121428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.04340","created_at":"2026-06-01T01:02:39.121428+00:00"},{"alias_kind":"pith_short_12","alias_value":"VEROC7JLHQIH","created_at":"2026-06-01T01:02:39.121428+00:00"},{"alias_kind":"pith_short_16","alias_value":"VEROC7JLHQIHPH5E","created_at":"2026-06-01T01:02:39.121428+00:00"},{"alias_kind":"pith_short_8","alias_value":"VEROC7JL","created_at":"2026-06-01T01:02:39.121428+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.04340","citing_title":"Replacing Gaussian Processes with Neural Networks in Pulsar Timing Array Inference of the Gravitational-Wave Background","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VEROC7JLHQIHPH5EZVQD42OGX5","json":"https://pith.science/pith/VEROC7JLHQIHPH5EZVQD42OGX5.json","graph_json":"https://pith.science/api/pith-number/VEROC7JLHQIHPH5EZVQD42OGX5/graph.json","events_json":"https://pith.science/api/pith-number/VEROC7JLHQIHPH5EZVQD42OGX5/events.json","paper":"https://pith.science/paper/VEROC7JL"},"agent_actions":{"view_html":"https://pith.science/pith/VEROC7JLHQIHPH5EZVQD42OGX5","download_json":"https://pith.science/pith/VEROC7JLHQIHPH5EZVQD42OGX5.json","view_paper":"https://pith.science/paper/VEROC7JL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.04340&json=true","fetch_graph":"https://pith.science/api/pith-number/VEROC7JLHQIHPH5EZVQD42OGX5/graph.json","fetch_events":"https://pith.science/api/pith-number/VEROC7JLHQIHPH5EZVQD42OGX5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VEROC7JLHQIHPH5EZVQD42OGX5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VEROC7JLHQIHPH5EZVQD42OGX5/action/storage_attestation","attest_author":"https://pith.science/pith/VEROC7JLHQIHPH5EZVQD42OGX5/action/author_attestation","sign_citation":"https://pith.science/pith/VEROC7JLHQIHPH5EZVQD42OGX5/action/citation_signature","submit_replication":"https://pith.science/pith/VEROC7JLHQIHPH5EZVQD42OGX5/action/replication_record"}},"created_at":"2026-06-01T01:02:39.121428+00:00","updated_at":"2026-06-01T01:02:39.121428+00:00"}