{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SMJ4MA32Y4H3NHK7IGTVA7RZ4D","short_pith_number":"pith:SMJ4MA32","schema_version":"1.0","canonical_sha256":"9313c6037ac70fb69d5f41a7507e39e0dc5b9af36014415ab96b06804346763e","source":{"kind":"arxiv","id":"2601.06147","version":2},"attestation_state":"computed","paper":{"title":"LLM Flow Processes for Text-Conditioned Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"LLM regression outputs become better calibrated and trajectory-consistent when blended with a lightweight diffusion neural process.","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Felix Biggs, Samuel Willis","submitted_at":"2026-01-05T21:20:38Z","abstract_excerpt":"Recent work has demonstrated surprisingly good performance of pre-trained LLMs on regression tasks (for example, time-series prediction), with the ability to incorporate expert prior knowledge and the information contained in textual metadata. However we observe major error cascades even in short sequences < ~100 points; these models are also computationally intensive and difficult to parallelise. Marginal LLM predictions do not suffer this issue and are trivially parallelised, but can predict over-broad densities. To address this, we propose combining these densities with a lightweight (diffu"},"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":true},"canonical_record":{"source":{"id":"2601.06147","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-05T21:20:38Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"8cb6e12ecb0c442675d2fa76ab8a39b1a96505f8abaaccef6561ab8efbaf7cfb","abstract_canon_sha256":"91e1b2339f784b968fd167e9afade6a71377db857ba4a60b42866bebd568ec53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:45:12.061592Z","signature_b64":"Rb+Hf7Rof8csAw/sRZKz7DQ2ZCTyyl00Fl4frgpNDl0chczTvYi3+haU3x2erBeo7yVd9MJDhwd7OsfTFj0qDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9313c6037ac70fb69d5f41a7507e39e0dc5b9af36014415ab96b06804346763e","last_reissued_at":"2026-05-18T02:45:12.061099Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:45:12.061099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM Flow Processes for Text-Conditioned Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"LLM regression outputs become better calibrated and trajectory-consistent when blended with a lightweight diffusion neural process.","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Felix Biggs, Samuel Willis","submitted_at":"2026-01-05T21:20:38Z","abstract_excerpt":"Recent work has demonstrated surprisingly good performance of pre-trained LLMs on regression tasks (for example, time-series prediction), with the ability to incorporate expert prior knowledge and the information contained in textual metadata. However we observe major error cascades even in short sequences < ~100 points; these models are also computationally intensive and difficult to parallelise. Marginal LLM predictions do not suffer this issue and are trivially parallelised, but can predict over-broad densities. To address this, we propose combining these densities with a lightweight (diffu"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Combining these densities with a lightweight (diffusion-based) neural process leads to better-calibrated predictions overall, outputs locally consistent trajectories, and leads to text-conditioned function space selection in the meta-learner. We propose a gradient-free (and non-Monte Carlo) method for sampling from a product-of-experts of a score model and an 'expert' (here the LLM predictive densities).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that marginal LLM predictions can be convolved with a Gaussian in closed form, enabling the proposed gradient-free sampling method, and that the lightweight neural process can correct over-broad densities without introducing new inconsistencies or requiring extensive tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LLM densities fused with a diffusion neural process yield better-calibrated, locally consistent text-conditioned regression predictions plus a gradient-free product-of-experts sampler.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"LLM regression outputs become better calibrated and trajectory-consistent when blended with a lightweight diffusion neural process.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"79ba12074260a7eb5ce4d432bd19735a79bcbfffbbc3fb3cdefe6cffbc16057a"},"source":{"id":"2601.06147","kind":"arxiv","version":2},"verdict":{"id":"5f768847-73d6-40ef-a0c9-7eefc01e51b5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T17:14:53.058736Z","strongest_claim":"Combining these densities with a lightweight (diffusion-based) neural process leads to better-calibrated predictions overall, outputs locally consistent trajectories, and leads to text-conditioned function space selection in the meta-learner. We propose a gradient-free (and non-Monte Carlo) method for sampling from a product-of-experts of a score model and an 'expert' (here the LLM predictive densities).","one_line_summary":"LLM densities fused with a diffusion neural process yield better-calibrated, locally consistent text-conditioned regression predictions plus a gradient-free product-of-experts sampler.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that marginal LLM predictions can be convolved with a Gaussian in closed form, enabling the proposed gradient-free sampling method, and that the lightweight neural process can correct over-broad densities without introducing new inconsistencies or requiring extensive tuning.","pith_extraction_headline":"LLM regression outputs become better calibrated and trajectory-consistent when blended with a lightweight diffusion neural process."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ceae6dcd7ae15cbff9713562413a110ffcb3c4744957a497f9ac1421c952385d"},"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":"2601.06147","created_at":"2026-05-18T02:45:12.061173+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.06147v2","created_at":"2026-05-18T02:45:12.061173+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.06147","created_at":"2026-05-18T02:45:12.061173+00:00"},{"alias_kind":"pith_short_12","alias_value":"SMJ4MA32Y4H3","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"SMJ4MA32Y4H3NHK7","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"SMJ4MA32","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.21041","citing_title":"Conditioning Gaussian Processes on Almost Anything","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SMJ4MA32Y4H3NHK7IGTVA7RZ4D","json":"https://pith.science/pith/SMJ4MA32Y4H3NHK7IGTVA7RZ4D.json","graph_json":"https://pith.science/api/pith-number/SMJ4MA32Y4H3NHK7IGTVA7RZ4D/graph.json","events_json":"https://pith.science/api/pith-number/SMJ4MA32Y4H3NHK7IGTVA7RZ4D/events.json","paper":"https://pith.science/paper/SMJ4MA32"},"agent_actions":{"view_html":"https://pith.science/pith/SMJ4MA32Y4H3NHK7IGTVA7RZ4D","download_json":"https://pith.science/pith/SMJ4MA32Y4H3NHK7IGTVA7RZ4D.json","view_paper":"https://pith.science/paper/SMJ4MA32","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.06147&json=true","fetch_graph":"https://pith.science/api/pith-number/SMJ4MA32Y4H3NHK7IGTVA7RZ4D/graph.json","fetch_events":"https://pith.science/api/pith-number/SMJ4MA32Y4H3NHK7IGTVA7RZ4D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SMJ4MA32Y4H3NHK7IGTVA7RZ4D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SMJ4MA32Y4H3NHK7IGTVA7RZ4D/action/storage_attestation","attest_author":"https://pith.science/pith/SMJ4MA32Y4H3NHK7IGTVA7RZ4D/action/author_attestation","sign_citation":"https://pith.science/pith/SMJ4MA32Y4H3NHK7IGTVA7RZ4D/action/citation_signature","submit_replication":"https://pith.science/pith/SMJ4MA32Y4H3NHK7IGTVA7RZ4D/action/replication_record"}},"created_at":"2026-05-18T02:45:12.061173+00:00","updated_at":"2026-05-18T02:45:12.061173+00:00"}