{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SMJ4MA32Y4H3NHK7IGTVA7RZ4D","short_pith_number":"pith:SMJ4MA32","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"},"canonical_sha256":"9313c6037ac70fb69d5f41a7507e39e0dc5b9af36014415ab96b06804346763e","source":{"kind":"arxiv","id":"2601.06147","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.06147","created_at":"2026-05-18T02:45:12Z"},{"alias_kind":"arxiv_version","alias_value":"2601.06147v2","created_at":"2026-05-18T02:45:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.06147","created_at":"2026-05-18T02:45:12Z"},{"alias_kind":"pith_short_12","alias_value":"SMJ4MA32Y4H3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"SMJ4MA32Y4H3NHK7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"SMJ4MA32","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SMJ4MA32Y4H3NHK7IGTVA7RZ4D","target":"record","payload":{"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"},"canonical_sha256":"9313c6037ac70fb69d5f41a7507e39e0dc5b9af36014415ab96b06804346763e","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"},"source_kind":"arxiv","source_id":"2601.06147","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:45:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S51NJrBSBiYoxL5z7tR7yQmsP5kJ2oqHSnUo2cLUxvPfWaku+/5eIdougR1XJ4R8vpLZU/nAEWxFou5lKAtKAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T04:15:39.775590Z"},"content_sha256":"73cc811c7efbbec03a7116438517b4a787dd91b7f285594c81cce304922024ca","schema_version":"1.0","event_id":"sha256:73cc811c7efbbec03a7116438517b4a787dd91b7f285594c81cce304922024ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SMJ4MA32Y4H3NHK7IGTVA7RZ4D","target":"graph","payload":{"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"},"verdict_id":"5f768847-73d6-40ef-a0c9-7eefc01e51b5"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:45:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1+brYKA7vnbHB9M+LuhAuBnTci7cQuqH0Ow5W9PlpMSPTpUGHO2rKRfz2ubvv3PkVpnAUsVsOKja3VaqqWJDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T04:15:39.776034Z"},"content_sha256":"c57d05719e0529746c4709ee5584fed3ef2bfc8c98509e781dfdcda665df1785","schema_version":"1.0","event_id":"sha256:c57d05719e0529746c4709ee5584fed3ef2bfc8c98509e781dfdcda665df1785"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SMJ4MA32Y4H3NHK7IGTVA7RZ4D/bundle.json","state_url":"https://pith.science/pith/SMJ4MA32Y4H3NHK7IGTVA7RZ4D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SMJ4MA32Y4H3NHK7IGTVA7RZ4D/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T04:15:39Z","links":{"resolver":"https://pith.science/pith/SMJ4MA32Y4H3NHK7IGTVA7RZ4D","bundle":"https://pith.science/pith/SMJ4MA32Y4H3NHK7IGTVA7RZ4D/bundle.json","state":"https://pith.science/pith/SMJ4MA32Y4H3NHK7IGTVA7RZ4D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SMJ4MA32Y4H3NHK7IGTVA7RZ4D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SMJ4MA32Y4H3NHK7IGTVA7RZ4D","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"91e1b2339f784b968fd167e9afade6a71377db857ba4a60b42866bebd568ec53","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-05T21:20:38Z","title_canon_sha256":"8cb6e12ecb0c442675d2fa76ab8a39b1a96505f8abaaccef6561ab8efbaf7cfb"},"schema_version":"1.0","source":{"id":"2601.06147","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.06147","created_at":"2026-05-18T02:45:12Z"},{"alias_kind":"arxiv_version","alias_value":"2601.06147v2","created_at":"2026-05-18T02:45:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.06147","created_at":"2026-05-18T02:45:12Z"},{"alias_kind":"pith_short_12","alias_value":"SMJ4MA32Y4H3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"SMJ4MA32Y4H3NHK7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"SMJ4MA32","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:c57d05719e0529746c4709ee5584fed3ef2bfc8c98509e781dfdcda665df1785","target":"graph","created_at":"2026-05-18T02:45:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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)."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"LLM regression outputs become better calibrated and trajectory-consistent when blended with a lightweight diffusion neural process."}],"snapshot_sha256":"79ba12074260a7eb5ce4d432bd19735a79bcbfffbbc3fb3cdefe6cffbc16057a"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ceae6dcd7ae15cbff9713562413a110ffcb3c4744957a497f9ac1421c952385d"},"paper":{"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","authors_text":"Felix Biggs, Samuel Willis","cross_cats":["cs.CL","stat.ML"],"headline":"LLM regression outputs become better calibrated and trajectory-consistent when blended with a lightweight diffusion neural process.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-05T21:20:38Z","title":"LLM Flow Processes for Text-Conditioned Regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.06147","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T17:14:53.058736Z","id":"5f768847-73d6-40ef-a0c9-7eefc01e51b5","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"LLM regression outputs become better calibrated and trajectory-consistent when blended with a lightweight diffusion neural process.","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).","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."}},"verdict_id":"5f768847-73d6-40ef-a0c9-7eefc01e51b5"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:73cc811c7efbbec03a7116438517b4a787dd91b7f285594c81cce304922024ca","target":"record","created_at":"2026-05-18T02:45:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"91e1b2339f784b968fd167e9afade6a71377db857ba4a60b42866bebd568ec53","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-05T21:20:38Z","title_canon_sha256":"8cb6e12ecb0c442675d2fa76ab8a39b1a96505f8abaaccef6561ab8efbaf7cfb"},"schema_version":"1.0","source":{"id":"2601.06147","kind":"arxiv","version":2}},"canonical_sha256":"9313c6037ac70fb69d5f41a7507e39e0dc5b9af36014415ab96b06804346763e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9313c6037ac70fb69d5f41a7507e39e0dc5b9af36014415ab96b06804346763e","first_computed_at":"2026-05-18T02:45:12.061099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:45:12.061099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rb+Hf7Rof8csAw/sRZKz7DQ2ZCTyyl00Fl4frgpNDl0chczTvYi3+haU3x2erBeo7yVd9MJDhwd7OsfTFj0qDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:45:12.061592Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.06147","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73cc811c7efbbec03a7116438517b4a787dd91b7f285594c81cce304922024ca","sha256:c57d05719e0529746c4709ee5584fed3ef2bfc8c98509e781dfdcda665df1785"],"state_sha256":"52bc003bc618a20cd1988e74cecdc09db93557d75f3dccae99ffff1a36727d8e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9mH+XMV13RyuakLRZyF/ACGE9oLuOZQsKGAtcEG42NOu8UpDZJ61aTDGp4GI6LsvxLn98ogcYm5UTNaX5puBDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T04:15:39.778587Z","bundle_sha256":"85c86bc4f62e2e8be214d2dcf4e4cf688102408b34a5bd4dd704f8da2f9e41c7"}}