{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BE3XEHDFIO333TGJSXD235QPQH","short_pith_number":"pith:BE3XEHDF","schema_version":"1.0","canonical_sha256":"0937721c6543b7bdccc995c7adf60f81f98e9fc1b80eb06c5ff04ffcaeacc4cd","source":{"kind":"arxiv","id":"2602.08920","version":2},"attestation_state":"computed","paper":{"title":"Diffusion-Inspired Reconfiguration of Transformers for Uncertainty Calibration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Modeling each transformer block as a probabilistic mapping creates a diffusion-like path that propagates representation uncertainty without changing predictions.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bryan Kian Hsiang Low, Manh Cuong Dao, Phi Le Nguyen, Quang Hung Pham, Thao Nguyen Truong, Trong Nghia Hoang","submitted_at":"2026-02-09T17:24:47Z","abstract_excerpt":"Uncertainty calibration in pre-trained transformers is critical for their reliable deployment in risk-sensitive applications. Yet, most existing pre-trained transformers do not have a principled mechanism for uncertainty propagation through their feature transformation stack. In this work, we propose a diffusion-inspired reconfiguration of transformers in which each feature transformation block is modeled as a probabilistic mapping. Composing these probabilistic mappings reveals a probability path that mimics the structure of a diffusion process, transporting data mass from the input distribut"},"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":"2602.08920","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-09T17:24:47Z","cross_cats_sorted":[],"title_canon_sha256":"276eeb634f74cbb01273749e5037273208011d522f29e72ffc205b22f4a5bf9b","abstract_canon_sha256":"3b38d6ee4539924e9dff3f78f5919e8b3a2aa8934f8050ecaae12b555d80e742"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:23.693301Z","signature_b64":"5hDohrUCR4H37uDHfS64Wd8YEHTiy6phfNHPvViJ72IQ4XfROGaQLe84sJbWIR6nbHCChMgrjkeYkOL5YFjKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0937721c6543b7bdccc995c7adf60f81f98e9fc1b80eb06c5ff04ffcaeacc4cd","last_reissued_at":"2026-05-18T03:09:23.692577Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:23.692577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion-Inspired Reconfiguration of Transformers for Uncertainty Calibration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Modeling each transformer block as a probabilistic mapping creates a diffusion-like path that propagates representation uncertainty without changing predictions.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bryan Kian Hsiang Low, Manh Cuong Dao, Phi Le Nguyen, Quang Hung Pham, Thao Nguyen Truong, Trong Nghia Hoang","submitted_at":"2026-02-09T17:24:47Z","abstract_excerpt":"Uncertainty calibration in pre-trained transformers is critical for their reliable deployment in risk-sensitive applications. Yet, most existing pre-trained transformers do not have a principled mechanism for uncertainty propagation through their feature transformation stack. In this work, we propose a diffusion-inspired reconfiguration of transformers in which each feature transformation block is modeled as a probabilistic mapping. Composing these probabilistic mappings reveals a probability path that mimics the structure of a diffusion process, transporting data mass from the input distribut"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Composing these probabilistic mappings reveals a probability path that mimics the structure of a diffusion process, transporting data mass from the input distribution to the pre-trained feature distribution. This probability path can then be recompiled on a diffusion process with a unified transition model to enable principled propagation of representation uncertainty throughout the pre-trained model's architecture while maintaining its original predictive performance.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That modeling each feature transformation block as a probabilistic mapping accurately captures and propagates representation uncertainty without introducing systematic biases or changing the model's learned behavior in unintended ways.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Diffusion-inspired probabilistic mappings enable principled uncertainty propagation through pre-trained transformer layers without degrading accuracy.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Modeling each transformer block as a probabilistic mapping creates a diffusion-like path that propagates representation uncertainty without changing predictions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"6161b6dd8c8fddb1cf746345ccdb39cc289ed57445c1a34a517c424c7b44105f"},"source":{"id":"2602.08920","kind":"arxiv","version":2},"verdict":{"id":"4adc9c85-68b9-4c0d-9495-ac42867f84bf","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T05:26:55.547267Z","strongest_claim":"Composing these probabilistic mappings reveals a probability path that mimics the structure of a diffusion process, transporting data mass from the input distribution to the pre-trained feature distribution. This probability path can then be recompiled on a diffusion process with a unified transition model to enable principled propagation of representation uncertainty throughout the pre-trained model's architecture while maintaining its original predictive performance.","one_line_summary":"Diffusion-inspired probabilistic mappings enable principled uncertainty propagation through pre-trained transformer layers without degrading accuracy.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That modeling each feature transformation block as a probabilistic mapping accurately captures and propagates representation uncertainty without introducing systematic biases or changing the model's learned behavior in unintended ways.","pith_extraction_headline":"Modeling each transformer block as a probabilistic mapping creates a diffusion-like path that propagates representation uncertainty without changing predictions."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0c33b46ca9602e2637640ab2ffa2bb2450aae2f8e4bee5ed7771a040d80460cc"},"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":"2602.08920","created_at":"2026-05-18T03:09:23.692684+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.08920v2","created_at":"2026-05-18T03:09:23.692684+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.08920","created_at":"2026-05-18T03:09:23.692684+00:00"},{"alias_kind":"pith_short_12","alias_value":"BE3XEHDFIO33","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"BE3XEHDFIO333TGJ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"BE3XEHDF","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BE3XEHDFIO333TGJSXD235QPQH","json":"https://pith.science/pith/BE3XEHDFIO333TGJSXD235QPQH.json","graph_json":"https://pith.science/api/pith-number/BE3XEHDFIO333TGJSXD235QPQH/graph.json","events_json":"https://pith.science/api/pith-number/BE3XEHDFIO333TGJSXD235QPQH/events.json","paper":"https://pith.science/paper/BE3XEHDF"},"agent_actions":{"view_html":"https://pith.science/pith/BE3XEHDFIO333TGJSXD235QPQH","download_json":"https://pith.science/pith/BE3XEHDFIO333TGJSXD235QPQH.json","view_paper":"https://pith.science/paper/BE3XEHDF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.08920&json=true","fetch_graph":"https://pith.science/api/pith-number/BE3XEHDFIO333TGJSXD235QPQH/graph.json","fetch_events":"https://pith.science/api/pith-number/BE3XEHDFIO333TGJSXD235QPQH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BE3XEHDFIO333TGJSXD235QPQH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BE3XEHDFIO333TGJSXD235QPQH/action/storage_attestation","attest_author":"https://pith.science/pith/BE3XEHDFIO333TGJSXD235QPQH/action/author_attestation","sign_citation":"https://pith.science/pith/BE3XEHDFIO333TGJSXD235QPQH/action/citation_signature","submit_replication":"https://pith.science/pith/BE3XEHDFIO333TGJSXD235QPQH/action/replication_record"}},"created_at":"2026-05-18T03:09:23.692684+00:00","updated_at":"2026-05-18T03:09:23.692684+00:00"}