{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BE3XEHDFIO333TGJSXD235QPQH","short_pith_number":"pith:BE3XEHDF","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"},"canonical_sha256":"0937721c6543b7bdccc995c7adf60f81f98e9fc1b80eb06c5ff04ffcaeacc4cd","source":{"kind":"arxiv","id":"2602.08920","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.08920","created_at":"2026-05-18T03:09:23Z"},{"alias_kind":"arxiv_version","alias_value":"2602.08920v2","created_at":"2026-05-18T03:09:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.08920","created_at":"2026-05-18T03:09:23Z"},{"alias_kind":"pith_short_12","alias_value":"BE3XEHDFIO33","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"BE3XEHDFIO333TGJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"BE3XEHDF","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BE3XEHDFIO333TGJSXD235QPQH","target":"record","payload":{"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"},"canonical_sha256":"0937721c6543b7bdccc995c7adf60f81f98e9fc1b80eb06c5ff04ffcaeacc4cd","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"},"source_kind":"arxiv","source_id":"2602.08920","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":"2026-05-18T03:09:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KuD63MEs9MkMo75w0Ip+r5yAMlgbUzmR7aqo7DB7vw4O2ibJhtWopykO8HdeV2v95Tri9x9ADuxAZ/9VIsVFAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T16:15:20.544351Z"},"content_sha256":"8a77143ae4d4c24a5fb009ad35f9f5e670fe0025ed68860af78034987b4996ad","schema_version":"1.0","event_id":"sha256:8a77143ae4d4c24a5fb009ad35f9f5e670fe0025ed68860af78034987b4996ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BE3XEHDFIO333TGJSXD235QPQH","target":"graph","payload":{"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"},"verdict_id":"4adc9c85-68b9-4c0d-9495-ac42867f84bf"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BlAmAS0vNqfJJHNolIhvtFHqzPCskux9IZWkWDQTL1ZceHA2UAPvCmEciL2jxdPTcI+81sFpc+FbCET5i7uCBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T16:15:20.544795Z"},"content_sha256":"2cbe8116f8965505e119f3110b97f90a0820b56547bff12ce38218f3cabf9ea7","schema_version":"1.0","event_id":"sha256:2cbe8116f8965505e119f3110b97f90a0820b56547bff12ce38218f3cabf9ea7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BE3XEHDFIO333TGJSXD235QPQH/bundle.json","state_url":"https://pith.science/pith/BE3XEHDFIO333TGJSXD235QPQH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BE3XEHDFIO333TGJSXD235QPQH/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":"2026-06-01T16:15:20Z","links":{"resolver":"https://pith.science/pith/BE3XEHDFIO333TGJSXD235QPQH","bundle":"https://pith.science/pith/BE3XEHDFIO333TGJSXD235QPQH/bundle.json","state":"https://pith.science/pith/BE3XEHDFIO333TGJSXD235QPQH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BE3XEHDFIO333TGJSXD235QPQH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BE3XEHDFIO333TGJSXD235QPQH","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":"3b38d6ee4539924e9dff3f78f5919e8b3a2aa8934f8050ecaae12b555d80e742","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-09T17:24:47Z","title_canon_sha256":"276eeb634f74cbb01273749e5037273208011d522f29e72ffc205b22f4a5bf9b"},"schema_version":"1.0","source":{"id":"2602.08920","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.08920","created_at":"2026-05-18T03:09:23Z"},{"alias_kind":"arxiv_version","alias_value":"2602.08920v2","created_at":"2026-05-18T03:09:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.08920","created_at":"2026-05-18T03:09:23Z"},{"alias_kind":"pith_short_12","alias_value":"BE3XEHDFIO33","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"BE3XEHDFIO333TGJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"BE3XEHDF","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:2cbe8116f8965505e119f3110b97f90a0820b56547bff12ce38218f3cabf9ea7","target":"graph","created_at":"2026-05-18T03:09:23Z","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":"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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Diffusion-inspired probabilistic mappings enable principled uncertainty propagation through pre-trained transformer layers without degrading accuracy."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Modeling each transformer block as a probabilistic mapping creates a diffusion-like path that propagates representation uncertainty without changing predictions."}],"snapshot_sha256":"6161b6dd8c8fddb1cf746345ccdb39cc289ed57445c1a34a517c424c7b44105f"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0c33b46ca9602e2637640ab2ffa2bb2450aae2f8e4bee5ed7771a040d80460cc"},"paper":{"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","authors_text":"Bryan Kian Hsiang Low, Manh Cuong Dao, Phi Le Nguyen, Quang Hung Pham, Thao Nguyen Truong, Trong Nghia Hoang","cross_cats":[],"headline":"Modeling each transformer block as a probabilistic mapping creates a diffusion-like path that propagates representation uncertainty without changing predictions.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-09T17:24:47Z","title":"Diffusion-Inspired Reconfiguration of Transformers for Uncertainty Calibration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.08920","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T05:26:55.547267Z","id":"4adc9c85-68b9-4c0d-9495-ac42867f84bf","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Modeling each transformer block as a probabilistic mapping creates a diffusion-like path that propagates representation uncertainty without changing predictions.","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.","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."}},"verdict_id":"4adc9c85-68b9-4c0d-9495-ac42867f84bf"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8a77143ae4d4c24a5fb009ad35f9f5e670fe0025ed68860af78034987b4996ad","target":"record","created_at":"2026-05-18T03:09:23Z","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":"3b38d6ee4539924e9dff3f78f5919e8b3a2aa8934f8050ecaae12b555d80e742","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-09T17:24:47Z","title_canon_sha256":"276eeb634f74cbb01273749e5037273208011d522f29e72ffc205b22f4a5bf9b"},"schema_version":"1.0","source":{"id":"2602.08920","kind":"arxiv","version":2}},"canonical_sha256":"0937721c6543b7bdccc995c7adf60f81f98e9fc1b80eb06c5ff04ffcaeacc4cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0937721c6543b7bdccc995c7adf60f81f98e9fc1b80eb06c5ff04ffcaeacc4cd","first_computed_at":"2026-05-18T03:09:23.692577Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:23.692577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5hDohrUCR4H37uDHfS64Wd8YEHTiy6phfNHPvViJ72IQ4XfROGaQLe84sJbWIR6nbHCChMgrjkeYkOL5YFjKBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:23.693301Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.08920","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a77143ae4d4c24a5fb009ad35f9f5e670fe0025ed68860af78034987b4996ad","sha256:2cbe8116f8965505e119f3110b97f90a0820b56547bff12ce38218f3cabf9ea7"],"state_sha256":"b1765dfb17b4404c3bfd13856f69caed1dc40710268b50117775be0fe7e8933b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3eF9Wo71NY5zvHQ99sZ7ddhlXNesxnnDJfm4+bDt9B1JHAcpl0IUvXVQRnyC/vtlCNR0mtrp7QDEh/TPJxJMAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T16:15:20.547024Z","bundle_sha256":"47207b50ea6c71c76558e7a635a9bb48acd5b6e483128f2b94d31b27f06ec76c"}}