{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NJQYTKEIQA5RHIMPFO4ARTK7KT","short_pith_number":"pith:NJQYTKEI","canonical_record":{"source":{"id":"2605.29580","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T08:24:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"09fe76a05a15c1342447ad7e6b7079e8b917c697d6bb3740946e95511db5ab8b","abstract_canon_sha256":"8c55892fde84da1c43947bb686374bd55a9a98d0a015724480791724e1d37845"},"schema_version":"1.0"},"canonical_sha256":"6a6189a888803b13a18f2bb808cd5f54c268467ad4eba816d1f85e9d0ca40664","source":{"kind":"arxiv","id":"2605.29580","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29580","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29580v1","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29580","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"pith_short_12","alias_value":"NJQYTKEIQA5R","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"pith_short_16","alias_value":"NJQYTKEIQA5RHIMP","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"pith_short_8","alias_value":"NJQYTKEI","created_at":"2026-05-29T01:05:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NJQYTKEIQA5RHIMPFO4ARTK7KT","target":"record","payload":{"canonical_record":{"source":{"id":"2605.29580","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T08:24:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"09fe76a05a15c1342447ad7e6b7079e8b917c697d6bb3740946e95511db5ab8b","abstract_canon_sha256":"8c55892fde84da1c43947bb686374bd55a9a98d0a015724480791724e1d37845"},"schema_version":"1.0"},"canonical_sha256":"6a6189a888803b13a18f2bb808cd5f54c268467ad4eba816d1f85e9d0ca40664","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:48.746643Z","signature_b64":"aVnxTDpFwzpMb0UNM0k8GzHy5VZJJWiVWo1eypwuoK0Bt8T7Ylp3uILhZgAY6KRzFNRcJaO4TCRgx/v+8hHcDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a6189a888803b13a18f2bb808cd5f54c268467ad4eba816d1f85e9d0ca40664","last_reissued_at":"2026-05-29T01:05:48.745776Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:48.745776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.29580","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T01:05:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wd6kHxGCr+c20cTSnn2AsQ9mj+CrMWbfeUB0BLSJLg/heCMPoeATsKnp0xwvJy1AbyzNa1FsPfGCkIa4lwHzBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T09:22:15.143463Z"},"content_sha256":"85c4cb3d7e88f1e60e86051aa840d7588fbb03ade05b92dc804a2da736bbf534","schema_version":"1.0","event_id":"sha256:85c4cb3d7e88f1e60e86051aa840d7588fbb03ade05b92dc804a2da736bbf534"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NJQYTKEIQA5RHIMPFO4ARTK7KT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Construction and Implications of Low-Loss Valleys in LoRA-based Bayesian Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Dold, David R\\\"ugamer, Emanuel Sommer, Julius Kobialka, Oliver D\\\"urr","submitted_at":"2026-05-28T08:24:45Z","abstract_excerpt":"While parameter-efficient fine-tuning methods like low-rank adaptation (LoRA) are standard for large language models, principled estimation of epistemic uncertainty remains challenging. Recent results in the LoRA regime suggest that discrete multi-mode approaches such as deep ensembles offer little benefit over single-mode methods. This contradicts broader observations in deep learning, where ensembling independent optima typically improves generalization, and linking these modes through continuous low-loss valleys further enhances Bayesian model averaging (BMA). Whether such structure exists "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29580","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.29580/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T01:05:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MCl5bXKBe04nlLqm9iIg8MsQrPtM8DFOAwjzJOelVR8y6rWpnVqIA84u/UD7uGEhtyx0M+EChE+5wgMIxkSwCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T09:22:15.143849Z"},"content_sha256":"9a19daa8607f37635c3e244783e5c89940a9b013f7ca04307d695f3164301854","schema_version":"1.0","event_id":"sha256:9a19daa8607f37635c3e244783e5c89940a9b013f7ca04307d695f3164301854"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NJQYTKEIQA5RHIMPFO4ARTK7KT/bundle.json","state_url":"https://pith.science/pith/NJQYTKEIQA5RHIMPFO4ARTK7KT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NJQYTKEIQA5RHIMPFO4ARTK7KT/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":"2026-06-05T09:22:15Z","links":{"resolver":"https://pith.science/pith/NJQYTKEIQA5RHIMPFO4ARTK7KT","bundle":"https://pith.science/pith/NJQYTKEIQA5RHIMPFO4ARTK7KT/bundle.json","state":"https://pith.science/pith/NJQYTKEIQA5RHIMPFO4ARTK7KT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NJQYTKEIQA5RHIMPFO4ARTK7KT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NJQYTKEIQA5RHIMPFO4ARTK7KT","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":"8c55892fde84da1c43947bb686374bd55a9a98d0a015724480791724e1d37845","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T08:24:45Z","title_canon_sha256":"09fe76a05a15c1342447ad7e6b7079e8b917c697d6bb3740946e95511db5ab8b"},"schema_version":"1.0","source":{"id":"2605.29580","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29580","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29580v1","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29580","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"pith_short_12","alias_value":"NJQYTKEIQA5R","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"pith_short_16","alias_value":"NJQYTKEIQA5RHIMP","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"pith_short_8","alias_value":"NJQYTKEI","created_at":"2026-05-29T01:05:48Z"}],"graph_snapshots":[{"event_id":"sha256:9a19daa8607f37635c3e244783e5c89940a9b013f7ca04307d695f3164301854","target":"graph","created_at":"2026-05-29T01:05:48Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.29580/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While parameter-efficient fine-tuning methods like low-rank adaptation (LoRA) are standard for large language models, principled estimation of epistemic uncertainty remains challenging. Recent results in the LoRA regime suggest that discrete multi-mode approaches such as deep ensembles offer little benefit over single-mode methods. This contradicts broader observations in deep learning, where ensembling independent optima typically improves generalization, and linking these modes through continuous low-loss valleys further enhances Bayesian model averaging (BMA). Whether such structure exists ","authors_text":"Daniel Dold, David R\\\"ugamer, Emanuel Sommer, Julius Kobialka, Oliver D\\\"urr","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T08:24:45Z","title":"On the Construction and Implications of Low-Loss Valleys in LoRA-based Bayesian Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29580","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:85c4cb3d7e88f1e60e86051aa840d7588fbb03ade05b92dc804a2da736bbf534","target":"record","created_at":"2026-05-29T01:05:48Z","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":"8c55892fde84da1c43947bb686374bd55a9a98d0a015724480791724e1d37845","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T08:24:45Z","title_canon_sha256":"09fe76a05a15c1342447ad7e6b7079e8b917c697d6bb3740946e95511db5ab8b"},"schema_version":"1.0","source":{"id":"2605.29580","kind":"arxiv","version":1}},"canonical_sha256":"6a6189a888803b13a18f2bb808cd5f54c268467ad4eba816d1f85e9d0ca40664","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a6189a888803b13a18f2bb808cd5f54c268467ad4eba816d1f85e9d0ca40664","first_computed_at":"2026-05-29T01:05:48.745776Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:48.745776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aVnxTDpFwzpMb0UNM0k8GzHy5VZJJWiVWo1eypwuoK0Bt8T7Ylp3uILhZgAY6KRzFNRcJaO4TCRgx/v+8hHcDA==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:48.746643Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29580","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85c4cb3d7e88f1e60e86051aa840d7588fbb03ade05b92dc804a2da736bbf534","sha256:9a19daa8607f37635c3e244783e5c89940a9b013f7ca04307d695f3164301854"],"state_sha256":"2c834fb34e1b7b08105cdf76950dea106589dba01300439b26476b19a338a981"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N+GSDYo+j4+imD5Jz/1pghxYFcYCdou8F/Hj9OSgKnqEF5/mLeI3bHSJh7AaOOyerQ8Y2/E7To9xUxP7UkMZAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T09:22:15.145978Z","bundle_sha256":"7b3984d83e16ec332e61fd5ce24dd64e45efbc1e18dd2bb972cac95397fff260"}}