{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3A3NSDLDDAURSZEKB2WUDWSEKN","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":"08982f296d3b7011c8b7b2fdf6bec4c5c580d305c1cc7386049148fae213f8dc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T13:47:11Z","title_canon_sha256":"71ca1095213f9418fa258a120300c4beee4c761bb6f28c94731d6b266582527e"},"schema_version":"1.0","source":{"id":"2605.13538","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13538","created_at":"2026-05-18T02:44:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13538v1","created_at":"2026-05-18T02:44:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13538","created_at":"2026-05-18T02:44:24Z"},{"alias_kind":"pith_short_12","alias_value":"3A3NSDLDDAUR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"3A3NSDLDDAURSZEK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"3A3NSDLD","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:9aeb073cd6a4ee78316646a7a496d8c3908964698b74e9f10aa92be23816e870","target":"graph","created_at":"2026-05-18T02:44:24Z","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":"With the fix, 482/482 unique Bonsai-1.7B calls succeed (no echoes) and produce locale-correct surrogates, although the SLM still copies from a small same-locale demonstration pool - a residual narrowness we quantify."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the observed NER performance gap is caused primarily by reduced variety in SLM outputs rather than by other unmeasured differences in the 160/40 subset or by the choice of XGLM-564M as the multilingual evaluator."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Locale-conditioned rotating few-shot prompting eliminates demonstration regurgitation in 1.7B SLMs for PII substitution while producing more natural text than rule-based methods, though downstream NER training benefits more from synthetic variety than naturalness."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Locale-conditioned rotating few-shot prompts stop small language models from echoing demonstration examples during on-device PII substitution."}],"snapshot_sha256":"1767d0d1798e97fd46bb4e9176590148e9eb44ae983ad5d85fb458dc47ca6388"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"13cea1224d6f07fff5395eb607961feb0d0eb9b58ef3be5215275e4827c88642"},"paper":{"abstract_excerpt":"Personally Identifiable Information (PII) redaction usually replaces detected entities with placeholder tokens such as [PERSON], destroying the downstream utility of the redacted text for retrieval and Named Entity Recognition (NER) training. We propose a fully on-device pipeline that substitutes PII with consistent, type-preserving fake values: a 1.5 B mixture-of-experts token classifier (openai/privacy-filter) detects spans, a 1-bit Bonsai-1.7B Small Language Model (SLM) proposes contextual surrogates for names, addresses, and dates, and a rule-based generator (faker) handles patterned field","authors_text":"Anuj Sadani, Deepak Kumar","cross_cats":["cs.AI"],"headline":"Locale-conditioned rotating few-shot prompts stop small language models from echoing demonstration examples during on-device PII substitution.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T13:47:11Z","title":"Locale-Conditioned Few-Shot Prompting Mitigates Demonstration Regurgitation in On-Device PII Substitution with Small Language Models"},"references":{"count":16,"internal_anchors":3,"resolved_work":16,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Faker: a Python package that generates fake data","work_id":"b1918f04-be18-4cdc-8b1b-8098eac3c9ec","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"llama.cpp: Port of LLaMA models in C/C++","work_id":"6b334f6b-fac2-4e0c-910e-43ed4197b5c2","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"spaCy: Industrial-strength natural language processing in Python","work_id":"8878703d-2330-47d2-81ec-6f3b4c7eacb6","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Few-shot learning with multilingual language models","work_id":"32d56185-d394-41f6-a038-08c943a4650c","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity","work_id":"c6ecb82b-59ca-437f-91d8-470531f9f7c8","year":2022}],"snapshot_sha256":"8f7fc02398e1eadab2ea9d9fadc8e255a1580afbb705951483156df5e9d4b78b"},"source":{"id":"2605.13538","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:00:57.673618Z","id":"fddab2d7-c488-4d6a-8201-d6bc53eabbb7","model_set":{"reader":"grok-4.3"},"one_line_summary":"Locale-conditioned rotating few-shot prompting eliminates demonstration regurgitation in 1.7B SLMs for PII substitution while producing more natural text than rule-based methods, though downstream NER training benefits more from synthetic variety than naturalness.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Locale-conditioned rotating few-shot prompts stop small language models from echoing demonstration examples during on-device PII substitution.","strongest_claim":"With the fix, 482/482 unique Bonsai-1.7B calls succeed (no echoes) and produce locale-correct surrogates, although the SLM still copies from a small same-locale demonstration pool - a residual narrowness we quantify.","weakest_assumption":"That the observed NER performance gap is caused primarily by reduced variety in SLM outputs rather than by other unmeasured differences in the 160/40 subset or by the choice of XGLM-564M as the multilingual evaluator."}},"verdict_id":"fddab2d7-c488-4d6a-8201-d6bc53eabbb7"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e205aef49527f7367491c5b765d6e765333d1476e8829e1eb8aab59b63cfaba6","target":"record","created_at":"2026-05-18T02:44:24Z","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":"08982f296d3b7011c8b7b2fdf6bec4c5c580d305c1cc7386049148fae213f8dc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T13:47:11Z","title_canon_sha256":"71ca1095213f9418fa258a120300c4beee4c761bb6f28c94731d6b266582527e"},"schema_version":"1.0","source":{"id":"2605.13538","kind":"arxiv","version":1}},"canonical_sha256":"d836d90d63182919648a0ead41da445340ce937cfd128a535c945fe435ff69ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d836d90d63182919648a0ead41da445340ce937cfd128a535c945fe435ff69ef","first_computed_at":"2026-05-18T02:44:24.088768Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:24.088768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UiiGXX66GqPyk1m3keJIB02P+V1lkUMgi/TVIISJ75wsBSzxgqypbEdhHkYG6O7UB9AclxzmKuuQDANrTUErDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:24.089214Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13538","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e205aef49527f7367491c5b765d6e765333d1476e8829e1eb8aab59b63cfaba6","sha256:9aeb073cd6a4ee78316646a7a496d8c3908964698b74e9f10aa92be23816e870"],"state_sha256":"a43335df8b189df0ebc97c8c7478933f17a8b55e5f17e595cd88f3d5afcc5426"}