{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YGMM7CD4VC3ZX22RNHDMFTKYEL","short_pith_number":"pith:YGMM7CD4","canonical_record":{"source":{"id":"2607.21620","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T12:42:17Z","cross_cats_sorted":[],"title_canon_sha256":"aa076289672833e80bf7239f2fdd037a2aa5f55068e4cce240b43486c3bd37e8","abstract_canon_sha256":"0d1d2a977c0bb3893c7e38ed45546fb399c896bc14c16871a839eef6c91a7883"},"schema_version":"1.0"},"canonical_sha256":"c198cf887ca8b79beb5169c6c2cd5822f5bc05c8a2c35bf3d6f4d4753e49e634","source":{"kind":"arxiv","id":"2607.21620","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21620","created_at":"2026-07-27T00:20:11Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21620v1","created_at":"2026-07-27T00:20:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21620","created_at":"2026-07-27T00:20:11Z"},{"alias_kind":"pith_short_12","alias_value":"YGMM7CD4VC3Z","created_at":"2026-07-27T00:20:11Z"},{"alias_kind":"pith_short_16","alias_value":"YGMM7CD4VC3ZX22R","created_at":"2026-07-27T00:20:11Z"},{"alias_kind":"pith_short_8","alias_value":"YGMM7CD4","created_at":"2026-07-27T00:20:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YGMM7CD4VC3ZX22RNHDMFTKYEL","target":"record","payload":{"canonical_record":{"source":{"id":"2607.21620","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T12:42:17Z","cross_cats_sorted":[],"title_canon_sha256":"aa076289672833e80bf7239f2fdd037a2aa5f55068e4cce240b43486c3bd37e8","abstract_canon_sha256":"0d1d2a977c0bb3893c7e38ed45546fb399c896bc14c16871a839eef6c91a7883"},"schema_version":"1.0"},"canonical_sha256":"c198cf887ca8b79beb5169c6c2cd5822f5bc05c8a2c35bf3d6f4d4753e49e634","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T00:20:11.542014Z","signature_b64":"23ysgBuvFPO/xiXciKWoDJnGuKK/qVN3nrD/dk6/MQFFAQ1lDCQvI7LQaQS/3kbi3MDEL5o3n8HKBhZAHmrdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c198cf887ca8b79beb5169c6c2cd5822f5bc05c8a2c35bf3d6f4d4753e49e634","last_reissued_at":"2026-07-27T00:20:11.541115Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T00:20:11.541115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.21620","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":"2026-07-27T00:20:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3SM+buA+JABHLRatycX48IST/MMo40GbPqRu9nEI5wINX0wuHargzX0H6DvIT5adsNK3tlnY7iXL0YyzPypdBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:11:34.287497Z"},"content_sha256":"26176b6caaf136154e2edb44a564130973c69a45698a12b0bfccd30a105dcff0","schema_version":"1.0","event_id":"sha256:26176b6caaf136154e2edb44a564130973c69a45698a12b0bfccd30a105dcff0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YGMM7CD4VC3ZX22RNHDMFTKYEL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Profiles to Steering Vectors: Global Sparse Priors and Local Semantic Calibration for Personalized Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Liang Wang, Liuji Chen, Qiang Liu, Shuai Nie, Shu Wu, Xinyuan Zhang, Zeyu Zhang","submitted_at":"2026-06-01T12:42:17Z","abstract_excerpt":"Personalized text generation requires models to capture user-specific writing styles from historical data. Existing approaches based on retrieval, parameter-efficient fine-tuning, or activation steering either introduce inference and storage overhead or struggle to separate stylistic signals from semantic content. We propose GLASS, a training-free framework for personalized generation via Global-Local Activation Steering with Sparse priors. GLASS uses sparse autoencoders to extract a global user-style prior from historical responses and constructs local contrastive style vectors over clustered"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21620","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/2607.21620/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":"2026-07-27T00:20:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NeoGe10h4TG/IFTMdWZydtfP2+FbtNoZZlagWk1YGFw3i3WZ74d9i38sR9rnB8QyyCWF68CT1YgdAr9rx2fbDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:11:34.288086Z"},"content_sha256":"c61107328bca1e616eede6f4a234234edf0a426c63d73205f555f9bdf97bf759","schema_version":"1.0","event_id":"sha256:c61107328bca1e616eede6f4a234234edf0a426c63d73205f555f9bdf97bf759"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YGMM7CD4VC3ZX22RNHDMFTKYEL/bundle.json","state_url":"https://pith.science/pith/YGMM7CD4VC3ZX22RNHDMFTKYEL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YGMM7CD4VC3ZX22RNHDMFTKYEL/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":"2026-08-07T15:11:34Z","links":{"resolver":"https://pith.science/pith/YGMM7CD4VC3ZX22RNHDMFTKYEL","bundle":"https://pith.science/pith/YGMM7CD4VC3ZX22RNHDMFTKYEL/bundle.json","state":"https://pith.science/pith/YGMM7CD4VC3ZX22RNHDMFTKYEL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YGMM7CD4VC3ZX22RNHDMFTKYEL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YGMM7CD4VC3ZX22RNHDMFTKYEL","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":"0d1d2a977c0bb3893c7e38ed45546fb399c896bc14c16871a839eef6c91a7883","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T12:42:17Z","title_canon_sha256":"aa076289672833e80bf7239f2fdd037a2aa5f55068e4cce240b43486c3bd37e8"},"schema_version":"1.0","source":{"id":"2607.21620","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21620","created_at":"2026-07-27T00:20:11Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21620v1","created_at":"2026-07-27T00:20:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21620","created_at":"2026-07-27T00:20:11Z"},{"alias_kind":"pith_short_12","alias_value":"YGMM7CD4VC3Z","created_at":"2026-07-27T00:20:11Z"},{"alias_kind":"pith_short_16","alias_value":"YGMM7CD4VC3ZX22R","created_at":"2026-07-27T00:20:11Z"},{"alias_kind":"pith_short_8","alias_value":"YGMM7CD4","created_at":"2026-07-27T00:20:11Z"}],"graph_snapshots":[{"event_id":"sha256:c61107328bca1e616eede6f4a234234edf0a426c63d73205f555f9bdf97bf759","target":"graph","created_at":"2026-07-27T00:20:11Z","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/2607.21620/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Personalized text generation requires models to capture user-specific writing styles from historical data. Existing approaches based on retrieval, parameter-efficient fine-tuning, or activation steering either introduce inference and storage overhead or struggle to separate stylistic signals from semantic content. We propose GLASS, a training-free framework for personalized generation via Global-Local Activation Steering with Sparse priors. GLASS uses sparse autoencoders to extract a global user-style prior from historical responses and constructs local contrastive style vectors over clustered","authors_text":"Liang Wang, Liuji Chen, Qiang Liu, Shuai Nie, Shu Wu, Xinyuan Zhang, Zeyu Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T12:42:17Z","title":"From Profiles to Steering Vectors: Global Sparse Priors and Local Semantic Calibration for Personalized Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21620","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":"sha256:26176b6caaf136154e2edb44a564130973c69a45698a12b0bfccd30a105dcff0","target":"record","created_at":"2026-07-27T00:20:11Z","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":"0d1d2a977c0bb3893c7e38ed45546fb399c896bc14c16871a839eef6c91a7883","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T12:42:17Z","title_canon_sha256":"aa076289672833e80bf7239f2fdd037a2aa5f55068e4cce240b43486c3bd37e8"},"schema_version":"1.0","source":{"id":"2607.21620","kind":"arxiv","version":1}},"canonical_sha256":"c198cf887ca8b79beb5169c6c2cd5822f5bc05c8a2c35bf3d6f4d4753e49e634","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c198cf887ca8b79beb5169c6c2cd5822f5bc05c8a2c35bf3d6f4d4753e49e634","first_computed_at":"2026-07-27T00:20:11.541115Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-27T00:20:11.541115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"23ysgBuvFPO/xiXciKWoDJnGuKK/qVN3nrD/dk6/MQFFAQ1lDCQvI7LQaQS/3kbi3MDEL5o3n8HKBhZAHmrdBg==","signature_status":"signed_v1","signed_at":"2026-07-27T00:20:11.542014Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.21620","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26176b6caaf136154e2edb44a564130973c69a45698a12b0bfccd30a105dcff0","sha256:c61107328bca1e616eede6f4a234234edf0a426c63d73205f555f9bdf97bf759"],"state_sha256":"6733be2bc7e9cb959cff5c68130ee0c8bb5904b97326511dde39e53b365c3034"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tRtCJ9eh1QJBjY/OPrJd+PfAt8Ek33pUQwOo1ZioKWfLH1H4/+1ZKdLdW8HRLP8gtcrisXaELhxL2MTi31RHCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:11:34.293430Z","bundle_sha256":"68509c89678be5a4e5d562913b53f68f4392be57bad5c5b56e43acacde86ab13"}}