{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:W7HULFIFSBQG4VIT2WKPMX3RCY","short_pith_number":"pith:W7HULFIF","canonical_record":{"source":{"id":"2606.04547","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-03T07:32:18Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ea25fdcf6f0a53be6f6e83bab41386cd380b1a78304a620fe5b940cf1f7e554c","abstract_canon_sha256":"82d8bd6017fb40d555cdf23b3c03b2cb55018125b0b9fa1da348ebf416b95afd"},"schema_version":"1.0"},"canonical_sha256":"b7cf45950590606e5513d594f65f7116116a843b0be8f006c6efa5242efcef55","source":{"kind":"arxiv","id":"2606.04547","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04547","created_at":"2026-06-04T01:09:17Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04547v1","created_at":"2026-06-04T01:09:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04547","created_at":"2026-06-04T01:09:17Z"},{"alias_kind":"pith_short_12","alias_value":"W7HULFIFSBQG","created_at":"2026-06-04T01:09:17Z"},{"alias_kind":"pith_short_16","alias_value":"W7HULFIFSBQG4VIT","created_at":"2026-06-04T01:09:17Z"},{"alias_kind":"pith_short_8","alias_value":"W7HULFIF","created_at":"2026-06-04T01:09:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:W7HULFIFSBQG4VIT2WKPMX3RCY","target":"record","payload":{"canonical_record":{"source":{"id":"2606.04547","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-03T07:32:18Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ea25fdcf6f0a53be6f6e83bab41386cd380b1a78304a620fe5b940cf1f7e554c","abstract_canon_sha256":"82d8bd6017fb40d555cdf23b3c03b2cb55018125b0b9fa1da348ebf416b95afd"},"schema_version":"1.0"},"canonical_sha256":"b7cf45950590606e5513d594f65f7116116a843b0be8f006c6efa5242efcef55","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:17.379562Z","signature_b64":"iROVCehJepAr+IH6me8W+CX3uAKIntQkJ8XASs+RGcyJSysZJMA63dwdYyq2N/ijfFRGBn4djRWD2KeS7y3GCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7cf45950590606e5513d594f65f7116116a843b0be8f006c6efa5242efcef55","last_reissued_at":"2026-06-04T01:09:17.378704Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:17.378704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.04547","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":"2026-06-04T01:09:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4XlcA+Z4j2qcmDrDm/ADSjCBK9dk66bXeg/bCS1G8gMzeL9WXxeFamutqvIJ29LUu4Qw5Y/9rwRnEw7DU2YeDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T02:41:10.827222Z"},"content_sha256":"5fd70f0766d157601cf2618b56a1b5da0b35f7a67e626428b9b04e3bb80f3562","schema_version":"1.0","event_id":"sha256:5fd70f0766d157601cf2618b56a1b5da0b35f7a67e626428b9b04e3bb80f3562"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:W7HULFIFSBQG4VIT2WKPMX3RCY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Retrieval: Learning Compact User Representations for Scalable LLM Personalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Changlin Zhao, Fan Zhang, Heng Cao, Huaiyu Fu, Jian Yao, Lu Hao, Wangze Ni, Xuyan Mo, Yujie Zheng, Yuqian Sun, Yuxuan Wei","submitted_at":"2026-06-03T07:32:18Z","abstract_excerpt":"Personalizing large language models requires adapting model behavior to individual users while preserving robustness and deployment-scale efficiency. Existing approaches typically personalize LLMs either at the input level, by retrieving user histories or constructing profile prompts, or at the parameter level, by maintaining user-specific parameter-efficient modules. The former makes personalization sensitive to retrieval quality and prompt design, whereas the latter incurs storage and maintenance costs that grow with the user population. To address these limitations, we propose TAP-PER (Temp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04547","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/2606.04547/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":"2026-06-04T01:09:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Q0Yy9MV3sifXTCP/lefGkzH46P703wEmX3UhsrzuUMOiDrl0nmlfbBoa2/py+GpJaTMi4+58a2uv+Zb7tEHAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T02:41:10.827613Z"},"content_sha256":"84edef79beaa467c1ac1b8425bb626cf27ccb07f488b0ffe4ddef41e7a4b5318","schema_version":"1.0","event_id":"sha256:84edef79beaa467c1ac1b8425bb626cf27ccb07f488b0ffe4ddef41e7a4b5318"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W7HULFIFSBQG4VIT2WKPMX3RCY/bundle.json","state_url":"https://pith.science/pith/W7HULFIFSBQG4VIT2WKPMX3RCY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W7HULFIFSBQG4VIT2WKPMX3RCY/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":"2026-06-20T02:41:10Z","links":{"resolver":"https://pith.science/pith/W7HULFIFSBQG4VIT2WKPMX3RCY","bundle":"https://pith.science/pith/W7HULFIFSBQG4VIT2WKPMX3RCY/bundle.json","state":"https://pith.science/pith/W7HULFIFSBQG4VIT2WKPMX3RCY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W7HULFIFSBQG4VIT2WKPMX3RCY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:W7HULFIFSBQG4VIT2WKPMX3RCY","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":"82d8bd6017fb40d555cdf23b3c03b2cb55018125b0b9fa1da348ebf416b95afd","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-03T07:32:18Z","title_canon_sha256":"ea25fdcf6f0a53be6f6e83bab41386cd380b1a78304a620fe5b940cf1f7e554c"},"schema_version":"1.0","source":{"id":"2606.04547","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04547","created_at":"2026-06-04T01:09:17Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04547v1","created_at":"2026-06-04T01:09:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04547","created_at":"2026-06-04T01:09:17Z"},{"alias_kind":"pith_short_12","alias_value":"W7HULFIFSBQG","created_at":"2026-06-04T01:09:17Z"},{"alias_kind":"pith_short_16","alias_value":"W7HULFIFSBQG4VIT","created_at":"2026-06-04T01:09:17Z"},{"alias_kind":"pith_short_8","alias_value":"W7HULFIF","created_at":"2026-06-04T01:09:17Z"}],"graph_snapshots":[{"event_id":"sha256:84edef79beaa467c1ac1b8425bb626cf27ccb07f488b0ffe4ddef41e7a4b5318","target":"graph","created_at":"2026-06-04T01:09:17Z","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/2606.04547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Personalizing large language models requires adapting model behavior to individual users while preserving robustness and deployment-scale efficiency. Existing approaches typically personalize LLMs either at the input level, by retrieving user histories or constructing profile prompts, or at the parameter level, by maintaining user-specific parameter-efficient modules. The former makes personalization sensitive to retrieval quality and prompt design, whereas the latter incurs storage and maintenance costs that grow with the user population. To address these limitations, we propose TAP-PER (Temp","authors_text":"Changlin Zhao, Fan Zhang, Heng Cao, Huaiyu Fu, Jian Yao, Lu Hao, Wangze Ni, Xuyan Mo, Yujie Zheng, Yuqian Sun, Yuxuan Wei","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-03T07:32:18Z","title":"Beyond Retrieval: Learning Compact User Representations for Scalable LLM Personalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04547","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":"sha256:5fd70f0766d157601cf2618b56a1b5da0b35f7a67e626428b9b04e3bb80f3562","target":"record","created_at":"2026-06-04T01:09:17Z","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":"82d8bd6017fb40d555cdf23b3c03b2cb55018125b0b9fa1da348ebf416b95afd","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-03T07:32:18Z","title_canon_sha256":"ea25fdcf6f0a53be6f6e83bab41386cd380b1a78304a620fe5b940cf1f7e554c"},"schema_version":"1.0","source":{"id":"2606.04547","kind":"arxiv","version":1}},"canonical_sha256":"b7cf45950590606e5513d594f65f7116116a843b0be8f006c6efa5242efcef55","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7cf45950590606e5513d594f65f7116116a843b0be8f006c6efa5242efcef55","first_computed_at":"2026-06-04T01:09:17.378704Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:09:17.378704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iROVCehJepAr+IH6me8W+CX3uAKIntQkJ8XASs+RGcyJSysZJMA63dwdYyq2N/ijfFRGBn4djRWD2KeS7y3GCQ==","signature_status":"signed_v1","signed_at":"2026-06-04T01:09:17.379562Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04547","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5fd70f0766d157601cf2618b56a1b5da0b35f7a67e626428b9b04e3bb80f3562","sha256:84edef79beaa467c1ac1b8425bb626cf27ccb07f488b0ffe4ddef41e7a4b5318"],"state_sha256":"771f4cb2f81b92dfa9fa74901e932ca6d6e9d2fd568b55b2098a8182e2051e7c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jNNqYjNlnw7T370/LsJ4U1WgekTT1q0m2E+8efXB5IAONZvaokzvHx5Bgh+Z2fAAucJs3VTiOgoeNH6MJyg/Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T02:41:10.829650Z","bundle_sha256":"6b08df3cc0ea7a24affcb51616a5e2462f9dfe5f6b9262f888d59b968242d744"}}