{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KFYP5M6ASFU2IEGT25EZ4SM6QT","short_pith_number":"pith:KFYP5M6A","canonical_record":{"source":{"id":"2606.05336","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T18:25:00Z","cross_cats_sorted":[],"title_canon_sha256":"7a70c38ea40a0a5b5459c922f3c993277677b9162a47ae2c228bfe4910a2e87c","abstract_canon_sha256":"5f3efe0e7e7f09b099bb65e400c023b43a811985fe0c18277c90184efb4ec56a"},"schema_version":"1.0"},"canonical_sha256":"5170feb3c09169a410d3d7499e499e84e4b50eb8748ab2b99be3f634a093e038","source":{"kind":"arxiv","id":"2606.05336","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05336","created_at":"2026-06-05T00:13:54Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05336v1","created_at":"2026-06-05T00:13:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05336","created_at":"2026-06-05T00:13:54Z"},{"alias_kind":"pith_short_12","alias_value":"KFYP5M6ASFU2","created_at":"2026-06-05T00:13:54Z"},{"alias_kind":"pith_short_16","alias_value":"KFYP5M6ASFU2IEGT","created_at":"2026-06-05T00:13:54Z"},{"alias_kind":"pith_short_8","alias_value":"KFYP5M6A","created_at":"2026-06-05T00:13:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KFYP5M6ASFU2IEGT25EZ4SM6QT","target":"record","payload":{"canonical_record":{"source":{"id":"2606.05336","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T18:25:00Z","cross_cats_sorted":[],"title_canon_sha256":"7a70c38ea40a0a5b5459c922f3c993277677b9162a47ae2c228bfe4910a2e87c","abstract_canon_sha256":"5f3efe0e7e7f09b099bb65e400c023b43a811985fe0c18277c90184efb4ec56a"},"schema_version":"1.0"},"canonical_sha256":"5170feb3c09169a410d3d7499e499e84e4b50eb8748ab2b99be3f634a093e038","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T00:13:54.603146Z","signature_b64":"cIYpfz7x2cV6a/w1SKHbpJcaQzboJEGWwmxiUThnVR/dcKdIYuok6mIvxOZ1RoVv5IvifhNQl/rAyIRgo3m1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5170feb3c09169a410d3d7499e499e84e4b50eb8748ab2b99be3f634a093e038","last_reissued_at":"2026-06-05T00:13:54.601877Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T00:13:54.601877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.05336","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":"2026-06-05T00:13:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M0Yuse98j8CeEonRaEcUkUNxGXQkDt7zo9ctWtPng9kXO/aJYGhJ184BSwGU6EpBh1NSMxpLOForqOXLN32zCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T18:43:39.191684Z"},"content_sha256":"52276b557a2a30eee78d618be481f6efaa6409e829b44d4543336a49f1b6b96e","schema_version":"1.0","event_id":"sha256:52276b557a2a30eee78d618be481f6efaa6409e829b44d4543336a49f1b6b96e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KFYP5M6ASFU2IEGT25EZ4SM6QT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-supervised User Profile Generation for Personalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Clark Mingxuan Ju, Neil Shah, Tong Zhao, Yuwei Qiu","submitted_at":"2026-06-03T18:25:00Z","abstract_excerpt":"Personalizing large language models (LLMs) has become a central challenge as LLMs are deployed across recommendation, search, dialogue, and content generation -- settings where the same query should yield different answers given different users. A promising route is to summarize each user's interaction history into a natural-language memory or profile and prepend it to the prompt to facilitate personalization. Existing methods learn such profile generators with explicit rewards derived from labeled downstream tasks, which are expensive and sparse as they require annotated supervision for every"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05336","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/2606.05336/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":"2026-06-05T00:13:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wDfMnbt4wTf+Tb8ihlGdSBxppwUytY08icKsFWl6s5+adk2a6i+seb7uL/rHrRdH+yDUbDaFHkXI7y7IZSdUBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T18:43:39.193702Z"},"content_sha256":"a21b4d5f57e38f2463a09c41750a45af89019b49a202a1bd9be3078ca41c2d57","schema_version":"1.0","event_id":"sha256:a21b4d5f57e38f2463a09c41750a45af89019b49a202a1bd9be3078ca41c2d57"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KFYP5M6ASFU2IEGT25EZ4SM6QT/bundle.json","state_url":"https://pith.science/pith/KFYP5M6ASFU2IEGT25EZ4SM6QT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KFYP5M6ASFU2IEGT25EZ4SM6QT/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":"2026-08-13T18:43:39Z","links":{"resolver":"https://pith.science/pith/KFYP5M6ASFU2IEGT25EZ4SM6QT","bundle":"https://pith.science/pith/KFYP5M6ASFU2IEGT25EZ4SM6QT/bundle.json","state":"https://pith.science/pith/KFYP5M6ASFU2IEGT25EZ4SM6QT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KFYP5M6ASFU2IEGT25EZ4SM6QT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KFYP5M6ASFU2IEGT25EZ4SM6QT","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":"5f3efe0e7e7f09b099bb65e400c023b43a811985fe0c18277c90184efb4ec56a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T18:25:00Z","title_canon_sha256":"7a70c38ea40a0a5b5459c922f3c993277677b9162a47ae2c228bfe4910a2e87c"},"schema_version":"1.0","source":{"id":"2606.05336","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05336","created_at":"2026-06-05T00:13:54Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05336v1","created_at":"2026-06-05T00:13:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05336","created_at":"2026-06-05T00:13:54Z"},{"alias_kind":"pith_short_12","alias_value":"KFYP5M6ASFU2","created_at":"2026-06-05T00:13:54Z"},{"alias_kind":"pith_short_16","alias_value":"KFYP5M6ASFU2IEGT","created_at":"2026-06-05T00:13:54Z"},{"alias_kind":"pith_short_8","alias_value":"KFYP5M6A","created_at":"2026-06-05T00:13:54Z"}],"graph_snapshots":[{"event_id":"sha256:a21b4d5f57e38f2463a09c41750a45af89019b49a202a1bd9be3078ca41c2d57","target":"graph","created_at":"2026-06-05T00:13:54Z","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/2606.05336/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Personalizing large language models (LLMs) has become a central challenge as LLMs are deployed across recommendation, search, dialogue, and content generation -- settings where the same query should yield different answers given different users. A promising route is to summarize each user's interaction history into a natural-language memory or profile and prepend it to the prompt to facilitate personalization. Existing methods learn such profile generators with explicit rewards derived from labeled downstream tasks, which are expensive and sparse as they require annotated supervision for every","authors_text":"Clark Mingxuan Ju, Neil Shah, Tong Zhao, Yuwei Qiu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T18:25:00Z","title":"Self-supervised User Profile Generation for Personalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05336","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":"sha256:52276b557a2a30eee78d618be481f6efaa6409e829b44d4543336a49f1b6b96e","target":"record","created_at":"2026-06-05T00:13:54Z","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":"5f3efe0e7e7f09b099bb65e400c023b43a811985fe0c18277c90184efb4ec56a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T18:25:00Z","title_canon_sha256":"7a70c38ea40a0a5b5459c922f3c993277677b9162a47ae2c228bfe4910a2e87c"},"schema_version":"1.0","source":{"id":"2606.05336","kind":"arxiv","version":1}},"canonical_sha256":"5170feb3c09169a410d3d7499e499e84e4b50eb8748ab2b99be3f634a093e038","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5170feb3c09169a410d3d7499e499e84e4b50eb8748ab2b99be3f634a093e038","first_computed_at":"2026-06-05T00:13:54.601877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T00:13:54.601877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cIYpfz7x2cV6a/w1SKHbpJcaQzboJEGWwmxiUThnVR/dcKdIYuok6mIvxOZ1RoVv5IvifhNQl/rAyIRgo3m1CA==","signature_status":"signed_v1","signed_at":"2026-06-05T00:13:54.603146Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05336","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52276b557a2a30eee78d618be481f6efaa6409e829b44d4543336a49f1b6b96e","sha256:a21b4d5f57e38f2463a09c41750a45af89019b49a202a1bd9be3078ca41c2d57"],"state_sha256":"712e6e89ea668a8db7b6b614be8d2c11ac38a6dfc32556f2d65b011483520ad5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x+eRrCFBbl7DlG+/S2Ebittfene6D2WHf8gEFmCeEmR6KSDTXKl+c/N5fLEGWqIFYDvXfd2iU27skVREK696Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T18:43:39.240180Z","bundle_sha256":"f743d5f1deb1c9811f5199df8074b5fbf8fdbefae0a1cb874c6e6327b0a0a7c6"}}