{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AIM6D3HZG6KXINJVMTSXFNRYGB","short_pith_number":"pith:AIM6D3HZ","canonical_record":{"source":{"id":"2607.26473","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T04:56:14Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"673b4babd45474379734ae4794c806a908500e266ac0371147f4b85646db715d","abstract_canon_sha256":"441b0864b596a07d3a02405be7f8de41fcb359a43b84eaf6e68d1d8cd5e07978"},"schema_version":"1.0"},"canonical_sha256":"0219e1ecf9379574353564e572b638305f8a89f27a79b57395867206e73bc967","source":{"kind":"arxiv","id":"2607.26473","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26473","created_at":"2026-07-30T01:20:36Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26473v1","created_at":"2026-07-30T01:20:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26473","created_at":"2026-07-30T01:20:36Z"},{"alias_kind":"pith_short_12","alias_value":"AIM6D3HZG6KX","created_at":"2026-07-30T01:20:36Z"},{"alias_kind":"pith_short_16","alias_value":"AIM6D3HZG6KXINJV","created_at":"2026-07-30T01:20:36Z"},{"alias_kind":"pith_short_8","alias_value":"AIM6D3HZ","created_at":"2026-07-30T01:20:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AIM6D3HZG6KXINJVMTSXFNRYGB","target":"record","payload":{"canonical_record":{"source":{"id":"2607.26473","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T04:56:14Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"673b4babd45474379734ae4794c806a908500e266ac0371147f4b85646db715d","abstract_canon_sha256":"441b0864b596a07d3a02405be7f8de41fcb359a43b84eaf6e68d1d8cd5e07978"},"schema_version":"1.0"},"canonical_sha256":"0219e1ecf9379574353564e572b638305f8a89f27a79b57395867206e73bc967","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0219e1ecf9379574353564e572b638305f8a89f27a79b57395867206e73bc967","last_reissued_at":"2026-07-30T01:20:36.559864Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:20:36.559864Z"},"source_kind":"arxiv","source_id":"2607.26473","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":"2026-07-30T01:20:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tKhegbrU7+I05J/p+rAS4o1DiE3AfZezhUTewOGiygd1Tgi6chgZY1pGN9RuVla57V9CXitOvF0ufMgeuIoQBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:18:39.662881Z"},"content_sha256":"98f3c3a8cac8e2a6d99a6bd4e83d744361408aacbd8a970188e53eb2ab4d2bfa","schema_version":"1.0","event_id":"sha256:98f3c3a8cac8e2a6d99a6bd4e83d744361408aacbd8a970188e53eb2ab4d2bfa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AIM6D3HZG6KXINJVMTSXFNRYGB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Dynamic User Personas from Implicit Interaction Streams via Iterative Refinement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Haifeng Wu","submitted_at":"2026-07-29T04:56:14Z","abstract_excerpt":"Personalizing large language models (LLMs) to individual users is essential for improving user experience, yet existing approaches typically rely on explicit preference supervision such as pairwise comparisons or demographic attributes, limiting their applicability in natural interaction settings. We propose IRIS, a framework that learns dynamic user personas directly from implicit interaction streams by extracting behavioral signals from everyday conversations and iteratively refining persona representations through a prediction-driven closed loop without requiring explicit feedback. We intro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26473","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/2607.26473/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":"2026-07-30T01:20:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eUqLUclc9aqhnP+n6O4LGd+cAZf+8eInhfJzwKrEXAye4ronahOwfvT5E72Y1xF7xcMRTkJn94meaa+sAKplCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:18:39.663534Z"},"content_sha256":"131dc4f05cdb9142bb6393c7b6216f6840304592fecb60c2281c022d981025ec","schema_version":"1.0","event_id":"sha256:131dc4f05cdb9142bb6393c7b6216f6840304592fecb60c2281c022d981025ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AIM6D3HZG6KXINJVMTSXFNRYGB/bundle.json","state_url":"https://pith.science/pith/AIM6D3HZG6KXINJVMTSXFNRYGB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AIM6D3HZG6KXINJVMTSXFNRYGB/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":"2026-08-04T10:18:39Z","links":{"resolver":"https://pith.science/pith/AIM6D3HZG6KXINJVMTSXFNRYGB","bundle":"https://pith.science/pith/AIM6D3HZG6KXINJVMTSXFNRYGB/bundle.json","state":"https://pith.science/pith/AIM6D3HZG6KXINJVMTSXFNRYGB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AIM6D3HZG6KXINJVMTSXFNRYGB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AIM6D3HZG6KXINJVMTSXFNRYGB","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":"441b0864b596a07d3a02405be7f8de41fcb359a43b84eaf6e68d1d8cd5e07978","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T04:56:14Z","title_canon_sha256":"673b4babd45474379734ae4794c806a908500e266ac0371147f4b85646db715d"},"schema_version":"1.0","source":{"id":"2607.26473","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26473","created_at":"2026-07-30T01:20:36Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26473v1","created_at":"2026-07-30T01:20:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26473","created_at":"2026-07-30T01:20:36Z"},{"alias_kind":"pith_short_12","alias_value":"AIM6D3HZG6KX","created_at":"2026-07-30T01:20:36Z"},{"alias_kind":"pith_short_16","alias_value":"AIM6D3HZG6KXINJV","created_at":"2026-07-30T01:20:36Z"},{"alias_kind":"pith_short_8","alias_value":"AIM6D3HZ","created_at":"2026-07-30T01:20:36Z"}],"graph_snapshots":[{"event_id":"sha256:131dc4f05cdb9142bb6393c7b6216f6840304592fecb60c2281c022d981025ec","target":"graph","created_at":"2026-07-30T01:20:36Z","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/2607.26473/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Personalizing large language models (LLMs) to individual users is essential for improving user experience, yet existing approaches typically rely on explicit preference supervision such as pairwise comparisons or demographic attributes, limiting their applicability in natural interaction settings. We propose IRIS, a framework that learns dynamic user personas directly from implicit interaction streams by extracting behavioral signals from everyday conversations and iteratively refining persona representations through a prediction-driven closed loop without requiring explicit feedback. We intro","authors_text":"Haifeng Wu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T04:56:14Z","title":"Learning Dynamic User Personas from Implicit Interaction Streams via Iterative Refinement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26473","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":"sha256:98f3c3a8cac8e2a6d99a6bd4e83d744361408aacbd8a970188e53eb2ab4d2bfa","target":"record","created_at":"2026-07-30T01:20:36Z","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":"441b0864b596a07d3a02405be7f8de41fcb359a43b84eaf6e68d1d8cd5e07978","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T04:56:14Z","title_canon_sha256":"673b4babd45474379734ae4794c806a908500e266ac0371147f4b85646db715d"},"schema_version":"1.0","source":{"id":"2607.26473","kind":"arxiv","version":1}},"canonical_sha256":"0219e1ecf9379574353564e572b638305f8a89f27a79b57395867206e73bc967","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0219e1ecf9379574353564e572b638305f8a89f27a79b57395867206e73bc967","first_computed_at":"2026-07-30T01:20:36.559864Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:20:36.559864Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.26473","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98f3c3a8cac8e2a6d99a6bd4e83d744361408aacbd8a970188e53eb2ab4d2bfa","sha256:131dc4f05cdb9142bb6393c7b6216f6840304592fecb60c2281c022d981025ec"],"state_sha256":"47ad8757178d2139d51fbcce090918dfc3d59d630d3d6eb00fdf1602269bd5b6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QcRrJf40BZFpCdBxRBNFPbNWM0pFNHB6Hdto8Lz1rYxmMLOT+l1GIrqaMZk5t/5kbiZloS6CjxetXdMYyaKOCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T10:18:39.667699Z","bundle_sha256":"a66d7dc998b8f098aef3c07575f23686d3cef9c1d90fe63a16c950095af8e445"}}