{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VKCHFSDXF6L3NUVEDBUSDHACNP","short_pith_number":"pith:VKCHFSDX","canonical_record":{"source":{"id":"2505.00038","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-29T18:01:46Z","cross_cats_sorted":[],"title_canon_sha256":"7f7817943961724a4861766fe7bc65e05e91855d75d913e5ef2287c00a449677","abstract_canon_sha256":"49fc70fe7c7d25dc3c79f533d7b44181c2093e73d84245aeaf8c2fd83a7d44a8"},"schema_version":"1.0"},"canonical_sha256":"aa8472c8772f97b6d2a41869219c026bf4e5dc20f81eec3abce5b2d8f2cfe93a","source":{"kind":"arxiv","id":"2505.00038","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.00038","created_at":"2026-07-05T11:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2505.00038v2","created_at":"2026-07-05T11:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00038","created_at":"2026-07-05T11:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"VKCHFSDXF6L3","created_at":"2026-07-05T11:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"VKCHFSDXF6L3NUVE","created_at":"2026-07-05T11:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"VKCHFSDX","created_at":"2026-07-05T11:05:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VKCHFSDXF6L3NUVEDBUSDHACNP","target":"record","payload":{"canonical_record":{"source":{"id":"2505.00038","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-29T18:01:46Z","cross_cats_sorted":[],"title_canon_sha256":"7f7817943961724a4861766fe7bc65e05e91855d75d913e5ef2287c00a449677","abstract_canon_sha256":"49fc70fe7c7d25dc3c79f533d7b44181c2093e73d84245aeaf8c2fd83a7d44a8"},"schema_version":"1.0"},"canonical_sha256":"aa8472c8772f97b6d2a41869219c026bf4e5dc20f81eec3abce5b2d8f2cfe93a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:43.649141Z","signature_b64":"3xZVzPIzTymUFSC8KYzEfKbMdk4yKP1f411ZPyc5nmJST0AA7egKwEZ3qRBqv3Al1uMfXh9WM4IwxeWJ65MmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa8472c8772f97b6d2a41869219c026bf4e5dc20f81eec3abce5b2d8f2cfe93a","last_reissued_at":"2026-07-05T11:05:43.648656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:43.648656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.00038","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:05:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lQOyFSjDNxkGj1vsRBdBHHqUtgiPPHyghfcBbFPcmrpoMr5gYBB7g0SXgq+mAk+mmdH1M5iLLudWzwBzoH1+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:21:16.207448Z"},"content_sha256":"d179c1457b75cf188ff4be15f813a347f492f91d85a2a0ed3efb82ceae766bb3","schema_version":"1.0","event_id":"sha256:d179c1457b75cf188ff4be15f813a347f492f91d85a2a0ed3efb82ceae766bb3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VKCHFSDXF6L3NUVEDBUSDHACNP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HyPerAlign: Interpretable Personalized LLM Alignment via Hypothesis Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenhao Tan, Cristina Garbacea","submitted_at":"2025-04-29T18:01:46Z","abstract_excerpt":"Alignment algorithms are widely used to align large language models (LLMs) to human users based on preference annotations. Typically these (often divergent) preferences are aggregated over a diverse set of users, resulting in fine-tuned models that are aligned to the ``average-user'' preference. Nevertheless, current models are used by individual users in very specific contexts and situations, emphasizing the need for user-dependent preference control. In this work we address the problem of personalizing LLM outputs to their users. We aim to generate customized responses tailored to specific i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00038","kind":"arxiv","version":2},"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/2505.00038/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":"2026-07-05T11:05:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wYWUtrMx72DTrR3MW/dsgNjhsKlPIrcSLbdApE0+YbvWnRnKnxTfUnZDymmU7Tg+KEKasDmv4orGfeOkom5WBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:21:16.207970Z"},"content_sha256":"11c72bb73fd8745c775576f3dc53588b49cc804ac9135bc5a59e7ef9fa53b74d","schema_version":"1.0","event_id":"sha256:11c72bb73fd8745c775576f3dc53588b49cc804ac9135bc5a59e7ef9fa53b74d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VKCHFSDXF6L3NUVEDBUSDHACNP/bundle.json","state_url":"https://pith.science/pith/VKCHFSDXF6L3NUVEDBUSDHACNP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VKCHFSDXF6L3NUVEDBUSDHACNP/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":"2026-08-09T23:21:16Z","links":{"resolver":"https://pith.science/pith/VKCHFSDXF6L3NUVEDBUSDHACNP","bundle":"https://pith.science/pith/VKCHFSDXF6L3NUVEDBUSDHACNP/bundle.json","state":"https://pith.science/pith/VKCHFSDXF6L3NUVEDBUSDHACNP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VKCHFSDXF6L3NUVEDBUSDHACNP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VKCHFSDXF6L3NUVEDBUSDHACNP","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":"49fc70fe7c7d25dc3c79f533d7b44181c2093e73d84245aeaf8c2fd83a7d44a8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-29T18:01:46Z","title_canon_sha256":"7f7817943961724a4861766fe7bc65e05e91855d75d913e5ef2287c00a449677"},"schema_version":"1.0","source":{"id":"2505.00038","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.00038","created_at":"2026-07-05T11:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2505.00038v2","created_at":"2026-07-05T11:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00038","created_at":"2026-07-05T11:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"VKCHFSDXF6L3","created_at":"2026-07-05T11:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"VKCHFSDXF6L3NUVE","created_at":"2026-07-05T11:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"VKCHFSDX","created_at":"2026-07-05T11:05:43Z"}],"graph_snapshots":[{"event_id":"sha256:11c72bb73fd8745c775576f3dc53588b49cc804ac9135bc5a59e7ef9fa53b74d","target":"graph","created_at":"2026-07-05T11:05:43Z","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/2505.00038/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Alignment algorithms are widely used to align large language models (LLMs) to human users based on preference annotations. Typically these (often divergent) preferences are aggregated over a diverse set of users, resulting in fine-tuned models that are aligned to the ``average-user'' preference. Nevertheless, current models are used by individual users in very specific contexts and situations, emphasizing the need for user-dependent preference control. In this work we address the problem of personalizing LLM outputs to their users. We aim to generate customized responses tailored to specific i","authors_text":"Chenhao Tan, Cristina Garbacea","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-29T18:01:46Z","title":"HyPerAlign: Interpretable Personalized LLM Alignment via Hypothesis Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00038","kind":"arxiv","version":2},"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:d179c1457b75cf188ff4be15f813a347f492f91d85a2a0ed3efb82ceae766bb3","target":"record","created_at":"2026-07-05T11:05:43Z","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":"49fc70fe7c7d25dc3c79f533d7b44181c2093e73d84245aeaf8c2fd83a7d44a8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-29T18:01:46Z","title_canon_sha256":"7f7817943961724a4861766fe7bc65e05e91855d75d913e5ef2287c00a449677"},"schema_version":"1.0","source":{"id":"2505.00038","kind":"arxiv","version":2}},"canonical_sha256":"aa8472c8772f97b6d2a41869219c026bf4e5dc20f81eec3abce5b2d8f2cfe93a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa8472c8772f97b6d2a41869219c026bf4e5dc20f81eec3abce5b2d8f2cfe93a","first_computed_at":"2026-07-05T11:05:43.648656Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:43.648656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3xZVzPIzTymUFSC8KYzEfKbMdk4yKP1f411ZPyc5nmJST0AA7egKwEZ3qRBqv3Al1uMfXh9WM4IwxeWJ65MmDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:43.649141Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.00038","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d179c1457b75cf188ff4be15f813a347f492f91d85a2a0ed3efb82ceae766bb3","sha256:11c72bb73fd8745c775576f3dc53588b49cc804ac9135bc5a59e7ef9fa53b74d"],"state_sha256":"dd3f38648df863a1762ab851f87fabbd8ad95e9828dfb421878241d5cee15095"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cpr2Gw+QZqBS30tgfV0s8HuIoeETk9yaaFa6D+ioDmqM0ZxT0LMgI1z2bRXReVpU4VP9yEFTSeuwmZB/snm5Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T23:21:16.213696Z","bundle_sha256":"4f0b4a90d2e9ca5d5d3f9062eab593a6f78117e7fffb190a104b55e42e18b32d"}}