{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EYDHFGU7MCNEAPBZ7OSMLKHOWB","short_pith_number":"pith:EYDHFGU7","canonical_record":{"source":{"id":"2510.11194","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-10-13T09:26:47Z","cross_cats_sorted":[],"title_canon_sha256":"42a1f70d213108d73d744be0eadf6b378e6fa838a7f71df21bba14d6fae25590","abstract_canon_sha256":"9c6d763531b86280ef24c8afd4deccbca97e00cdd09dbc5fd42670f8952af77c"},"schema_version":"1.0"},"canonical_sha256":"2606729a9f609a403c39fba4c5a8eeb07bfb38b1b8a44e5b26fdca023ed283de","source":{"kind":"arxiv","id":"2510.11194","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.11194","created_at":"2026-06-04T01:08:33Z"},{"alias_kind":"arxiv_version","alias_value":"2510.11194v3","created_at":"2026-06-04T01:08:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.11194","created_at":"2026-06-04T01:08:33Z"},{"alias_kind":"pith_short_12","alias_value":"EYDHFGU7MCNE","created_at":"2026-06-04T01:08:33Z"},{"alias_kind":"pith_short_16","alias_value":"EYDHFGU7MCNEAPBZ","created_at":"2026-06-04T01:08:33Z"},{"alias_kind":"pith_short_8","alias_value":"EYDHFGU7","created_at":"2026-06-04T01:08:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EYDHFGU7MCNEAPBZ7OSMLKHOWB","target":"record","payload":{"canonical_record":{"source":{"id":"2510.11194","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-10-13T09:26:47Z","cross_cats_sorted":[],"title_canon_sha256":"42a1f70d213108d73d744be0eadf6b378e6fa838a7f71df21bba14d6fae25590","abstract_canon_sha256":"9c6d763531b86280ef24c8afd4deccbca97e00cdd09dbc5fd42670f8952af77c"},"schema_version":"1.0"},"canonical_sha256":"2606729a9f609a403c39fba4c5a8eeb07bfb38b1b8a44e5b26fdca023ed283de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:33.600279Z","signature_b64":"wAt90CkGUsAnPGHd/5GZQZnvVkL2mOy/Q8CTPNXPcZtkBIDS3GR0Rc+o5fMUk2U8Zea6iZTzajI6Hbh7mYzvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2606729a9f609a403c39fba4c5a8eeb07bfb38b1b8a44e5b26fdca023ed283de","last_reissued_at":"2026-06-04T01:08:33.599423Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:33.599423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.11194","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-04T01:08:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6xoE+6wuA/W8OJSQ+heu+TPEEJjS6eDOhkdOYwbolziCKqR5ukE3U1E6svXjQHDGbO3oG5F4Q5IAYUgmLzYjDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T22:12:53.913714Z"},"content_sha256":"d9c622d88d35bd1af2bd5d507e904007e5e151abe0bc044b5ecf4f3d215fb9eb","schema_version":"1.0","event_id":"sha256:d9c622d88d35bd1af2bd5d507e904007e5e151abe0bc044b5ecf4f3d215fb9eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EYDHFGU7MCNEAPBZ7OSMLKHOWB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aligning Deep Implicit Preferences by Learning to Reason Defensively","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"CDRA reframes LLM alignment as a critique-driven reasoning process to infer unstated goals, contexts, and risk tolerances.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Peiming Li, Shiyu Li, Xi Chen, Yang Tang, Zhiyuan Hu","submitted_at":"2025-10-13T09:26:47Z","abstract_excerpt":"Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current methods face a dual challenge: they fail to infer users' deep implicit preferences (including unstated goals, semantic context and risk tolerances), and they lack the defensive reasoning required to navigate real-world ambiguity. This cognitive gap leads to responses that are superficial, brittle and short-sighted. To address this, we propose Critique-Driven Reasoning Alignment (CDRA), which reframes alignment from a scalar reward-matching task into a"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments demonstrate that CDRA excels at discovering and aligning with users' true preferences while executing robust reasoning.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that a simulated multi-faceted cognitive council can reliably produce critique-annotated reasoning chains that accurately deconstruct query semantics and reveal latent risks for the DeepPref benchmark curation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CDRA reframes LLM alignment as a critique-driven reasoning process using the DeepPref benchmark and Pers-GenPRM to infer implicit preferences and guide policy via process-level RL.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CDRA reframes LLM alignment as a critique-driven reasoning process to infer unstated goals, contexts, and risk tolerances.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e91c24ba52e64970a228d3d5a66e350a0fb76c1094886baa42c91f765cb16aec"},"source":{"id":"2510.11194","kind":"arxiv","version":3},"verdict":{"id":"2a53780c-9319-497a-bcb6-acc29a7cc340","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-18T08:07:56.171496Z","strongest_claim":"Experiments demonstrate that CDRA excels at discovering and aligning with users' true preferences while executing robust reasoning.","one_line_summary":"CDRA reframes LLM alignment as a critique-driven reasoning process using the DeepPref benchmark and Pers-GenPRM to infer implicit preferences and guide policy via process-level RL.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that a simulated multi-faceted cognitive council can reliably produce critique-annotated reasoning chains that accurately deconstruct query semantics and reveal latent risks for the DeepPref benchmark curation.","pith_extraction_headline":"CDRA reframes LLM alignment as a critique-driven reasoning process to infer unstated goals, contexts, and risk tolerances."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2510.11194/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":"2a53780c-9319-497a-bcb6-acc29a7cc340"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-04T01:08:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ui4GtD7gU4azzCp1rHScic6VvPhEIAavrO6XOgH6MltSeLICuFcqQA3Jj6FA3/dvTOYeTkGx9KTKohf1T2kTBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T22:12:53.914662Z"},"content_sha256":"e34ccf7d55fb5ab022820a6f6a2c9d7928272362b1ef16b4bc3fea83f36358aa","schema_version":"1.0","event_id":"sha256:e34ccf7d55fb5ab022820a6f6a2c9d7928272362b1ef16b4bc3fea83f36358aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EYDHFGU7MCNEAPBZ7OSMLKHOWB/bundle.json","state_url":"https://pith.science/pith/EYDHFGU7MCNEAPBZ7OSMLKHOWB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EYDHFGU7MCNEAPBZ7OSMLKHOWB/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":"2026-06-06T22:12:53Z","links":{"resolver":"https://pith.science/pith/EYDHFGU7MCNEAPBZ7OSMLKHOWB","bundle":"https://pith.science/pith/EYDHFGU7MCNEAPBZ7OSMLKHOWB/bundle.json","state":"https://pith.science/pith/EYDHFGU7MCNEAPBZ7OSMLKHOWB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EYDHFGU7MCNEAPBZ7OSMLKHOWB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EYDHFGU7MCNEAPBZ7OSMLKHOWB","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":"9c6d763531b86280ef24c8afd4deccbca97e00cdd09dbc5fd42670f8952af77c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-10-13T09:26:47Z","title_canon_sha256":"42a1f70d213108d73d744be0eadf6b378e6fa838a7f71df21bba14d6fae25590"},"schema_version":"1.0","source":{"id":"2510.11194","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.11194","created_at":"2026-06-04T01:08:33Z"},{"alias_kind":"arxiv_version","alias_value":"2510.11194v3","created_at":"2026-06-04T01:08:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.11194","created_at":"2026-06-04T01:08:33Z"},{"alias_kind":"pith_short_12","alias_value":"EYDHFGU7MCNE","created_at":"2026-06-04T01:08:33Z"},{"alias_kind":"pith_short_16","alias_value":"EYDHFGU7MCNEAPBZ","created_at":"2026-06-04T01:08:33Z"},{"alias_kind":"pith_short_8","alias_value":"EYDHFGU7","created_at":"2026-06-04T01:08:33Z"}],"graph_snapshots":[{"event_id":"sha256:e34ccf7d55fb5ab022820a6f6a2c9d7928272362b1ef16b4bc3fea83f36358aa","target":"graph","created_at":"2026-06-04T01:08:33Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experiments demonstrate that CDRA excels at discovering and aligning with users' true preferences while executing robust reasoning."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that a simulated multi-faceted cognitive council can reliably produce critique-annotated reasoning chains that accurately deconstruct query semantics and reveal latent risks for the DeepPref benchmark curation."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CDRA reframes LLM alignment as a critique-driven reasoning process using the DeepPref benchmark and Pers-GenPRM to infer implicit preferences and guide policy via process-level RL."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CDRA reframes LLM alignment as a critique-driven reasoning process to infer unstated goals, contexts, and risk tolerances."}],"snapshot_sha256":"e91c24ba52e64970a228d3d5a66e350a0fb76c1094886baa42c91f765cb16aec"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2510.11194/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current methods face a dual challenge: they fail to infer users' deep implicit preferences (including unstated goals, semantic context and risk tolerances), and they lack the defensive reasoning required to navigate real-world ambiguity. This cognitive gap leads to responses that are superficial, brittle and short-sighted. To address this, we propose Critique-Driven Reasoning Alignment (CDRA), which reframes alignment from a scalar reward-matching task into a","authors_text":"Peiming Li, Shiyu Li, Xi Chen, Yang Tang, Zhiyuan Hu","cross_cats":[],"headline":"CDRA reframes LLM alignment as a critique-driven reasoning process to infer unstated goals, contexts, and risk tolerances.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-10-13T09:26:47Z","title":"Aligning Deep Implicit Preferences by Learning to Reason Defensively"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.11194","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-18T08:07:56.171496Z","id":"2a53780c-9319-497a-bcb6-acc29a7cc340","model_set":{"reader":"grok-4.3"},"one_line_summary":"CDRA reframes LLM alignment as a critique-driven reasoning process using the DeepPref benchmark and Pers-GenPRM to infer implicit preferences and guide policy via process-level RL.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"CDRA reframes LLM alignment as a critique-driven reasoning process to infer unstated goals, contexts, and risk tolerances.","strongest_claim":"Experiments demonstrate that CDRA excels at discovering and aligning with users' true preferences while executing robust reasoning.","weakest_assumption":"The assumption that a simulated multi-faceted cognitive council can reliably produce critique-annotated reasoning chains that accurately deconstruct query semantics and reveal latent risks for the DeepPref benchmark curation."}},"verdict_id":"2a53780c-9319-497a-bcb6-acc29a7cc340"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d9c622d88d35bd1af2bd5d507e904007e5e151abe0bc044b5ecf4f3d215fb9eb","target":"record","created_at":"2026-06-04T01:08:33Z","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":"9c6d763531b86280ef24c8afd4deccbca97e00cdd09dbc5fd42670f8952af77c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-10-13T09:26:47Z","title_canon_sha256":"42a1f70d213108d73d744be0eadf6b378e6fa838a7f71df21bba14d6fae25590"},"schema_version":"1.0","source":{"id":"2510.11194","kind":"arxiv","version":3}},"canonical_sha256":"2606729a9f609a403c39fba4c5a8eeb07bfb38b1b8a44e5b26fdca023ed283de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2606729a9f609a403c39fba4c5a8eeb07bfb38b1b8a44e5b26fdca023ed283de","first_computed_at":"2026-06-04T01:08:33.599423Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:08:33.599423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wAt90CkGUsAnPGHd/5GZQZnvVkL2mOy/Q8CTPNXPcZtkBIDS3GR0Rc+o5fMUk2U8Zea6iZTzajI6Hbh7mYzvCw==","signature_status":"signed_v1","signed_at":"2026-06-04T01:08:33.600279Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.11194","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9c622d88d35bd1af2bd5d507e904007e5e151abe0bc044b5ecf4f3d215fb9eb","sha256:e34ccf7d55fb5ab022820a6f6a2c9d7928272362b1ef16b4bc3fea83f36358aa"],"state_sha256":"f7b0549c4d33b6d8b09e8297b66f57025e9acf15147a65b92037b48e956ba8de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/s6Fo6aebuP8XYG+xaX3w/jb2JXz6D8DTbOMeaTJm3XH581AGmTwfslCkGx/BHiZAcgDt91vT5WZPMfZL4hTDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T22:12:53.919089Z","bundle_sha256":"c98347581c34bda725ccd42b49683a83c5bbd3bb2f2686dc4ecf7337369f3b46"}}