{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:L3IWBGBFNRMR2ISGSYHGYN2TIH","short_pith_number":"pith:L3IWBGBF","canonical_record":{"source":{"id":"2505.11718","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-16T22:00:49Z","cross_cats_sorted":[],"title_canon_sha256":"c6ea3bc007e50c206a9e7f904ad12cf494759c0dbcaa5641954d9530ac557406","abstract_canon_sha256":"782a4291a2f99d07809ed9909f91b7a2a6cd795cfa818d578a61bb6fcc5f5e58"},"schema_version":"1.0"},"canonical_sha256":"5ed16098256c591d2246960e6c375341f5c27c29fb827a47cdbf4ec499db3dae","source":{"kind":"arxiv","id":"2505.11718","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11718","created_at":"2026-07-05T11:27:54Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11718v2","created_at":"2026-07-05T11:27:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11718","created_at":"2026-07-05T11:27:54Z"},{"alias_kind":"pith_short_12","alias_value":"L3IWBGBFNRMR","created_at":"2026-07-05T11:27:54Z"},{"alias_kind":"pith_short_16","alias_value":"L3IWBGBFNRMR2ISG","created_at":"2026-07-05T11:27:54Z"},{"alias_kind":"pith_short_8","alias_value":"L3IWBGBF","created_at":"2026-07-05T11:27:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:L3IWBGBFNRMR2ISGSYHGYN2TIH","target":"record","payload":{"canonical_record":{"source":{"id":"2505.11718","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-16T22:00:49Z","cross_cats_sorted":[],"title_canon_sha256":"c6ea3bc007e50c206a9e7f904ad12cf494759c0dbcaa5641954d9530ac557406","abstract_canon_sha256":"782a4291a2f99d07809ed9909f91b7a2a6cd795cfa818d578a61bb6fcc5f5e58"},"schema_version":"1.0"},"canonical_sha256":"5ed16098256c591d2246960e6c375341f5c27c29fb827a47cdbf4ec499db3dae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:54.933064Z","signature_b64":"eAceBVU5CH3CFqYmZIf1z43SWnkX3jvsNS2ttTFV5r0sp5oWiW5q21YHRspTcfhh7Df19CFgYwbPP22KQNV2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ed16098256c591d2246960e6c375341f5c27c29fb827a47cdbf4ec499db3dae","last_reissued_at":"2026-07-05T11:27:54.932508Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:54.932508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.11718","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":"2026-07-05T11:27:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f6GRNWiuISozjXnsrqDGq/iVlfXaz+OL2/m/6n2DrHSBjX0n+q+xewu5UheBfDpDB5Mf2wZkk7zrxLqTo0WNBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T05:46:55.192859Z"},"content_sha256":"b273618372d4e8ff1ede8c61bc5404dc6564c52ac1f5cd0aa76a1ac617237c50","schema_version":"1.0","event_id":"sha256:b273618372d4e8ff1ede8c61bc5404dc6564c52ac1f5cd0aa76a1ac617237c50"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:L3IWBGBFNRMR2ISGSYHGYN2TIH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"REMOR: Automated Peer Review Generation with LLM Reasoning and Multi-Objective Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Daniel Acuna, Pawin Taechoyotin","submitted_at":"2025-05-16T22:00:49Z","abstract_excerpt":"AI-based peer review systems tend to produce shallow and overpraising suggestions compared to human feedback. Here, we evaluate how well a reasoning LLM trained with multi-objective reinforcement learning (REMOR) can overcome these limitations. We start by designing a multi-aspect reward function that aligns with human evaluation of reviews. The aspects are related to the review itself (e.g., criticisms, novelty) and the relationship between the review and the manuscript (i.e., relevance). First, we perform supervised fine-tuning of DeepSeek-R1-Distill-Qwen-7B using LoRA on PeerRT, a new datas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11718","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/2505.11718/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":"2026-07-05T11:27:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zTkd9AfCHI7chIW6PrZTJhD4d9kff6YQ907iu/7nJPdA33GyFne7igBLYFc3sVkl8WEQ7G3AKAdWvymY9M3WAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T05:46:55.193225Z"},"content_sha256":"b248415f9be9196f95d903897b47eacc1e5e12208573859127d161a56483afe5","schema_version":"1.0","event_id":"sha256:b248415f9be9196f95d903897b47eacc1e5e12208573859127d161a56483afe5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L3IWBGBFNRMR2ISGSYHGYN2TIH/bundle.json","state_url":"https://pith.science/pith/L3IWBGBFNRMR2ISGSYHGYN2TIH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L3IWBGBFNRMR2ISGSYHGYN2TIH/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":"2026-07-06T05:46:55Z","links":{"resolver":"https://pith.science/pith/L3IWBGBFNRMR2ISGSYHGYN2TIH","bundle":"https://pith.science/pith/L3IWBGBFNRMR2ISGSYHGYN2TIH/bundle.json","state":"https://pith.science/pith/L3IWBGBFNRMR2ISGSYHGYN2TIH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L3IWBGBFNRMR2ISGSYHGYN2TIH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:L3IWBGBFNRMR2ISGSYHGYN2TIH","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":"782a4291a2f99d07809ed9909f91b7a2a6cd795cfa818d578a61bb6fcc5f5e58","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-16T22:00:49Z","title_canon_sha256":"c6ea3bc007e50c206a9e7f904ad12cf494759c0dbcaa5641954d9530ac557406"},"schema_version":"1.0","source":{"id":"2505.11718","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11718","created_at":"2026-07-05T11:27:54Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11718v2","created_at":"2026-07-05T11:27:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11718","created_at":"2026-07-05T11:27:54Z"},{"alias_kind":"pith_short_12","alias_value":"L3IWBGBFNRMR","created_at":"2026-07-05T11:27:54Z"},{"alias_kind":"pith_short_16","alias_value":"L3IWBGBFNRMR2ISG","created_at":"2026-07-05T11:27:54Z"},{"alias_kind":"pith_short_8","alias_value":"L3IWBGBF","created_at":"2026-07-05T11:27:54Z"}],"graph_snapshots":[{"event_id":"sha256:b248415f9be9196f95d903897b47eacc1e5e12208573859127d161a56483afe5","target":"graph","created_at":"2026-07-05T11:27:54Z","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/2505.11718/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"AI-based peer review systems tend to produce shallow and overpraising suggestions compared to human feedback. Here, we evaluate how well a reasoning LLM trained with multi-objective reinforcement learning (REMOR) can overcome these limitations. We start by designing a multi-aspect reward function that aligns with human evaluation of reviews. The aspects are related to the review itself (e.g., criticisms, novelty) and the relationship between the review and the manuscript (i.e., relevance). First, we perform supervised fine-tuning of DeepSeek-R1-Distill-Qwen-7B using LoRA on PeerRT, a new datas","authors_text":"Daniel Acuna, Pawin Taechoyotin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-16T22:00:49Z","title":"REMOR: Automated Peer Review Generation with LLM Reasoning and Multi-Objective Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11718","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:b273618372d4e8ff1ede8c61bc5404dc6564c52ac1f5cd0aa76a1ac617237c50","target":"record","created_at":"2026-07-05T11:27:54Z","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":"782a4291a2f99d07809ed9909f91b7a2a6cd795cfa818d578a61bb6fcc5f5e58","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-16T22:00:49Z","title_canon_sha256":"c6ea3bc007e50c206a9e7f904ad12cf494759c0dbcaa5641954d9530ac557406"},"schema_version":"1.0","source":{"id":"2505.11718","kind":"arxiv","version":2}},"canonical_sha256":"5ed16098256c591d2246960e6c375341f5c27c29fb827a47cdbf4ec499db3dae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ed16098256c591d2246960e6c375341f5c27c29fb827a47cdbf4ec499db3dae","first_computed_at":"2026-07-05T11:27:54.932508Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:54.932508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eAceBVU5CH3CFqYmZIf1z43SWnkX3jvsNS2ttTFV5r0sp5oWiW5q21YHRspTcfhh7Df19CFgYwbPP22KQNV2Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:54.933064Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11718","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b273618372d4e8ff1ede8c61bc5404dc6564c52ac1f5cd0aa76a1ac617237c50","sha256:b248415f9be9196f95d903897b47eacc1e5e12208573859127d161a56483afe5"],"state_sha256":"7341358de76001d3cf5aece667ebe496fdc4a18c19668be95f0bfeb174d52afa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"11xQ8stNcECge5F/qDns1nPtRnK34mgGd9qZL7AqPccq1+PS6EeQ2yq0Jz/bryPXHbJ8WuTRIp95fypzwmpPAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T05:46:55.195345Z","bundle_sha256":"e0fbf790e1c9214dcdf3d692306a75e082098b43231ea117d2303369261da37d"}}