{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IEX2FZZEKAHOV745IHI3264HNC","short_pith_number":"pith:IEX2FZZE","canonical_record":{"source":{"id":"2501.17030","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-28T15:52:51Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CR"],"title_canon_sha256":"5612d7a334bd1c3294022241af9802dab2e9418983268c085d23fe8eb5c7ec6b","abstract_canon_sha256":"2cbf31adfa0c4f827760db10fe3e369735057b8357c440433c95aeb5369b0b64"},"schema_version":"1.0"},"canonical_sha256":"412fa2e724500eeaff9d41d1bd7b876893208306f6a8ab0716e80a7f46fcc652","source":{"kind":"arxiv","id":"2501.17030","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.17030","created_at":"2026-07-05T10:06:21Z"},{"alias_kind":"arxiv_version","alias_value":"2501.17030v1","created_at":"2026-07-05T10:06:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17030","created_at":"2026-07-05T10:06:21Z"},{"alias_kind":"pith_short_12","alias_value":"IEX2FZZEKAHO","created_at":"2026-07-05T10:06:21Z"},{"alias_kind":"pith_short_16","alias_value":"IEX2FZZEKAHOV745","created_at":"2026-07-05T10:06:21Z"},{"alias_kind":"pith_short_8","alias_value":"IEX2FZZE","created_at":"2026-07-05T10:06:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IEX2FZZEKAHOV745IHI3264HNC","target":"record","payload":{"canonical_record":{"source":{"id":"2501.17030","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-28T15:52:51Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CR"],"title_canon_sha256":"5612d7a334bd1c3294022241af9802dab2e9418983268c085d23fe8eb5c7ec6b","abstract_canon_sha256":"2cbf31adfa0c4f827760db10fe3e369735057b8357c440433c95aeb5369b0b64"},"schema_version":"1.0"},"canonical_sha256":"412fa2e724500eeaff9d41d1bd7b876893208306f6a8ab0716e80a7f46fcc652","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:21.870443Z","signature_b64":"ME6ACS+U+TlXo9ZIfHRyF8zZzsUtPhocdjII8ZI4Gy9VPdkxadJN5mM4XPve5ThSGAZkJAWKBH9+cLAr0zUBCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"412fa2e724500eeaff9d41d1bd7b876893208306f6a8ab0716e80a7f46fcc652","last_reissued_at":"2026-07-05T10:06:21.870024Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:21.870024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.17030","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":"2026-07-05T10:06:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uBNZGoqUa57aN3neLZa1xuh+N0IuoH98JLr5RxZ63zlBg4YJiPFkKNzI5dHA1fRmzytCe4osiOzKeQb2Sg/nBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T22:15:22.600525Z"},"content_sha256":"0537a77dd92bcb378212d6ec7e190b279a8a1f0cf274208c5dad987f952c74c8","schema_version":"1.0","event_id":"sha256:0537a77dd92bcb378212d6ec7e190b279a8a1f0cf274208c5dad987f952c74c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IEX2FZZEKAHOV745IHI3264HNC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CR"],"primary_cat":"cs.LG","authors_text":"Manojkumar Parmar, Yuvaraj Govindarajulu","submitted_at":"2025-01-28T15:52:51Z","abstract_excerpt":"Large Language Models (LLMs) have achieved remarkable progress in reasoning, alignment, and task-specific performance. However, ensuring harmlessness in these systems remains a critical challenge, particularly in advanced models like DeepSeek-R1. This paper examines the limitations of Reinforcement Learning (RL) as the primary approach for reducing harmful outputs in DeepSeek-R1 and compares it with Supervised Fine-Tuning (SFT). While RL improves reasoning capabilities, it faces challenges such as reward hacking, generalization failures, language mixing, and high computational costs. We propos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17030","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/2501.17030/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":"2026-07-05T10:06:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4QftWtl97XUaSo28g8nQ1/NKBbQfhjj5VjfkeZmITsoa8jeOVqu5VOC/ypb1O42wsgndQ0eEWQ6xnYuUNZtkDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T22:15:22.601536Z"},"content_sha256":"456df6e807bec51a91581dcf15bc2f7335381cc558212093ec085a0b55f844c5","schema_version":"1.0","event_id":"sha256:456df6e807bec51a91581dcf15bc2f7335381cc558212093ec085a0b55f844c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IEX2FZZEKAHOV745IHI3264HNC/bundle.json","state_url":"https://pith.science/pith/IEX2FZZEKAHOV745IHI3264HNC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IEX2FZZEKAHOV745IHI3264HNC/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":"2026-08-15T22:15:22Z","links":{"resolver":"https://pith.science/pith/IEX2FZZEKAHOV745IHI3264HNC","bundle":"https://pith.science/pith/IEX2FZZEKAHOV745IHI3264HNC/bundle.json","state":"https://pith.science/pith/IEX2FZZEKAHOV745IHI3264HNC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IEX2FZZEKAHOV745IHI3264HNC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IEX2FZZEKAHOV745IHI3264HNC","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":"2cbf31adfa0c4f827760db10fe3e369735057b8357c440433c95aeb5369b0b64","cross_cats_sorted":["cs.AI","cs.CL","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-28T15:52:51Z","title_canon_sha256":"5612d7a334bd1c3294022241af9802dab2e9418983268c085d23fe8eb5c7ec6b"},"schema_version":"1.0","source":{"id":"2501.17030","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.17030","created_at":"2026-07-05T10:06:21Z"},{"alias_kind":"arxiv_version","alias_value":"2501.17030v1","created_at":"2026-07-05T10:06:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17030","created_at":"2026-07-05T10:06:21Z"},{"alias_kind":"pith_short_12","alias_value":"IEX2FZZEKAHO","created_at":"2026-07-05T10:06:21Z"},{"alias_kind":"pith_short_16","alias_value":"IEX2FZZEKAHOV745","created_at":"2026-07-05T10:06:21Z"},{"alias_kind":"pith_short_8","alias_value":"IEX2FZZE","created_at":"2026-07-05T10:06:21Z"}],"graph_snapshots":[{"event_id":"sha256:456df6e807bec51a91581dcf15bc2f7335381cc558212093ec085a0b55f844c5","target":"graph","created_at":"2026-07-05T10:06:21Z","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/2501.17030/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have achieved remarkable progress in reasoning, alignment, and task-specific performance. However, ensuring harmlessness in these systems remains a critical challenge, particularly in advanced models like DeepSeek-R1. This paper examines the limitations of Reinforcement Learning (RL) as the primary approach for reducing harmful outputs in DeepSeek-R1 and compares it with Supervised Fine-Tuning (SFT). While RL improves reasoning capabilities, it faces challenges such as reward hacking, generalization failures, language mixing, and high computational costs. We propos","authors_text":"Manojkumar Parmar, Yuvaraj Govindarajulu","cross_cats":["cs.AI","cs.CL","cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-28T15:52:51Z","title":"Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17030","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":"sha256:0537a77dd92bcb378212d6ec7e190b279a8a1f0cf274208c5dad987f952c74c8","target":"record","created_at":"2026-07-05T10:06:21Z","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":"2cbf31adfa0c4f827760db10fe3e369735057b8357c440433c95aeb5369b0b64","cross_cats_sorted":["cs.AI","cs.CL","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-28T15:52:51Z","title_canon_sha256":"5612d7a334bd1c3294022241af9802dab2e9418983268c085d23fe8eb5c7ec6b"},"schema_version":"1.0","source":{"id":"2501.17030","kind":"arxiv","version":1}},"canonical_sha256":"412fa2e724500eeaff9d41d1bd7b876893208306f6a8ab0716e80a7f46fcc652","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"412fa2e724500eeaff9d41d1bd7b876893208306f6a8ab0716e80a7f46fcc652","first_computed_at":"2026-07-05T10:06:21.870024Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:06:21.870024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ME6ACS+U+TlXo9ZIfHRyF8zZzsUtPhocdjII8ZI4Gy9VPdkxadJN5mM4XPve5ThSGAZkJAWKBH9+cLAr0zUBCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:06:21.870443Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.17030","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0537a77dd92bcb378212d6ec7e190b279a8a1f0cf274208c5dad987f952c74c8","sha256:456df6e807bec51a91581dcf15bc2f7335381cc558212093ec085a0b55f844c5"],"state_sha256":"f683a5fe9bb99ae397ef32b21c16cefd99b31ee8c9f2941ae7297f92591e18e2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yx57naVzhBe6BWeYxB82peTaziFObdVc2s54sjyWqhArTrXUYsMeW/c27f1k1xmXO2bUnGv+iQWKrIOi38ByDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T22:15:22.609281Z","bundle_sha256":"e0e084e91a21f749533b52137ccce5d083e830a0f83e77b6cc2655ab022f0f9b"}}