{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:77G2FJQYRV3DUXMP7ET2WYLEWH","short_pith_number":"pith:77G2FJQY","canonical_record":{"source":{"id":"2505.22660","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T17:59:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eb9ed5e636670862faae819e272a7adf2cb1e123c9b6c1477eee363daf8f04d9","abstract_canon_sha256":"a2a0fa73d4e3a0fbd833fc59feae5fada2c0a254d03040241c7b32ff5e723487"},"schema_version":"1.0"},"canonical_sha256":"ffcda2a6188d763a5d8ff927ab6164b1f29d2ca89312a3ea935d69d949ca1023","source":{"kind":"arxiv","id":"2505.22660","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22660","created_at":"2026-07-05T11:28:16Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22660v4","created_at":"2026-07-05T11:28:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22660","created_at":"2026-07-05T11:28:16Z"},{"alias_kind":"pith_short_12","alias_value":"77G2FJQYRV3D","created_at":"2026-07-05T11:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"77G2FJQYRV3DUXMP","created_at":"2026-07-05T11:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"77G2FJQY","created_at":"2026-07-05T11:28:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:77G2FJQYRV3DUXMP7ET2WYLEWH","target":"record","payload":{"canonical_record":{"source":{"id":"2505.22660","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T17:59:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eb9ed5e636670862faae819e272a7adf2cb1e123c9b6c1477eee363daf8f04d9","abstract_canon_sha256":"a2a0fa73d4e3a0fbd833fc59feae5fada2c0a254d03040241c7b32ff5e723487"},"schema_version":"1.0"},"canonical_sha256":"ffcda2a6188d763a5d8ff927ab6164b1f29d2ca89312a3ea935d69d949ca1023","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:16.922191Z","signature_b64":"60QdsJe1RcAcRJi/3+zPtgHhL3RrbPTcoSy+wHGkSpd1G0sXkisl/WhD7MDdIh2ILUVg4wUao+tiN6DSaACaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffcda2a6188d763a5d8ff927ab6164b1f29d2ca89312a3ea935d69d949ca1023","last_reissued_at":"2026-07-05T11:28:16.921551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:16.921551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.22660","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:28:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uun5TmXGfhpmaydd5P5M8KLUnmLtPYTqdubj/eJMUolJ9vtMKV/uyw5nJfO/VtMFdgXmRSDLLxjNfKUMD3mCBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:48:17.041924Z"},"content_sha256":"269e2ae72028651f6f870fd5e0ffdf901f0c532ece53a4601be08bf298852268","schema_version":"1.0","event_id":"sha256:269e2ae72028651f6f870fd5e0ffdf901f0c532ece53a4601be08bf298852268"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:77G2FJQYRV3DUXMP7ET2WYLEWH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Maximizing Confidence Alone Improves Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alex Ippoliti, Deepak Pathak, Hao Liu, Katerina Fragkiadaki, Lili Chen, Mihir Prabhudesai","submitted_at":"2025-05-28T17:59:37Z","abstract_excerpt":"Reinforcement learning (RL) has enabled machine learning models to achieve significant advances in many fields. Most recently, RL has empowered frontier language models to solve challenging math, science, and coding problems. However, central to any RL algorithm is the reward function, and reward engineering is a notoriously difficult problem in any domain. In this paper, we propose RENT: Reinforcement Learning via Entropy Minimization -- a fully unsupervised RL method that requires no external reward or ground-truth answers, and instead uses the model's entropy of its underlying distribution "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22660","kind":"arxiv","version":4},"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/2505.22660/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":"2026-07-05T11:28:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nv3+42XJSn3ZxIuvVAOVK253rkkin+ciFTFArlgcCjXWBzilcVAa3KgNaXS/B82u1q5+LE7ewzo3YZeJQ8pcAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:48:17.042838Z"},"content_sha256":"c8ddcd64f355ba900ba4380adf93b53087a6702f01e998a913c9b944982f6959","schema_version":"1.0","event_id":"sha256:c8ddcd64f355ba900ba4380adf93b53087a6702f01e998a913c9b944982f6959"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/77G2FJQYRV3DUXMP7ET2WYLEWH/bundle.json","state_url":"https://pith.science/pith/77G2FJQYRV3DUXMP7ET2WYLEWH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/77G2FJQYRV3DUXMP7ET2WYLEWH/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":"2026-08-04T17:48:17Z","links":{"resolver":"https://pith.science/pith/77G2FJQYRV3DUXMP7ET2WYLEWH","bundle":"https://pith.science/pith/77G2FJQYRV3DUXMP7ET2WYLEWH/bundle.json","state":"https://pith.science/pith/77G2FJQYRV3DUXMP7ET2WYLEWH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/77G2FJQYRV3DUXMP7ET2WYLEWH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:77G2FJQYRV3DUXMP7ET2WYLEWH","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":"a2a0fa73d4e3a0fbd833fc59feae5fada2c0a254d03040241c7b32ff5e723487","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T17:59:37Z","title_canon_sha256":"eb9ed5e636670862faae819e272a7adf2cb1e123c9b6c1477eee363daf8f04d9"},"schema_version":"1.0","source":{"id":"2505.22660","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22660","created_at":"2026-07-05T11:28:16Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22660v4","created_at":"2026-07-05T11:28:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22660","created_at":"2026-07-05T11:28:16Z"},{"alias_kind":"pith_short_12","alias_value":"77G2FJQYRV3D","created_at":"2026-07-05T11:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"77G2FJQYRV3DUXMP","created_at":"2026-07-05T11:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"77G2FJQY","created_at":"2026-07-05T11:28:16Z"}],"graph_snapshots":[{"event_id":"sha256:c8ddcd64f355ba900ba4380adf93b53087a6702f01e998a913c9b944982f6959","target":"graph","created_at":"2026-07-05T11:28:16Z","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/2505.22660/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has enabled machine learning models to achieve significant advances in many fields. Most recently, RL has empowered frontier language models to solve challenging math, science, and coding problems. However, central to any RL algorithm is the reward function, and reward engineering is a notoriously difficult problem in any domain. In this paper, we propose RENT: Reinforcement Learning via Entropy Minimization -- a fully unsupervised RL method that requires no external reward or ground-truth answers, and instead uses the model's entropy of its underlying distribution ","authors_text":"Alex Ippoliti, Deepak Pathak, Hao Liu, Katerina Fragkiadaki, Lili Chen, Mihir Prabhudesai","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T17:59:37Z","title":"Maximizing Confidence Alone Improves Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22660","kind":"arxiv","version":4},"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":"sha256:269e2ae72028651f6f870fd5e0ffdf901f0c532ece53a4601be08bf298852268","target":"record","created_at":"2026-07-05T11:28:16Z","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":"a2a0fa73d4e3a0fbd833fc59feae5fada2c0a254d03040241c7b32ff5e723487","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T17:59:37Z","title_canon_sha256":"eb9ed5e636670862faae819e272a7adf2cb1e123c9b6c1477eee363daf8f04d9"},"schema_version":"1.0","source":{"id":"2505.22660","kind":"arxiv","version":4}},"canonical_sha256":"ffcda2a6188d763a5d8ff927ab6164b1f29d2ca89312a3ea935d69d949ca1023","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ffcda2a6188d763a5d8ff927ab6164b1f29d2ca89312a3ea935d69d949ca1023","first_computed_at":"2026-07-05T11:28:16.921551Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:16.921551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"60QdsJe1RcAcRJi/3+zPtgHhL3RrbPTcoSy+wHGkSpd1G0sXkisl/WhD7MDdIh2ILUVg4wUao+tiN6DSaACaCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:16.922191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22660","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:269e2ae72028651f6f870fd5e0ffdf901f0c532ece53a4601be08bf298852268","sha256:c8ddcd64f355ba900ba4380adf93b53087a6702f01e998a913c9b944982f6959"],"state_sha256":"44e05fac4a0cbcf72213fe57cc68c2d37afd02c17f1a1849797712230e5ab4c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"twnD0MNc45Rw5El906+rRwAcCz6sdPlni6wiWpGzxLiytnDvz+5Fjplw//XHPyE3AX+li4476hNCfzmxROSmCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:48:17.070971Z","bundle_sha256":"961e95ed016322c934987a00e46b208dd7cb6d29570ccfbee4e4820c2ade974f"}}