{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VKWBDRDN5V43BYDFJ7IVWOU4R3","short_pith_number":"pith:VKWBDRDN","canonical_record":{"source":{"id":"2504.05812","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-08T08:48:51Z","cross_cats_sorted":[],"title_canon_sha256":"bd57732c67e4d439643093817238492cf7391781e935ec675a9a893a235f0b02","abstract_canon_sha256":"967f54c79c1b628e649fd1eefbe579464bda967aae2e80236b6416fd01b57444"},"schema_version":"1.0"},"canonical_sha256":"aaac11c46ded79b0e0654fd15b3a9c8ec977213dd016df9d9bf489cd7f472a91","source":{"kind":"arxiv","id":"2504.05812","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.05812","created_at":"2026-07-05T11:04:48Z"},{"alias_kind":"arxiv_version","alias_value":"2504.05812v3","created_at":"2026-07-05T11:04:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05812","created_at":"2026-07-05T11:04:48Z"},{"alias_kind":"pith_short_12","alias_value":"VKWBDRDN5V43","created_at":"2026-07-05T11:04:48Z"},{"alias_kind":"pith_short_16","alias_value":"VKWBDRDN5V43BYDF","created_at":"2026-07-05T11:04:48Z"},{"alias_kind":"pith_short_8","alias_value":"VKWBDRDN","created_at":"2026-07-05T11:04:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VKWBDRDN5V43BYDFJ7IVWOU4R3","target":"record","payload":{"canonical_record":{"source":{"id":"2504.05812","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-08T08:48:51Z","cross_cats_sorted":[],"title_canon_sha256":"bd57732c67e4d439643093817238492cf7391781e935ec675a9a893a235f0b02","abstract_canon_sha256":"967f54c79c1b628e649fd1eefbe579464bda967aae2e80236b6416fd01b57444"},"schema_version":"1.0"},"canonical_sha256":"aaac11c46ded79b0e0654fd15b3a9c8ec977213dd016df9d9bf489cd7f472a91","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:48.741539Z","signature_b64":"Qy4hP2aN8DO+caCQOmmc1eTm73nZNOZm+tRU9dXyh5ELm1xA36R4p9lLr88IH2oHTjSnrCgLMiVBJeCGESmaAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aaac11c46ded79b0e0654fd15b3a9c8ec977213dd016df9d9bf489cd7f472a91","last_reissued_at":"2026-07-05T11:04:48.740791Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:48.740791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.05812","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":"2026-07-05T11:04:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dQmX33ULiouOsCWIzzojsPxLT7Gv7mlrMarYd70uEULlcDbhnrzSAIl/xpJOg0taSlJNNkxJkQp63eq8NkkzDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T11:22:26.154591Z"},"content_sha256":"025003e7805e6f4bef6bbf302ebc4fcf80717ff095cccf27f65e56986512a1f2","schema_version":"1.0","event_id":"sha256:025003e7805e6f4bef6bbf302ebc4fcf80717ff095cccf27f65e56986512a1f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VKWBDRDN5V43BYDFJ7IVWOU4R3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Changqing Zhang, Haitao Wu, Peilin Zhao, Qingyang Zhang, Yatao Bian","submitted_at":"2025-04-08T08:48:51Z","abstract_excerpt":"Existing methods to enhance the reasoning capability of large language models predominantly rely on supervised fine-tuning (SFT) followed by reinforcement learning (RL) on reasoning-specific data. These approaches critically depend on external supervisions--such as labeled reasoning traces, verified golden answers, or pre-trained reward models. In this work, we propose Entropy Minimized Policy Optimization (\\ours), which makes an early attempt at fully unsupervised LLM reasoning incentivization. By continuously minimizing the predictive entropy of LLMs on unlabeled questions in a latent semant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05812","kind":"arxiv","version":3},"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/2504.05812/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":"2026-07-05T11:04:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vxe0u4uBtQS0ZFDM+eV3mEm5+EBmOuvoMhkMQsceUs0q+vqZu9/s8iYDNUaeyqHJFC7cu7IgAz9FvEXlJIixCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T11:22:26.154973Z"},"content_sha256":"c56ab4e2f5f7597f1ebb3a3479860775d39077a21660ae9a96bc7232a0957e03","schema_version":"1.0","event_id":"sha256:c56ab4e2f5f7597f1ebb3a3479860775d39077a21660ae9a96bc7232a0957e03"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VKWBDRDN5V43BYDFJ7IVWOU4R3/bundle.json","state_url":"https://pith.science/pith/VKWBDRDN5V43BYDFJ7IVWOU4R3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VKWBDRDN5V43BYDFJ7IVWOU4R3/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":"2026-07-11T11:22:26Z","links":{"resolver":"https://pith.science/pith/VKWBDRDN5V43BYDFJ7IVWOU4R3","bundle":"https://pith.science/pith/VKWBDRDN5V43BYDFJ7IVWOU4R3/bundle.json","state":"https://pith.science/pith/VKWBDRDN5V43BYDFJ7IVWOU4R3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VKWBDRDN5V43BYDFJ7IVWOU4R3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VKWBDRDN5V43BYDFJ7IVWOU4R3","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":"967f54c79c1b628e649fd1eefbe579464bda967aae2e80236b6416fd01b57444","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-08T08:48:51Z","title_canon_sha256":"bd57732c67e4d439643093817238492cf7391781e935ec675a9a893a235f0b02"},"schema_version":"1.0","source":{"id":"2504.05812","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.05812","created_at":"2026-07-05T11:04:48Z"},{"alias_kind":"arxiv_version","alias_value":"2504.05812v3","created_at":"2026-07-05T11:04:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05812","created_at":"2026-07-05T11:04:48Z"},{"alias_kind":"pith_short_12","alias_value":"VKWBDRDN5V43","created_at":"2026-07-05T11:04:48Z"},{"alias_kind":"pith_short_16","alias_value":"VKWBDRDN5V43BYDF","created_at":"2026-07-05T11:04:48Z"},{"alias_kind":"pith_short_8","alias_value":"VKWBDRDN","created_at":"2026-07-05T11:04:48Z"}],"graph_snapshots":[{"event_id":"sha256:c56ab4e2f5f7597f1ebb3a3479860775d39077a21660ae9a96bc7232a0957e03","target":"graph","created_at":"2026-07-05T11:04:48Z","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/2504.05812/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing methods to enhance the reasoning capability of large language models predominantly rely on supervised fine-tuning (SFT) followed by reinforcement learning (RL) on reasoning-specific data. These approaches critically depend on external supervisions--such as labeled reasoning traces, verified golden answers, or pre-trained reward models. In this work, we propose Entropy Minimized Policy Optimization (\\ours), which makes an early attempt at fully unsupervised LLM reasoning incentivization. By continuously minimizing the predictive entropy of LLMs on unlabeled questions in a latent semant","authors_text":"Changqing Zhang, Haitao Wu, Peilin Zhao, Qingyang Zhang, Yatao Bian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-08T08:48:51Z","title":"Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05812","kind":"arxiv","version":3},"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":"sha256:025003e7805e6f4bef6bbf302ebc4fcf80717ff095cccf27f65e56986512a1f2","target":"record","created_at":"2026-07-05T11:04:48Z","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":"967f54c79c1b628e649fd1eefbe579464bda967aae2e80236b6416fd01b57444","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-08T08:48:51Z","title_canon_sha256":"bd57732c67e4d439643093817238492cf7391781e935ec675a9a893a235f0b02"},"schema_version":"1.0","source":{"id":"2504.05812","kind":"arxiv","version":3}},"canonical_sha256":"aaac11c46ded79b0e0654fd15b3a9c8ec977213dd016df9d9bf489cd7f472a91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aaac11c46ded79b0e0654fd15b3a9c8ec977213dd016df9d9bf489cd7f472a91","first_computed_at":"2026-07-05T11:04:48.740791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:48.740791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qy4hP2aN8DO+caCQOmmc1eTm73nZNOZm+tRU9dXyh5ELm1xA36R4p9lLr88IH2oHTjSnrCgLMiVBJeCGESmaAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:48.741539Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.05812","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:025003e7805e6f4bef6bbf302ebc4fcf80717ff095cccf27f65e56986512a1f2","sha256:c56ab4e2f5f7597f1ebb3a3479860775d39077a21660ae9a96bc7232a0957e03"],"state_sha256":"9e2b844e9836bf05f5a2fb24f96de8b56f0c0c49f4742b7d00631fccb70b6456"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nYnE82NR9u7hOBvQRc21jjFcK87MsGxGxAVvnVMjcsojZUVC8FumUkIkSm7arnWE6Cjgakxi19gzaAcj4kkCDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T11:22:26.157438Z","bundle_sha256":"222a96dca72948264d32c533f07f8eec35f375fb6b26de34426360e7a5ded38e"}}