{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:X3FYPPVPN7NQANBN3KEA2Y7NNY","short_pith_number":"pith:X3FYPPVP","canonical_record":{"source":{"id":"2507.07017","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-09T16:45:48Z","cross_cats_sorted":[],"title_canon_sha256":"66deef57854505250fdfcfb710680ff60d1ebbbfab7752a6ecb4cbb24ddbfcf3","abstract_canon_sha256":"a9ec6588526ea91b1e1940d9987a3110411e9cda9c0d906c991583a902458671"},"schema_version":"1.0"},"canonical_sha256":"becb87beaf6fdb00342dda880d63ed6e3f18be26e1701fd72761023592ef4fa7","source":{"kind":"arxiv","id":"2507.07017","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07017","created_at":"2026-07-05T11:34:27Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07017v1","created_at":"2026-07-05T11:34:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07017","created_at":"2026-07-05T11:34:27Z"},{"alias_kind":"pith_short_12","alias_value":"X3FYPPVPN7NQ","created_at":"2026-07-05T11:34:27Z"},{"alias_kind":"pith_short_16","alias_value":"X3FYPPVPN7NQANBN","created_at":"2026-07-05T11:34:27Z"},{"alias_kind":"pith_short_8","alias_value":"X3FYPPVP","created_at":"2026-07-05T11:34:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:X3FYPPVPN7NQANBN3KEA2Y7NNY","target":"record","payload":{"canonical_record":{"source":{"id":"2507.07017","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-09T16:45:48Z","cross_cats_sorted":[],"title_canon_sha256":"66deef57854505250fdfcfb710680ff60d1ebbbfab7752a6ecb4cbb24ddbfcf3","abstract_canon_sha256":"a9ec6588526ea91b1e1940d9987a3110411e9cda9c0d906c991583a902458671"},"schema_version":"1.0"},"canonical_sha256":"becb87beaf6fdb00342dda880d63ed6e3f18be26e1701fd72761023592ef4fa7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:27.859756Z","signature_b64":"tLqIigC0bl1WcQWTrmrB3OuEWvQnN076VZXpxg9lzdoMV2f7FkvsytklRXEOHjr+yQSIxQQkQwShYkJcIerBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"becb87beaf6fdb00342dda880d63ed6e3f18be26e1701fd72761023592ef4fa7","last_reissued_at":"2026-07-05T11:34:27.859280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:27.859280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.07017","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":"2026-07-05T11:34:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iiWzS9UWlPZd827TlodHZXnfHha7JiqKxRsZB7AotOPqIHrYnWOK6rbMoZqGnARetEEWTWkejKZgf7eB6ko5Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:30:49.486949Z"},"content_sha256":"8ebcd038554b71ce20bd0dcd5ecb81d489b5ebf1c9abf79138ecf1fbcd7df8db","schema_version":"1.0","event_id":"sha256:8ebcd038554b71ce20bd0dcd5ecb81d489b5ebf1c9abf79138ecf1fbcd7df8db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:X3FYPPVPN7NQANBN3KEA2Y7NNY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"First Return, Entropy-Eliciting Explore","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenghua Lin, Ge Zhang, Qian Liu, Qingshui Gu, Taoran Liang, Tianshun Xing, Tianyu Zheng, Wenhao Huang, Xingwei Qu, Xin Zhou, Yizhi Li, Zejun Ma, Zhoufutu Wen","submitted_at":"2025-07-09T16:45:48Z","abstract_excerpt":"Reinforcement Learning from Verifiable Rewards (RLVR) improves the reasoning abilities of Large Language Models (LLMs) but it struggles with unstable exploration. We propose FR3E (First Return, Entropy-Eliciting Explore), a structured exploration framework that identifies high-uncertainty decision points in reasoning trajectories and performs targeted rollouts to construct semantically grounded intermediate feedback. Our method provides targeted guidance without relying on dense supervision. Empirical results on mathematical reasoning benchmarks(AIME24) show that FR3E promotes more stable trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07017","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/2507.07017/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":"2026-07-05T11:34:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NksxN2nbuuBpe7jUXS4sNXG6U2Mv5KqiKnRhOojSa71gAFa735IjSau7nmNkLbJvr3lMKljIjiJLYmBwi1RGAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:30:49.487346Z"},"content_sha256":"01c5bf3d77ab475a5c1aedfcc91f9264c70cdb3980973c62117ff39d70c38455","schema_version":"1.0","event_id":"sha256:01c5bf3d77ab475a5c1aedfcc91f9264c70cdb3980973c62117ff39d70c38455"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X3FYPPVPN7NQANBN3KEA2Y7NNY/bundle.json","state_url":"https://pith.science/pith/X3FYPPVPN7NQANBN3KEA2Y7NNY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X3FYPPVPN7NQANBN3KEA2Y7NNY/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":"2026-08-06T13:30:49Z","links":{"resolver":"https://pith.science/pith/X3FYPPVPN7NQANBN3KEA2Y7NNY","bundle":"https://pith.science/pith/X3FYPPVPN7NQANBN3KEA2Y7NNY/bundle.json","state":"https://pith.science/pith/X3FYPPVPN7NQANBN3KEA2Y7NNY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X3FYPPVPN7NQANBN3KEA2Y7NNY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:X3FYPPVPN7NQANBN3KEA2Y7NNY","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":"a9ec6588526ea91b1e1940d9987a3110411e9cda9c0d906c991583a902458671","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-09T16:45:48Z","title_canon_sha256":"66deef57854505250fdfcfb710680ff60d1ebbbfab7752a6ecb4cbb24ddbfcf3"},"schema_version":"1.0","source":{"id":"2507.07017","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07017","created_at":"2026-07-05T11:34:27Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07017v1","created_at":"2026-07-05T11:34:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07017","created_at":"2026-07-05T11:34:27Z"},{"alias_kind":"pith_short_12","alias_value":"X3FYPPVPN7NQ","created_at":"2026-07-05T11:34:27Z"},{"alias_kind":"pith_short_16","alias_value":"X3FYPPVPN7NQANBN","created_at":"2026-07-05T11:34:27Z"},{"alias_kind":"pith_short_8","alias_value":"X3FYPPVP","created_at":"2026-07-05T11:34:27Z"}],"graph_snapshots":[{"event_id":"sha256:01c5bf3d77ab475a5c1aedfcc91f9264c70cdb3980973c62117ff39d70c38455","target":"graph","created_at":"2026-07-05T11:34:27Z","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/2507.07017/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Verifiable Rewards (RLVR) improves the reasoning abilities of Large Language Models (LLMs) but it struggles with unstable exploration. We propose FR3E (First Return, Entropy-Eliciting Explore), a structured exploration framework that identifies high-uncertainty decision points in reasoning trajectories and performs targeted rollouts to construct semantically grounded intermediate feedback. Our method provides targeted guidance without relying on dense supervision. Empirical results on mathematical reasoning benchmarks(AIME24) show that FR3E promotes more stable trai","authors_text":"Chenghua Lin, Ge Zhang, Qian Liu, Qingshui Gu, Taoran Liang, Tianshun Xing, Tianyu Zheng, Wenhao Huang, Xingwei Qu, Xin Zhou, Yizhi Li, Zejun Ma, Zhoufutu Wen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-09T16:45:48Z","title":"First Return, Entropy-Eliciting Explore"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07017","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":"sha256:8ebcd038554b71ce20bd0dcd5ecb81d489b5ebf1c9abf79138ecf1fbcd7df8db","target":"record","created_at":"2026-07-05T11:34:27Z","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":"a9ec6588526ea91b1e1940d9987a3110411e9cda9c0d906c991583a902458671","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-09T16:45:48Z","title_canon_sha256":"66deef57854505250fdfcfb710680ff60d1ebbbfab7752a6ecb4cbb24ddbfcf3"},"schema_version":"1.0","source":{"id":"2507.07017","kind":"arxiv","version":1}},"canonical_sha256":"becb87beaf6fdb00342dda880d63ed6e3f18be26e1701fd72761023592ef4fa7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"becb87beaf6fdb00342dda880d63ed6e3f18be26e1701fd72761023592ef4fa7","first_computed_at":"2026-07-05T11:34:27.859280Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:27.859280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tLqIigC0bl1WcQWTrmrB3OuEWvQnN076VZXpxg9lzdoMV2f7FkvsytklRXEOHjr+yQSIxQQkQwShYkJcIerBDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:27.859756Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.07017","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ebcd038554b71ce20bd0dcd5ecb81d489b5ebf1c9abf79138ecf1fbcd7df8db","sha256:01c5bf3d77ab475a5c1aedfcc91f9264c70cdb3980973c62117ff39d70c38455"],"state_sha256":"ab96b82f4cf83456be9324f551b88673d878dabb551f6a39d55dc22b91784e06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pjCann7/O9Ee0BOlAEC9yqhOQex6XqPJseLI63WEXg51cTmW2/PCGitOCCp7EhqDCTHNzuph1T8eUgh3zcYhDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T13:30:49.499347Z","bundle_sha256":"8a3ff6eeda9134a07af355ce9e4fb2cabb2c2617fdc64cccdf22ad5bff6da301"}}