{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HI3CC773XWBM4OEKKB7ZYK2F4M","short_pith_number":"pith:HI3CC773","canonical_record":{"source":{"id":"2508.11356","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-15T09:49:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e15a7583072feae9237905972922d763ebacea3f3a20a6eae1fb715c80c53d64","abstract_canon_sha256":"e089b8a2f347b0018a59e2aed2db0afff1d71f046579d9d122db6496eec58ef5"},"schema_version":"1.0"},"canonical_sha256":"3a36217ffbbd82ce388a507f9c2b45e3289659d060397fa309a999bd05706215","source":{"kind":"arxiv","id":"2508.11356","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.11356","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"arxiv_version","alias_value":"2508.11356v2","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11356","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"pith_short_12","alias_value":"HI3CC773XWBM","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"pith_short_16","alias_value":"HI3CC773XWBM4OEK","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"pith_short_8","alias_value":"HI3CC773","created_at":"2026-07-05T12:01:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HI3CC773XWBM4OEKKB7ZYK2F4M","target":"record","payload":{"canonical_record":{"source":{"id":"2508.11356","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-15T09:49:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e15a7583072feae9237905972922d763ebacea3f3a20a6eae1fb715c80c53d64","abstract_canon_sha256":"e089b8a2f347b0018a59e2aed2db0afff1d71f046579d9d122db6496eec58ef5"},"schema_version":"1.0"},"canonical_sha256":"3a36217ffbbd82ce388a507f9c2b45e3289659d060397fa309a999bd05706215","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:25.460791Z","signature_b64":"OibeBA0T9+TFwdAPeKW3TtaD5AiksUdiP8XGXphHOgjDuqEa5Pv+dd7r/+5Zu1kiWm7pY1gtnw1lGkegAO83BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a36217ffbbd82ce388a507f9c2b45e3289659d060397fa309a999bd05706215","last_reissued_at":"2026-07-05T12:01:25.460304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:25.460304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.11356","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":"2026-07-05T12:01:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K5ybDrQy05mtxLW0VznADK/zQyQkg1Dp3H8kA+cccjuJw9+84iknHzIBjrlARWxnaGOEjSb8F1O589iAOwxUAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:11:27.529110Z"},"content_sha256":"8c25cd34ea175c2b2633e579f4736113119e84b734c2338d9251e67209d5797f","schema_version":"1.0","event_id":"sha256:8c25cd34ea175c2b2633e579f4736113119e84b734c2338d9251e67209d5797f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HI3CC773XWBM4OEKKB7ZYK2F4M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ETTRL: Balancing Exploration and Exploitation in LLM Test-Time Reinforcement Learning Via Entropy Mechanism","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changyi He, Feiyang Shen, Jia Liu, Mingmin Yang, Shaoguo Liu, Yingqiao Lin","submitted_at":"2025-08-15T09:49:14Z","abstract_excerpt":"Recent advancements in Large Language Models have yielded significant improvements in complex reasoning tasks such as mathematics and programming. However, these models remain heavily dependent on annotated data and exhibit limited adaptability in unsupervised scenarios. To address these limitations, test-time reinforcement learning (TTRL) has been proposed, which enables self-optimization by leveraging model-generated pseudo-labels. Despite its promise, TTRL faces several key challenges, including high inference costs due to parallel rollouts and early-stage estimation bias that fosters overc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11356","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/2508.11356/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":"2026-07-05T12:01:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cXDGht/Uk1d1k3ZbHCg0luguug2cxLN0fOJkHOYzrGuoePSdnVQxodP/hGnAY6HYlNGWquPff3t1YGjRtr07Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:11:27.530152Z"},"content_sha256":"ade84e72f0a967ff1b5401d9b43c30a7278735910397ff4c9796f01120830e5d","schema_version":"1.0","event_id":"sha256:ade84e72f0a967ff1b5401d9b43c30a7278735910397ff4c9796f01120830e5d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HI3CC773XWBM4OEKKB7ZYK2F4M/bundle.json","state_url":"https://pith.science/pith/HI3CC773XWBM4OEKKB7ZYK2F4M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HI3CC773XWBM4OEKKB7ZYK2F4M/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":"2026-08-18T01:11:27Z","links":{"resolver":"https://pith.science/pith/HI3CC773XWBM4OEKKB7ZYK2F4M","bundle":"https://pith.science/pith/HI3CC773XWBM4OEKKB7ZYK2F4M/bundle.json","state":"https://pith.science/pith/HI3CC773XWBM4OEKKB7ZYK2F4M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HI3CC773XWBM4OEKKB7ZYK2F4M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HI3CC773XWBM4OEKKB7ZYK2F4M","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":"e089b8a2f347b0018a59e2aed2db0afff1d71f046579d9d122db6496eec58ef5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-15T09:49:14Z","title_canon_sha256":"e15a7583072feae9237905972922d763ebacea3f3a20a6eae1fb715c80c53d64"},"schema_version":"1.0","source":{"id":"2508.11356","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.11356","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"arxiv_version","alias_value":"2508.11356v2","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11356","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"pith_short_12","alias_value":"HI3CC773XWBM","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"pith_short_16","alias_value":"HI3CC773XWBM4OEK","created_at":"2026-07-05T12:01:25Z"},{"alias_kind":"pith_short_8","alias_value":"HI3CC773","created_at":"2026-07-05T12:01:25Z"}],"graph_snapshots":[{"event_id":"sha256:ade84e72f0a967ff1b5401d9b43c30a7278735910397ff4c9796f01120830e5d","target":"graph","created_at":"2026-07-05T12:01:25Z","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/2508.11356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Large Language Models have yielded significant improvements in complex reasoning tasks such as mathematics and programming. However, these models remain heavily dependent on annotated data and exhibit limited adaptability in unsupervised scenarios. To address these limitations, test-time reinforcement learning (TTRL) has been proposed, which enables self-optimization by leveraging model-generated pseudo-labels. Despite its promise, TTRL faces several key challenges, including high inference costs due to parallel rollouts and early-stage estimation bias that fosters overc","authors_text":"Changyi He, Feiyang Shen, Jia Liu, Mingmin Yang, Shaoguo Liu, Yingqiao Lin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-15T09:49:14Z","title":"ETTRL: Balancing Exploration and Exploitation in LLM Test-Time Reinforcement Learning Via Entropy Mechanism"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11356","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":"sha256:8c25cd34ea175c2b2633e579f4736113119e84b734c2338d9251e67209d5797f","target":"record","created_at":"2026-07-05T12:01:25Z","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":"e089b8a2f347b0018a59e2aed2db0afff1d71f046579d9d122db6496eec58ef5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-15T09:49:14Z","title_canon_sha256":"e15a7583072feae9237905972922d763ebacea3f3a20a6eae1fb715c80c53d64"},"schema_version":"1.0","source":{"id":"2508.11356","kind":"arxiv","version":2}},"canonical_sha256":"3a36217ffbbd82ce388a507f9c2b45e3289659d060397fa309a999bd05706215","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a36217ffbbd82ce388a507f9c2b45e3289659d060397fa309a999bd05706215","first_computed_at":"2026-07-05T12:01:25.460304Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:25.460304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OibeBA0T9+TFwdAPeKW3TtaD5AiksUdiP8XGXphHOgjDuqEa5Pv+dd7r/+5Zu1kiWm7pY1gtnw1lGkegAO83BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:25.460791Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.11356","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c25cd34ea175c2b2633e579f4736113119e84b734c2338d9251e67209d5797f","sha256:ade84e72f0a967ff1b5401d9b43c30a7278735910397ff4c9796f01120830e5d"],"state_sha256":"f28e496fbf16c2c45614efc7ebd942642c6272606ca3632e58f68459877e4164"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eH0F9qFIl0cW6anWpIMV/zzvSQxEXxQ41CAjbhTAjcBie6shwF/H7pFfM09OJgED83YWKhNHvn3GMeGNUBoDCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T01:11:27.596214Z","bundle_sha256":"90a7852328032aacc50d008c6084274fb4f03f9e663e9d51f4d3c48b8855defe"}}