{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PB5MNKNU56Q46ZIAH4574QYQX7","short_pith_number":"pith:PB5MNKNU","canonical_record":{"source":{"id":"2508.21188","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-28T20:02:10Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f0fb9d690afdbcab3ef5d8e2ba54fbf8d6663f41efd1478ca667481eec680291","abstract_canon_sha256":"0df3fd53f787b63d5484de38168f31ffe693f2ffc92793e56724dc27876ff0fd"},"schema_version":"1.0"},"canonical_sha256":"787ac6a9b4efa1cf65003f3bfe4310bff0c4871fb9a5a3fa32e8c6faab3dd198","source":{"kind":"arxiv","id":"2508.21188","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21188","created_at":"2026-07-05T12:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21188v2","created_at":"2026-07-05T12:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21188","created_at":"2026-07-05T12:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"PB5MNKNU56Q4","created_at":"2026-07-05T12:03:32Z"},{"alias_kind":"pith_short_16","alias_value":"PB5MNKNU56Q46ZIA","created_at":"2026-07-05T12:03:32Z"},{"alias_kind":"pith_short_8","alias_value":"PB5MNKNU","created_at":"2026-07-05T12:03:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PB5MNKNU56Q46ZIAH4574QYQX7","target":"record","payload":{"canonical_record":{"source":{"id":"2508.21188","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-28T20:02:10Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f0fb9d690afdbcab3ef5d8e2ba54fbf8d6663f41efd1478ca667481eec680291","abstract_canon_sha256":"0df3fd53f787b63d5484de38168f31ffe693f2ffc92793e56724dc27876ff0fd"},"schema_version":"1.0"},"canonical_sha256":"787ac6a9b4efa1cf65003f3bfe4310bff0c4871fb9a5a3fa32e8c6faab3dd198","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:32.981895Z","signature_b64":"gM6K7D8QVhROw1s9WTmYSQd74UBeeA2iKcwGktdJ2cqLsPQ8DzK0Piq2d+FgvEBHvbzvIBfnlg60XHTeR6m6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"787ac6a9b4efa1cf65003f3bfe4310bff0c4871fb9a5a3fa32e8c6faab3dd198","last_reissued_at":"2026-07-05T12:03:32.981332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:32.981332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.21188","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":"2026-07-05T12:03:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8+VyRqOfXaj3BLdcm4gfuMFois4jKo5M8ZPClz7UhC5F6Io3JaDw01CXou2Fz/yzmD7lzz9twzgpAaPkDu6BAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:03:25.025233Z"},"content_sha256":"35b093bfbde2430e4c28072e1f4369ae384e1c52c364657c3c056f83d41fa103","schema_version":"1.0","event_id":"sha256:35b093bfbde2430e4c28072e1f4369ae384e1c52c364657c3c056f83d41fa103"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PB5MNKNU56Q46ZIAH4574QYQX7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mirage or Method? How Model-Task Alignment Induces Divergent RL Conclusions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Cheng Wang, Haoze Wu, Junxian He, Wenshuo Zhao","submitted_at":"2025-08-28T20:02:10Z","abstract_excerpt":"Recent advances in applying reinforcement learning (RL) to large language models (LLMs) have led to substantial progress. In particular, a series of remarkable yet often counterintuitive phenomena have been reported in LLMs, exhibiting patterns not typically observed in traditional RL settings. For example, notable claims include that a single training example can match the performance achieved with an entire dataset, that the reward signal does not need to be very accurate, and that training solely with negative samples can match or even surpass sophisticated reward-based methods. However, th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21188","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/2508.21188/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":"2026-07-05T12:03:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Krg2LLgNXTRIMr5XAw/rBK+8kGS7QOvSCIIu1aGBXNvpdD4u2AGn7N4gwpi34EGwjKVhFqHiH/HApqSdxr0UCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:03:25.026141Z"},"content_sha256":"5bb74ff27dc41145d4217144dbf7b46ca51f46b07da31037a968ef8a8f0a9096","schema_version":"1.0","event_id":"sha256:5bb74ff27dc41145d4217144dbf7b46ca51f46b07da31037a968ef8a8f0a9096"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PB5MNKNU56Q46ZIAH4574QYQX7/bundle.json","state_url":"https://pith.science/pith/PB5MNKNU56Q46ZIAH4574QYQX7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PB5MNKNU56Q46ZIAH4574QYQX7/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":"2026-08-09T17:03:25Z","links":{"resolver":"https://pith.science/pith/PB5MNKNU56Q46ZIAH4574QYQX7","bundle":"https://pith.science/pith/PB5MNKNU56Q46ZIAH4574QYQX7/bundle.json","state":"https://pith.science/pith/PB5MNKNU56Q46ZIAH4574QYQX7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PB5MNKNU56Q46ZIAH4574QYQX7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PB5MNKNU56Q46ZIAH4574QYQX7","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":"0df3fd53f787b63d5484de38168f31ffe693f2ffc92793e56724dc27876ff0fd","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-28T20:02:10Z","title_canon_sha256":"f0fb9d690afdbcab3ef5d8e2ba54fbf8d6663f41efd1478ca667481eec680291"},"schema_version":"1.0","source":{"id":"2508.21188","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21188","created_at":"2026-07-05T12:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21188v2","created_at":"2026-07-05T12:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21188","created_at":"2026-07-05T12:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"PB5MNKNU56Q4","created_at":"2026-07-05T12:03:32Z"},{"alias_kind":"pith_short_16","alias_value":"PB5MNKNU56Q46ZIA","created_at":"2026-07-05T12:03:32Z"},{"alias_kind":"pith_short_8","alias_value":"PB5MNKNU","created_at":"2026-07-05T12:03:32Z"}],"graph_snapshots":[{"event_id":"sha256:5bb74ff27dc41145d4217144dbf7b46ca51f46b07da31037a968ef8a8f0a9096","target":"graph","created_at":"2026-07-05T12:03:32Z","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/2508.21188/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in applying reinforcement learning (RL) to large language models (LLMs) have led to substantial progress. In particular, a series of remarkable yet often counterintuitive phenomena have been reported in LLMs, exhibiting patterns not typically observed in traditional RL settings. For example, notable claims include that a single training example can match the performance achieved with an entire dataset, that the reward signal does not need to be very accurate, and that training solely with negative samples can match or even surpass sophisticated reward-based methods. However, th","authors_text":"Cheng Wang, Haoze Wu, Junxian He, Wenshuo Zhao","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-28T20:02:10Z","title":"Mirage or Method? How Model-Task Alignment Induces Divergent RL Conclusions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21188","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":"sha256:35b093bfbde2430e4c28072e1f4369ae384e1c52c364657c3c056f83d41fa103","target":"record","created_at":"2026-07-05T12:03:32Z","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":"0df3fd53f787b63d5484de38168f31ffe693f2ffc92793e56724dc27876ff0fd","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-28T20:02:10Z","title_canon_sha256":"f0fb9d690afdbcab3ef5d8e2ba54fbf8d6663f41efd1478ca667481eec680291"},"schema_version":"1.0","source":{"id":"2508.21188","kind":"arxiv","version":2}},"canonical_sha256":"787ac6a9b4efa1cf65003f3bfe4310bff0c4871fb9a5a3fa32e8c6faab3dd198","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"787ac6a9b4efa1cf65003f3bfe4310bff0c4871fb9a5a3fa32e8c6faab3dd198","first_computed_at":"2026-07-05T12:03:32.981332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:32.981332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gM6K7D8QVhROw1s9WTmYSQd74UBeeA2iKcwGktdJ2cqLsPQ8DzK0Piq2d+FgvEBHvbzvIBfnlg60XHTeR6m6AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:32.981895Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.21188","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35b093bfbde2430e4c28072e1f4369ae384e1c52c364657c3c056f83d41fa103","sha256:5bb74ff27dc41145d4217144dbf7b46ca51f46b07da31037a968ef8a8f0a9096"],"state_sha256":"95b8bb908e1c123e42d8cc66cfd429889e9a5f4393d4064ac46f6deb6151aee6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lRwoR6+rwQ/DxXHP9NmXuQN+B3eNnZA/CNhSibksJpCZ2x5EOP4fOKpr8ms95o6RYYDGiqVP6wH9FQFBpETsBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T17:03:25.031193Z","bundle_sha256":"0bb178f1b52a97c73a366234f1e360f798e2f33805ad1876519da2865f99cece"}}