{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PKYU6UHICGWJTUKTGN4T6CTXFV","short_pith_number":"pith:PKYU6UHI","canonical_record":{"source":{"id":"2505.10182","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-15T11:29:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bdaf2cde6b2f266dc4d5ec5557c4804508b9d79f27fcea4afa2e9885003736d9","abstract_canon_sha256":"9d335625a0c01f3e8089482d40fe0e42a2c8160a859a2abec8a3a0434ec778f3"},"schema_version":"1.0"},"canonical_sha256":"7ab14f50e811ac99d15333793f0a772d79c4b67a0363b19eca73c73b74910ca5","source":{"kind":"arxiv","id":"2505.10182","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.10182","created_at":"2026-07-05T11:03:34Z"},{"alias_kind":"arxiv_version","alias_value":"2505.10182v1","created_at":"2026-07-05T11:03:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10182","created_at":"2026-07-05T11:03:34Z"},{"alias_kind":"pith_short_12","alias_value":"PKYU6UHICGWJ","created_at":"2026-07-05T11:03:34Z"},{"alias_kind":"pith_short_16","alias_value":"PKYU6UHICGWJTUKT","created_at":"2026-07-05T11:03:34Z"},{"alias_kind":"pith_short_8","alias_value":"PKYU6UHI","created_at":"2026-07-05T11:03:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PKYU6UHICGWJTUKTGN4T6CTXFV","target":"record","payload":{"canonical_record":{"source":{"id":"2505.10182","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-15T11:29:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bdaf2cde6b2f266dc4d5ec5557c4804508b9d79f27fcea4afa2e9885003736d9","abstract_canon_sha256":"9d335625a0c01f3e8089482d40fe0e42a2c8160a859a2abec8a3a0434ec778f3"},"schema_version":"1.0"},"canonical_sha256":"7ab14f50e811ac99d15333793f0a772d79c4b67a0363b19eca73c73b74910ca5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:34.614844Z","signature_b64":"lW8z17OBZ84uNgfEs+Njmd73RQF3pARyg/FDhIasrOge8e4LWO94eX2EcXGyb8wgd2oORcyzfLEgOJGS8wzVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ab14f50e811ac99d15333793f0a772d79c4b67a0363b19eca73c73b74910ca5","last_reissued_at":"2026-07-05T11:03:34.614417Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:34.614417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.10182","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":"2026-07-05T11:03:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KHpLkgL6aTE/smfeJIHIjEB91mL9GU/8uRbfVljFa22iStFrFrv/BShufBRePgf+FiIOlGnGq7l8um8krPv0AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T06:52:23.778741Z"},"content_sha256":"b2941df5f1d87a6bb235d71bd627f94d436004eee754a910a96763489f101b8a","schema_version":"1.0","event_id":"sha256:b2941df5f1d87a6bb235d71bd627f94d436004eee754a910a96763489f101b8a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PKYU6UHICGWJTUKTGN4T6CTXFV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mining Hidden Thoughts from Texts: Evaluating Continual Pretraining with Synthetic Data for LLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Masafumi Oyamada, Taro Yano, Yoichi Ishibashi","submitted_at":"2025-05-15T11:29:01Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated significant improvements in reasoning capabilities through supervised fine-tuning and reinforcement learning. However, when training reasoning models, these approaches are primarily applicable to specific domains such as mathematics and programming, which imposes fundamental constraints on the breadth and scalability of training data. In contrast, continual pretraining (CPT) offers the advantage of not requiring task-specific signals. Nevertheless, how to effectively synthesize training data for reasoning and how such data affect a wide range of d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10182","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/2505.10182/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":"2026-07-05T11:03:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VRlC5lOVsktfBGshJJ0/XLQ7UwhZZutAkNt2H9/fRqWoVckqggcYdZJj7GXqhEVuSGIKjeBSMXSpv8NKDvUUBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T06:52:23.779619Z"},"content_sha256":"702aea0972c49f93aa97b3e6e2b8cc01f69de8ae6953103f55d5f9be9bb4fafb","schema_version":"1.0","event_id":"sha256:702aea0972c49f93aa97b3e6e2b8cc01f69de8ae6953103f55d5f9be9bb4fafb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PKYU6UHICGWJTUKTGN4T6CTXFV/bundle.json","state_url":"https://pith.science/pith/PKYU6UHICGWJTUKTGN4T6CTXFV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PKYU6UHICGWJTUKTGN4T6CTXFV/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":"2026-08-16T06:52:23Z","links":{"resolver":"https://pith.science/pith/PKYU6UHICGWJTUKTGN4T6CTXFV","bundle":"https://pith.science/pith/PKYU6UHICGWJTUKTGN4T6CTXFV/bundle.json","state":"https://pith.science/pith/PKYU6UHICGWJTUKTGN4T6CTXFV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PKYU6UHICGWJTUKTGN4T6CTXFV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PKYU6UHICGWJTUKTGN4T6CTXFV","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":"9d335625a0c01f3e8089482d40fe0e42a2c8160a859a2abec8a3a0434ec778f3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-15T11:29:01Z","title_canon_sha256":"bdaf2cde6b2f266dc4d5ec5557c4804508b9d79f27fcea4afa2e9885003736d9"},"schema_version":"1.0","source":{"id":"2505.10182","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.10182","created_at":"2026-07-05T11:03:34Z"},{"alias_kind":"arxiv_version","alias_value":"2505.10182v1","created_at":"2026-07-05T11:03:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10182","created_at":"2026-07-05T11:03:34Z"},{"alias_kind":"pith_short_12","alias_value":"PKYU6UHICGWJ","created_at":"2026-07-05T11:03:34Z"},{"alias_kind":"pith_short_16","alias_value":"PKYU6UHICGWJTUKT","created_at":"2026-07-05T11:03:34Z"},{"alias_kind":"pith_short_8","alias_value":"PKYU6UHI","created_at":"2026-07-05T11:03:34Z"}],"graph_snapshots":[{"event_id":"sha256:702aea0972c49f93aa97b3e6e2b8cc01f69de8ae6953103f55d5f9be9bb4fafb","target":"graph","created_at":"2026-07-05T11:03:34Z","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/2505.10182/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated significant improvements in reasoning capabilities through supervised fine-tuning and reinforcement learning. However, when training reasoning models, these approaches are primarily applicable to specific domains such as mathematics and programming, which imposes fundamental constraints on the breadth and scalability of training data. In contrast, continual pretraining (CPT) offers the advantage of not requiring task-specific signals. Nevertheless, how to effectively synthesize training data for reasoning and how such data affect a wide range of d","authors_text":"Masafumi Oyamada, Taro Yano, Yoichi Ishibashi","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-15T11:29:01Z","title":"Mining Hidden Thoughts from Texts: Evaluating Continual Pretraining with Synthetic Data for LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10182","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:b2941df5f1d87a6bb235d71bd627f94d436004eee754a910a96763489f101b8a","target":"record","created_at":"2026-07-05T11:03:34Z","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":"9d335625a0c01f3e8089482d40fe0e42a2c8160a859a2abec8a3a0434ec778f3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-15T11:29:01Z","title_canon_sha256":"bdaf2cde6b2f266dc4d5ec5557c4804508b9d79f27fcea4afa2e9885003736d9"},"schema_version":"1.0","source":{"id":"2505.10182","kind":"arxiv","version":1}},"canonical_sha256":"7ab14f50e811ac99d15333793f0a772d79c4b67a0363b19eca73c73b74910ca5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ab14f50e811ac99d15333793f0a772d79c4b67a0363b19eca73c73b74910ca5","first_computed_at":"2026-07-05T11:03:34.614417Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:34.614417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lW8z17OBZ84uNgfEs+Njmd73RQF3pARyg/FDhIasrOge8e4LWO94eX2EcXGyb8wgd2oORcyzfLEgOJGS8wzVDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:34.614844Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.10182","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2941df5f1d87a6bb235d71bd627f94d436004eee754a910a96763489f101b8a","sha256:702aea0972c49f93aa97b3e6e2b8cc01f69de8ae6953103f55d5f9be9bb4fafb"],"state_sha256":"3b1e94fd1201c129f9194cc4c8b0d1b344e28efa1719de8f39846fceff387864"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HNjjDPnkTc9sEyvWvW75l4a8Ai0TUdUvpiaFAxRG1+HUVxQRznAlRE2Ea/4kRQhQxXjCmWPd8pBKljF3gtLgBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T06:52:23.786440Z","bundle_sha256":"575ddad53288aa5e1ab52db20e4ba6afff78e1c292a71b0e14817b6e7ad3d0dd"}}