{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LIADHZZIZDAVCPQC2DQVGW6XEC","short_pith_number":"pith:LIADHZZI","canonical_record":{"source":{"id":"2607.14895","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-16T12:11:25Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4573b2862c3ec310e2d5c9c3f6897138dedb525b0d05707087643d8873cb7733","abstract_canon_sha256":"876afbd0685ed5b11fe6cf72fb3799b0043eb0f4182412c27e8890f93f7200bf"},"schema_version":"1.0"},"canonical_sha256":"5a0033e728c8c1513e02d0e1535bd720b841862b98e38c3aa30e8b37f8dce532","source":{"kind":"arxiv","id":"2607.14895","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14895","created_at":"2026-07-17T01:21:57Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14895v1","created_at":"2026-07-17T01:21:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14895","created_at":"2026-07-17T01:21:57Z"},{"alias_kind":"pith_short_12","alias_value":"LIADHZZIZDAV","created_at":"2026-07-17T01:21:57Z"},{"alias_kind":"pith_short_16","alias_value":"LIADHZZIZDAVCPQC","created_at":"2026-07-17T01:21:57Z"},{"alias_kind":"pith_short_8","alias_value":"LIADHZZI","created_at":"2026-07-17T01:21:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LIADHZZIZDAVCPQC2DQVGW6XEC","target":"record","payload":{"canonical_record":{"source":{"id":"2607.14895","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-16T12:11:25Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4573b2862c3ec310e2d5c9c3f6897138dedb525b0d05707087643d8873cb7733","abstract_canon_sha256":"876afbd0685ed5b11fe6cf72fb3799b0043eb0f4182412c27e8890f93f7200bf"},"schema_version":"1.0"},"canonical_sha256":"5a0033e728c8c1513e02d0e1535bd720b841862b98e38c3aa30e8b37f8dce532","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:21:57.534250Z","signature_b64":"NrjTS1BFtqJzBK8JfsggHMo2NvZLkwXmqTLd40pBP+dIzwJuv3LJJCKt5gj2F1f9LkYHHKEWHcUjupbIBozIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a0033e728c8c1513e02d0e1535bd720b841862b98e38c3aa30e8b37f8dce532","last_reissued_at":"2026-07-17T01:21:57.533478Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:21:57.533478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.14895","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":"2026-07-17T01:21:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rHq6lUF5MT/g4izaqKLayyoLLiGUFfxO04EZna9dKZCFTFOgo8ondOp3Vy6Okad9PWcqAlJRREQq6JFT8rCADg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:42:55.284644Z"},"content_sha256":"5c4d422a4eb3abafffca5c970a3ea650afb28b74f2fbb02258bd5228d16adbc0","schema_version":"1.0","event_id":"sha256:5c4d422a4eb3abafffca5c970a3ea650afb28b74f2fbb02258bd5228d16adbc0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LIADHZZIZDAVCPQC2DQVGW6XEC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Mark Vero, Martin Vechev, Niels M\\\"undler-Sasahara, Yu-Du Feng","submitted_at":"2026-07-16T12:11:25Z","abstract_excerpt":"Reasoning language models (RLMs) have demonstrated impressive performance in domains such as mathematics and coding. These domains permit reliable verification of model outputs, which is important for enabling the reinforcement learning that drives RLM performance gains. However, training RLMs on domains that lack reliable verifiers remains challenging. Meanwhile, for both verifiable and unverifiable domains, large amounts of unused supervised fine-tuning data with human-written solutions exist. In this work, we show that these data can be used efficiently to further improve RLM performance. F"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14895","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/2607.14895/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":"2026-07-17T01:21:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AruCn6YK749BgcTMkcq1Y6vk659jrw54Bq8IafQpQNGnZgZusxd+Z104Qx7NtNbzfUOn5zG1MG1txonQef53BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:42:55.285127Z"},"content_sha256":"3ce17395b846368e7d6c6d0b77c05bbd798f7ecbb62304dac8d6fdd505f0ef77","schema_version":"1.0","event_id":"sha256:3ce17395b846368e7d6c6d0b77c05bbd798f7ecbb62304dac8d6fdd505f0ef77"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LIADHZZIZDAVCPQC2DQVGW6XEC/bundle.json","state_url":"https://pith.science/pith/LIADHZZIZDAVCPQC2DQVGW6XEC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LIADHZZIZDAVCPQC2DQVGW6XEC/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":"2026-08-03T19:42:55Z","links":{"resolver":"https://pith.science/pith/LIADHZZIZDAVCPQC2DQVGW6XEC","bundle":"https://pith.science/pith/LIADHZZIZDAVCPQC2DQVGW6XEC/bundle.json","state":"https://pith.science/pith/LIADHZZIZDAVCPQC2DQVGW6XEC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LIADHZZIZDAVCPQC2DQVGW6XEC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LIADHZZIZDAVCPQC2DQVGW6XEC","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":"876afbd0685ed5b11fe6cf72fb3799b0043eb0f4182412c27e8890f93f7200bf","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-16T12:11:25Z","title_canon_sha256":"4573b2862c3ec310e2d5c9c3f6897138dedb525b0d05707087643d8873cb7733"},"schema_version":"1.0","source":{"id":"2607.14895","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14895","created_at":"2026-07-17T01:21:57Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14895v1","created_at":"2026-07-17T01:21:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14895","created_at":"2026-07-17T01:21:57Z"},{"alias_kind":"pith_short_12","alias_value":"LIADHZZIZDAV","created_at":"2026-07-17T01:21:57Z"},{"alias_kind":"pith_short_16","alias_value":"LIADHZZIZDAVCPQC","created_at":"2026-07-17T01:21:57Z"},{"alias_kind":"pith_short_8","alias_value":"LIADHZZI","created_at":"2026-07-17T01:21:57Z"}],"graph_snapshots":[{"event_id":"sha256:3ce17395b846368e7d6c6d0b77c05bbd798f7ecbb62304dac8d6fdd505f0ef77","target":"graph","created_at":"2026-07-17T01:21:57Z","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/2607.14895/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reasoning language models (RLMs) have demonstrated impressive performance in domains such as mathematics and coding. These domains permit reliable verification of model outputs, which is important for enabling the reinforcement learning that drives RLM performance gains. However, training RLMs on domains that lack reliable verifiers remains challenging. Meanwhile, for both verifiable and unverifiable domains, large amounts of unused supervised fine-tuning data with human-written solutions exist. In this work, we show that these data can be used efficiently to further improve RLM performance. F","authors_text":"Mark Vero, Martin Vechev, Niels M\\\"undler-Sasahara, Yu-Du Feng","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-16T12:11:25Z","title":"Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14895","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":"sha256:5c4d422a4eb3abafffca5c970a3ea650afb28b74f2fbb02258bd5228d16adbc0","target":"record","created_at":"2026-07-17T01:21:57Z","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":"876afbd0685ed5b11fe6cf72fb3799b0043eb0f4182412c27e8890f93f7200bf","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-16T12:11:25Z","title_canon_sha256":"4573b2862c3ec310e2d5c9c3f6897138dedb525b0d05707087643d8873cb7733"},"schema_version":"1.0","source":{"id":"2607.14895","kind":"arxiv","version":1}},"canonical_sha256":"5a0033e728c8c1513e02d0e1535bd720b841862b98e38c3aa30e8b37f8dce532","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a0033e728c8c1513e02d0e1535bd720b841862b98e38c3aa30e8b37f8dce532","first_computed_at":"2026-07-17T01:21:57.533478Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T01:21:57.533478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NrjTS1BFtqJzBK8JfsggHMo2NvZLkwXmqTLd40pBP+dIzwJuv3LJJCKt5gj2F1f9LkYHHKEWHcUjupbIBozIAQ==","signature_status":"signed_v1","signed_at":"2026-07-17T01:21:57.534250Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.14895","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c4d422a4eb3abafffca5c970a3ea650afb28b74f2fbb02258bd5228d16adbc0","sha256:3ce17395b846368e7d6c6d0b77c05bbd798f7ecbb62304dac8d6fdd505f0ef77"],"state_sha256":"81229110500b80bd90ed206d0657fecf8792c24a481e570b959cf675e615cb4a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YCHIfEXCDcj9E0eKeNq7OF7HIyUWl21Eta+QBK3hmel69tNl08oc1RSlG1/NeL1NGQ05E3g0NNhWK3p3Kbi8AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:42:55.288271Z","bundle_sha256":"192e9f1aa38742632c5b96b6b990dcc2c844ac5d6926c1f7b01381634d1b4dd2"}}