{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NDOIN3UKB5HQVYL5R7R6LJYI4M","short_pith_number":"pith:NDOIN3UK","canonical_record":{"source":{"id":"2607.21971","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T04:35:29Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"24519bc30486f700fb663bfcabe5e8c1bcd95bdca90e7a08d53ab37500c83990","abstract_canon_sha256":"4e4ea134b0b3694ec5c3423028e203300add25dde34a1e4cd256038f3efb01c7"},"schema_version":"1.0"},"canonical_sha256":"68dc86ee8a0f4f0ae17d8fe3e5a708e321a5080898af84fa8dc48d5887eca905","source":{"kind":"arxiv","id":"2607.21971","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21971","created_at":"2026-07-27T00:20:30Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21971v1","created_at":"2026-07-27T00:20:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21971","created_at":"2026-07-27T00:20:30Z"},{"alias_kind":"pith_short_12","alias_value":"NDOIN3UKB5HQ","created_at":"2026-07-27T00:20:30Z"},{"alias_kind":"pith_short_16","alias_value":"NDOIN3UKB5HQVYL5","created_at":"2026-07-27T00:20:30Z"},{"alias_kind":"pith_short_8","alias_value":"NDOIN3UK","created_at":"2026-07-27T00:20:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NDOIN3UKB5HQVYL5R7R6LJYI4M","target":"record","payload":{"canonical_record":{"source":{"id":"2607.21971","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T04:35:29Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"24519bc30486f700fb663bfcabe5e8c1bcd95bdca90e7a08d53ab37500c83990","abstract_canon_sha256":"4e4ea134b0b3694ec5c3423028e203300add25dde34a1e4cd256038f3efb01c7"},"schema_version":"1.0"},"canonical_sha256":"68dc86ee8a0f4f0ae17d8fe3e5a708e321a5080898af84fa8dc48d5887eca905","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T00:20:30.623388Z","signature_b64":"5/sz2eycZ0HtvjEXtzLtlR/5YDqvvmw6hKEAqNLczShAN0tVkWwIHpngaL/udspa86IHjzFFLQZm400F+1IqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68dc86ee8a0f4f0ae17d8fe3e5a708e321a5080898af84fa8dc48d5887eca905","last_reissued_at":"2026-07-27T00:20:30.622455Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T00:20:30.622455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.21971","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":"2026-07-27T00:20:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7wgKspRE0ydU4tQ2kpQ/B9wISkho8s2V5oyIp0b8WROv++O4W9pQ3hBOSxAvsEa+0Eiqm/aJoOd7ZNgJyDolCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T07:26:07.518992Z"},"content_sha256":"4fdada7651ec81fc89381a26172f7f97f25922592e5ff4c96180602cd090ee88","schema_version":"1.0","event_id":"sha256:4fdada7651ec81fc89381a26172f7f97f25922592e5ff4c96180602cd090ee88"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NDOIN3UKB5HQVYL5R7R6LJYI4M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Cheng Qian, Heng Ji, Shujin Wu, Xiusi Chen","submitted_at":"2026-07-24T04:35:29Z","abstract_excerpt":"Test-time scaling through iterative self-evolution with environment feedback, as demonstrated by AlphaEvolve, shows remarkable performance gains. We hypothesize that the success of such evolution frameworks hinges on meta-skills, such as self-reflection with environment feedback, that enable effective multi-round refinement, yet are largely neglected by traditional post-training. To bridge this gap, we present MetaEvolve, a framework designed to develop these meta-skills via a data synthesis pipeline, evolution-aware reinforcement learning (RL), and inference-time evolutionary search. Concrete"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21971","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/2607.21971/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":"2026-07-27T00:20:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TpEkm8W+Iy1k5PZA6R/LdKzYiVEg0UwlVjJZb5mEifnHKNmI03N+gir9lCmJgpHG70F5KD5VDgx+3qemgLrtAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T07:26:07.520082Z"},"content_sha256":"f28eb5118de6a5e89576695039d1c3d1aca6fe7e10701c2ebc9b7f1d438358b0","schema_version":"1.0","event_id":"sha256:f28eb5118de6a5e89576695039d1c3d1aca6fe7e10701c2ebc9b7f1d438358b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NDOIN3UKB5HQVYL5R7R6LJYI4M/bundle.json","state_url":"https://pith.science/pith/NDOIN3UKB5HQVYL5R7R6LJYI4M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NDOIN3UKB5HQVYL5R7R6LJYI4M/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":"2026-08-19T07:26:07Z","links":{"resolver":"https://pith.science/pith/NDOIN3UKB5HQVYL5R7R6LJYI4M","bundle":"https://pith.science/pith/NDOIN3UKB5HQVYL5R7R6LJYI4M/bundle.json","state":"https://pith.science/pith/NDOIN3UKB5HQVYL5R7R6LJYI4M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NDOIN3UKB5HQVYL5R7R6LJYI4M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NDOIN3UKB5HQVYL5R7R6LJYI4M","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":"4e4ea134b0b3694ec5c3423028e203300add25dde34a1e4cd256038f3efb01c7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T04:35:29Z","title_canon_sha256":"24519bc30486f700fb663bfcabe5e8c1bcd95bdca90e7a08d53ab37500c83990"},"schema_version":"1.0","source":{"id":"2607.21971","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21971","created_at":"2026-07-27T00:20:30Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21971v1","created_at":"2026-07-27T00:20:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21971","created_at":"2026-07-27T00:20:30Z"},{"alias_kind":"pith_short_12","alias_value":"NDOIN3UKB5HQ","created_at":"2026-07-27T00:20:30Z"},{"alias_kind":"pith_short_16","alias_value":"NDOIN3UKB5HQVYL5","created_at":"2026-07-27T00:20:30Z"},{"alias_kind":"pith_short_8","alias_value":"NDOIN3UK","created_at":"2026-07-27T00:20:30Z"}],"graph_snapshots":[{"event_id":"sha256:f28eb5118de6a5e89576695039d1c3d1aca6fe7e10701c2ebc9b7f1d438358b0","target":"graph","created_at":"2026-07-27T00:20:30Z","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/2607.21971/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Test-time scaling through iterative self-evolution with environment feedback, as demonstrated by AlphaEvolve, shows remarkable performance gains. We hypothesize that the success of such evolution frameworks hinges on meta-skills, such as self-reflection with environment feedback, that enable effective multi-round refinement, yet are largely neglected by traditional post-training. To bridge this gap, we present MetaEvolve, a framework designed to develop these meta-skills via a data synthesis pipeline, evolution-aware reinforcement learning (RL), and inference-time evolutionary search. Concrete","authors_text":"Cheng Qian, Heng Ji, Shujin Wu, Xiusi Chen","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T04:35:29Z","title":"Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21971","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":"sha256:4fdada7651ec81fc89381a26172f7f97f25922592e5ff4c96180602cd090ee88","target":"record","created_at":"2026-07-27T00:20:30Z","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":"4e4ea134b0b3694ec5c3423028e203300add25dde34a1e4cd256038f3efb01c7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T04:35:29Z","title_canon_sha256":"24519bc30486f700fb663bfcabe5e8c1bcd95bdca90e7a08d53ab37500c83990"},"schema_version":"1.0","source":{"id":"2607.21971","kind":"arxiv","version":1}},"canonical_sha256":"68dc86ee8a0f4f0ae17d8fe3e5a708e321a5080898af84fa8dc48d5887eca905","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68dc86ee8a0f4f0ae17d8fe3e5a708e321a5080898af84fa8dc48d5887eca905","first_computed_at":"2026-07-27T00:20:30.622455Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-27T00:20:30.622455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5/sz2eycZ0HtvjEXtzLtlR/5YDqvvmw6hKEAqNLczShAN0tVkWwIHpngaL/udspa86IHjzFFLQZm400F+1IqCg==","signature_status":"signed_v1","signed_at":"2026-07-27T00:20:30.623388Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.21971","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fdada7651ec81fc89381a26172f7f97f25922592e5ff4c96180602cd090ee88","sha256:f28eb5118de6a5e89576695039d1c3d1aca6fe7e10701c2ebc9b7f1d438358b0"],"state_sha256":"5a59f81194156617fcae9978b76b006c8b6583a385f1607be41f50e7eb6c50c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qo/dPhLeVFHWvkHXiXKPNedkmzVXToAWfvn7NJQctHYK7hP7DjUtnBeZtCYKwLxmb82WjQJtHlU9FwOEDy+rAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T07:26:07.524949Z","bundle_sha256":"dda10b95e88b78487e4c76ca547a849322229749489f1a9b0562ad279c809e15"}}