{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ECBPXMRZ7TFHT7LRVUF6W6NDSW","short_pith_number":"pith:ECBPXMRZ","schema_version":"1.0","canonical_sha256":"2082fbb239fcca79fd71ad0beb79a39584b21ae89d1f04d32ad494cb491748a4","source":{"kind":"arxiv","id":"2608.02139","version":1},"attestation_state":"computed","paper":{"title":"Self-Improving Large Language Models via Progressive Experience Evolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Fandong Meng, Haoyang Zhou, Meng Li, Shijie Ren, Xiting Wang, Xunlong Wang, Yuetan Chen, Yujie Guo, Yunhang Yao, Yunlong Liang, Ziheng Peng","submitted_at":"2026-08-03T12:27:32Z","abstract_excerpt":"Large language models (LLMs) capable of self-improvement require not only effective policy optimization, but also a principled mechanism for transforming transient interaction experience into persistent model capabilities. Existing self-improvement paradigms remain fragmented: test-time methods can explicitly extract experience but cannot internalize it into model parameters, whereas training-time optimization methods can update model parameters but lack an explicit mechanism for accumulating transferable experience. Bridging these two paradigms requires a critical intermediate stage that rema"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.02139","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-03T12:27:32Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fc97de284144e71bc497c590c73df5a4237b15f414c0844a61871c41fddcb34e","abstract_canon_sha256":"0c6ab15012f0ca54a375d3d1a66d8882864dc62c73d93471416279c8cc4995a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:11:05.610737Z","signature_b64":"cV9rjWKUHDe5ydXkmzrylGQyZFoeCuAuvdG0LptH2nw8tnrV7zAT3e+tWWaL+Su+niCi5eoGBpSHXQJ0tXl/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2082fbb239fcca79fd71ad0beb79a39584b21ae89d1f04d32ad494cb491748a4","last_reissued_at":"2026-08-04T02:11:05.609206Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:11:05.609206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Improving Large Language Models via Progressive Experience Evolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Fandong Meng, Haoyang Zhou, Meng Li, Shijie Ren, Xiting Wang, Xunlong Wang, Yuetan Chen, Yujie Guo, Yunhang Yao, Yunlong Liang, Ziheng Peng","submitted_at":"2026-08-03T12:27:32Z","abstract_excerpt":"Large language models (LLMs) capable of self-improvement require not only effective policy optimization, but also a principled mechanism for transforming transient interaction experience into persistent model capabilities. Existing self-improvement paradigms remain fragmented: test-time methods can explicitly extract experience but cannot internalize it into model parameters, whereas training-time optimization methods can update model parameters but lack an explicit mechanism for accumulating transferable experience. Bridging these two paradigms requires a critical intermediate stage that rema"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02139","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/2608.02139/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.02139","created_at":"2026-08-04T02:11:05.610756+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.02139v1","created_at":"2026-08-04T02:11:05.610756+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02139","created_at":"2026-08-04T02:11:05.610756+00:00"},{"alias_kind":"pith_short_12","alias_value":"ECBPXMRZ7TFH","created_at":"2026-08-04T02:11:05.610756+00:00"},{"alias_kind":"pith_short_16","alias_value":"ECBPXMRZ7TFHT7LR","created_at":"2026-08-04T02:11:05.610756+00:00"},{"alias_kind":"pith_short_8","alias_value":"ECBPXMRZ","created_at":"2026-08-04T02:11:05.610756+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ECBPXMRZ7TFHT7LRVUF6W6NDSW","json":"https://pith.science/pith/ECBPXMRZ7TFHT7LRVUF6W6NDSW.json","graph_json":"https://pith.science/api/pith-number/ECBPXMRZ7TFHT7LRVUF6W6NDSW/graph.json","events_json":"https://pith.science/api/pith-number/ECBPXMRZ7TFHT7LRVUF6W6NDSW/events.json","paper":"https://pith.science/paper/ECBPXMRZ"},"agent_actions":{"view_html":"https://pith.science/pith/ECBPXMRZ7TFHT7LRVUF6W6NDSW","download_json":"https://pith.science/pith/ECBPXMRZ7TFHT7LRVUF6W6NDSW.json","view_paper":"https://pith.science/paper/ECBPXMRZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.02139&json=true","fetch_graph":"https://pith.science/api/pith-number/ECBPXMRZ7TFHT7LRVUF6W6NDSW/graph.json","fetch_events":"https://pith.science/api/pith-number/ECBPXMRZ7TFHT7LRVUF6W6NDSW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ECBPXMRZ7TFHT7LRVUF6W6NDSW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ECBPXMRZ7TFHT7LRVUF6W6NDSW/action/storage_attestation","attest_author":"https://pith.science/pith/ECBPXMRZ7TFHT7LRVUF6W6NDSW/action/author_attestation","sign_citation":"https://pith.science/pith/ECBPXMRZ7TFHT7LRVUF6W6NDSW/action/citation_signature","submit_replication":"https://pith.science/pith/ECBPXMRZ7TFHT7LRVUF6W6NDSW/action/replication_record"}},"created_at":"2026-08-04T02:11:05.610756+00:00","updated_at":"2026-08-04T02:11:05.610756+00:00"}