{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YZDYMQXZC2FYGPTLJPXSRRHKMB","short_pith_number":"pith:YZDYMQXZ","canonical_record":{"source":{"id":"2605.31509","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T16:28:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"39352c5ed9fd1d1ee9c60a4f189d9fba962a199023466994687a87ca7ff86e7f","abstract_canon_sha256":"da355a68e2861e259fff347f76264f2f3d86f3e8629ea813dc78504e76712335"},"schema_version":"1.0"},"canonical_sha256":"c6478642f9168b833e6b4bef28c4ea607fd52d3d4b876db7ab54537318301f9c","source":{"kind":"arxiv","id":"2605.31509","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.31509","created_at":"2026-06-01T02:04:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.31509v1","created_at":"2026-06-01T02:04:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31509","created_at":"2026-06-01T02:04:10Z"},{"alias_kind":"pith_short_12","alias_value":"YZDYMQXZC2FY","created_at":"2026-06-01T02:04:10Z"},{"alias_kind":"pith_short_16","alias_value":"YZDYMQXZC2FYGPTL","created_at":"2026-06-01T02:04:10Z"},{"alias_kind":"pith_short_8","alias_value":"YZDYMQXZ","created_at":"2026-06-01T02:04:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YZDYMQXZC2FYGPTLJPXSRRHKMB","target":"record","payload":{"canonical_record":{"source":{"id":"2605.31509","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T16:28:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"39352c5ed9fd1d1ee9c60a4f189d9fba962a199023466994687a87ca7ff86e7f","abstract_canon_sha256":"da355a68e2861e259fff347f76264f2f3d86f3e8629ea813dc78504e76712335"},"schema_version":"1.0"},"canonical_sha256":"c6478642f9168b833e6b4bef28c4ea607fd52d3d4b876db7ab54537318301f9c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T02:04:10.003059Z","signature_b64":"teVZcEGs8QFdiUpQ4fwnHPNA28NPyzOohoOgrqRheL0ToMEZVVRkxXWKuZQnBzusf6JhglPWqHh1yt+UuAdmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6478642f9168b833e6b4bef28c4ea607fd52d3d4b876db7ab54537318301f9c","last_reissued_at":"2026-06-01T02:04:10.002143Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T02:04:10.002143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.31509","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":"2026-06-01T02:04:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A6hY4LusCxTKxzAFryvBkQsi0bOKYWoMGAYfrSuiKlASQJum6FAkJZw3CTf6ehNqCQxmrn8hw1hgFq0yMtFdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T14:42:11.372603Z"},"content_sha256":"2c7a1ebbfc2bef5f9e11037f830858cf278b6b38501c13189da5834a6a020648","schema_version":"1.0","event_id":"sha256:2c7a1ebbfc2bef5f9e11037f830858cf278b6b38501c13189da5834a6a020648"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YZDYMQXZC2FYGPTLJPXSRRHKMB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Skill Reuse as Compression in Agentic RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ben Zhou, Jacob Dineen, Jieyu Zhao, Taiwei Shi, Yu Feng, Zhikun Xu","submitted_at":"2026-05-29T16:28:34Z","abstract_excerpt":"Large language model agents trained with reinforcement learning (RL) often learn brittle, task-specific shortcuts. We hypothesize that agents generalize better when their successful trajectories are structurally compressible, decomposed into a small set of reusable abstract patterns. To formalize this, we introduce ReuseRL, which grounds agentic RL in the Minimum Description Length (MDL) principle. ReuseRL extracts a shared skill dictionary from successful trajectories and augments the RL objective with a segmentation cost, explicitly penalizing idiosyncratic behaviors that encode poorly. We p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31509","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/2605.31509/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":"2026-06-01T02:04:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y3X4vgoFxe6Ok7bC/F7OjLhEhbhKz9epuXSaOlpKyujt+gPMSMGlmh2N9zVOBE40awOs1z2C9TzN25bM4cb+Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T14:42:11.372962Z"},"content_sha256":"afc1003e496355af32cdf2b9ccc51a7012c2ea2270fa8d217a9c751af57fd4f5","schema_version":"1.0","event_id":"sha256:afc1003e496355af32cdf2b9ccc51a7012c2ea2270fa8d217a9c751af57fd4f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YZDYMQXZC2FYGPTLJPXSRRHKMB/bundle.json","state_url":"https://pith.science/pith/YZDYMQXZC2FYGPTLJPXSRRHKMB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YZDYMQXZC2FYGPTLJPXSRRHKMB/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":"2026-06-07T14:42:11Z","links":{"resolver":"https://pith.science/pith/YZDYMQXZC2FYGPTLJPXSRRHKMB","bundle":"https://pith.science/pith/YZDYMQXZC2FYGPTLJPXSRRHKMB/bundle.json","state":"https://pith.science/pith/YZDYMQXZC2FYGPTLJPXSRRHKMB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YZDYMQXZC2FYGPTLJPXSRRHKMB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YZDYMQXZC2FYGPTLJPXSRRHKMB","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":"da355a68e2861e259fff347f76264f2f3d86f3e8629ea813dc78504e76712335","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T16:28:34Z","title_canon_sha256":"39352c5ed9fd1d1ee9c60a4f189d9fba962a199023466994687a87ca7ff86e7f"},"schema_version":"1.0","source":{"id":"2605.31509","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.31509","created_at":"2026-06-01T02:04:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.31509v1","created_at":"2026-06-01T02:04:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31509","created_at":"2026-06-01T02:04:10Z"},{"alias_kind":"pith_short_12","alias_value":"YZDYMQXZC2FY","created_at":"2026-06-01T02:04:10Z"},{"alias_kind":"pith_short_16","alias_value":"YZDYMQXZC2FYGPTL","created_at":"2026-06-01T02:04:10Z"},{"alias_kind":"pith_short_8","alias_value":"YZDYMQXZ","created_at":"2026-06-01T02:04:10Z"}],"graph_snapshots":[{"event_id":"sha256:afc1003e496355af32cdf2b9ccc51a7012c2ea2270fa8d217a9c751af57fd4f5","target":"graph","created_at":"2026-06-01T02:04:10Z","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/2605.31509/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model agents trained with reinforcement learning (RL) often learn brittle, task-specific shortcuts. We hypothesize that agents generalize better when their successful trajectories are structurally compressible, decomposed into a small set of reusable abstract patterns. To formalize this, we introduce ReuseRL, which grounds agentic RL in the Minimum Description Length (MDL) principle. ReuseRL extracts a shared skill dictionary from successful trajectories and augments the RL objective with a segmentation cost, explicitly penalizing idiosyncratic behaviors that encode poorly. We p","authors_text":"Ben Zhou, Jacob Dineen, Jieyu Zhao, Taiwei Shi, Yu Feng, Zhikun Xu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T16:28:34Z","title":"Skill Reuse as Compression in Agentic RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31509","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":"sha256:2c7a1ebbfc2bef5f9e11037f830858cf278b6b38501c13189da5834a6a020648","target":"record","created_at":"2026-06-01T02:04:10Z","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":"da355a68e2861e259fff347f76264f2f3d86f3e8629ea813dc78504e76712335","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T16:28:34Z","title_canon_sha256":"39352c5ed9fd1d1ee9c60a4f189d9fba962a199023466994687a87ca7ff86e7f"},"schema_version":"1.0","source":{"id":"2605.31509","kind":"arxiv","version":1}},"canonical_sha256":"c6478642f9168b833e6b4bef28c4ea607fd52d3d4b876db7ab54537318301f9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6478642f9168b833e6b4bef28c4ea607fd52d3d4b876db7ab54537318301f9c","first_computed_at":"2026-06-01T02:04:10.002143Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T02:04:10.002143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"teVZcEGs8QFdiUpQ4fwnHPNA28NPyzOohoOgrqRheL0ToMEZVVRkxXWKuZQnBzusf6JhglPWqHh1yt+UuAdmDQ==","signature_status":"signed_v1","signed_at":"2026-06-01T02:04:10.003059Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.31509","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c7a1ebbfc2bef5f9e11037f830858cf278b6b38501c13189da5834a6a020648","sha256:afc1003e496355af32cdf2b9ccc51a7012c2ea2270fa8d217a9c751af57fd4f5"],"state_sha256":"28036d9014580dd0144d51509a60a9646310c6f5dc5c9847b7a29b74761938dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"be3BZHLuWwjpBny9AQJ5pPxD1r13ERiCda9lDwKQ+ZySFUFvb8AFVCUF45Tc9gbHG67zm1PwJrxyN0FzrRDPCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T14:42:11.375078Z","bundle_sha256":"32e341280d97c62b8610e8ca05ee9465757d3b7402cf1812b1901cd8eec7067c"}}