{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IGVUSGZSQAAIIZF6LCST42TSWZ","short_pith_number":"pith:IGVUSGZS","canonical_record":{"source":{"id":"2608.03874","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T16:15:02Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"24c59c9b385434f3d68c686eb6ace74801c66bec81280740251bf1376c0a7f3d","abstract_canon_sha256":"bd635a817d52e2f8103ac4c87c921e150b811e2abb73552861ca5530e7c7cb66"},"schema_version":"1.0"},"canonical_sha256":"41ab491b3280008464be58a53e6a72b660161a2c63bc55a39f6edc1f3ec9ab63","source":{"kind":"arxiv","id":"2608.03874","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03874","created_at":"2026-08-05T01:37:17Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03874v1","created_at":"2026-08-05T01:37:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03874","created_at":"2026-08-05T01:37:17Z"},{"alias_kind":"pith_short_12","alias_value":"IGVUSGZSQAAI","created_at":"2026-08-05T01:37:17Z"},{"alias_kind":"pith_short_16","alias_value":"IGVUSGZSQAAIIZF6","created_at":"2026-08-05T01:37:17Z"},{"alias_kind":"pith_short_8","alias_value":"IGVUSGZS","created_at":"2026-08-05T01:37:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IGVUSGZSQAAIIZF6LCST42TSWZ","target":"record","payload":{"canonical_record":{"source":{"id":"2608.03874","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T16:15:02Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"24c59c9b385434f3d68c686eb6ace74801c66bec81280740251bf1376c0a7f3d","abstract_canon_sha256":"bd635a817d52e2f8103ac4c87c921e150b811e2abb73552861ca5530e7c7cb66"},"schema_version":"1.0"},"canonical_sha256":"41ab491b3280008464be58a53e6a72b660161a2c63bc55a39f6edc1f3ec9ab63","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:37:17.995270Z","signature_b64":"mmMFGh7aRkvMFz3eZHqhJpeIXT6jqyemzYgxGCggY22dgg2Kj4cSaz6Wq1+ra12vqx99OaO3w1ZAU8wAzq6bBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41ab491b3280008464be58a53e6a72b660161a2c63bc55a39f6edc1f3ec9ab63","last_reissued_at":"2026-08-05T01:37:17.993698Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:37:17.993698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.03874","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":"2026-08-05T01:37:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zaak/vxtArBMYHlK+Np9CPtmRakegjOCb+Y3x9MrZPjb4zK8wbkV8plX3NHFWdHepFFL1q8tcbYizEh83FtKBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:32:38.760989Z"},"content_sha256":"f969865b01e84c6c875dcf4c0b5199f5637cb0258e3cd306738223646465daaa","schema_version":"1.0","event_id":"sha256:f969865b01e84c6c875dcf4c0b5199f5637cb0258e3cd306738223646465daaa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IGVUSGZSQAAIIZF6LCST42TSWZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Haotong Yang, Jiaqi Li, Muhan Zhang, Shirui Liu, Siyuan Cao, Tianyi Guan, Yiding Wang, Yi Hu","submitted_at":"2026-08-04T16:15:02Z","abstract_excerpt":"Modern agent frameworks equip large language models with external skill libraries to solve complex tasks. However, it remains unclear whether these systems can effectively evolve their skills and whether the resulting skills improve task-solving capabilities. To bridge this gap, we introduce ContinualSkillBench, a dynamic evaluation framework for in-context continual skill learning. It covers five representative domains, each containing 100 interconnected subtasks ordered by increasing difficulty and opportunities for cross-task skill reuse. Our experiments show that sequential execution gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03874","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/2608.03874/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":"2026-08-05T01:37:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pzrav2PwnuyS530YQB/o2IQiUTLwotGxnP/lnA0Mx9RN5fyVBx4yRE9LUdhs2CUMu+E/awdYv+3scTK3OvEPDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:32:38.761545Z"},"content_sha256":"73aac5f115db1a575631dbe0e26cfb97fc6d7028a9912e0105bb0bebd4def1dc","schema_version":"1.0","event_id":"sha256:73aac5f115db1a575631dbe0e26cfb97fc6d7028a9912e0105bb0bebd4def1dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IGVUSGZSQAAIIZF6LCST42TSWZ/bundle.json","state_url":"https://pith.science/pith/IGVUSGZSQAAIIZF6LCST42TSWZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IGVUSGZSQAAIIZF6LCST42TSWZ/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":"2026-08-06T02:32:38Z","links":{"resolver":"https://pith.science/pith/IGVUSGZSQAAIIZF6LCST42TSWZ","bundle":"https://pith.science/pith/IGVUSGZSQAAIIZF6LCST42TSWZ/bundle.json","state":"https://pith.science/pith/IGVUSGZSQAAIIZF6LCST42TSWZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IGVUSGZSQAAIIZF6LCST42TSWZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IGVUSGZSQAAIIZF6LCST42TSWZ","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":"bd635a817d52e2f8103ac4c87c921e150b811e2abb73552861ca5530e7c7cb66","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T16:15:02Z","title_canon_sha256":"24c59c9b385434f3d68c686eb6ace74801c66bec81280740251bf1376c0a7f3d"},"schema_version":"1.0","source":{"id":"2608.03874","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03874","created_at":"2026-08-05T01:37:17Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03874v1","created_at":"2026-08-05T01:37:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03874","created_at":"2026-08-05T01:37:17Z"},{"alias_kind":"pith_short_12","alias_value":"IGVUSGZSQAAI","created_at":"2026-08-05T01:37:17Z"},{"alias_kind":"pith_short_16","alias_value":"IGVUSGZSQAAIIZF6","created_at":"2026-08-05T01:37:17Z"},{"alias_kind":"pith_short_8","alias_value":"IGVUSGZS","created_at":"2026-08-05T01:37:17Z"}],"graph_snapshots":[{"event_id":"sha256:73aac5f115db1a575631dbe0e26cfb97fc6d7028a9912e0105bb0bebd4def1dc","target":"graph","created_at":"2026-08-05T01:37:17Z","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/2608.03874/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern agent frameworks equip large language models with external skill libraries to solve complex tasks. However, it remains unclear whether these systems can effectively evolve their skills and whether the resulting skills improve task-solving capabilities. To bridge this gap, we introduce ContinualSkillBench, a dynamic evaluation framework for in-context continual skill learning. It covers five representative domains, each containing 100 interconnected subtasks ordered by increasing difficulty and opportunities for cross-task skill reuse. Our experiments show that sequential execution gener","authors_text":"Haotong Yang, Jiaqi Li, Muhan Zhang, Shirui Liu, Siyuan Cao, Tianyi Guan, Yiding Wang, Yi Hu","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T16:15:02Z","title":"ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03874","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:f969865b01e84c6c875dcf4c0b5199f5637cb0258e3cd306738223646465daaa","target":"record","created_at":"2026-08-05T01:37:17Z","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":"bd635a817d52e2f8103ac4c87c921e150b811e2abb73552861ca5530e7c7cb66","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T16:15:02Z","title_canon_sha256":"24c59c9b385434f3d68c686eb6ace74801c66bec81280740251bf1376c0a7f3d"},"schema_version":"1.0","source":{"id":"2608.03874","kind":"arxiv","version":1}},"canonical_sha256":"41ab491b3280008464be58a53e6a72b660161a2c63bc55a39f6edc1f3ec9ab63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41ab491b3280008464be58a53e6a72b660161a2c63bc55a39f6edc1f3ec9ab63","first_computed_at":"2026-08-05T01:37:17.993698Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T01:37:17.993698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mmMFGh7aRkvMFz3eZHqhJpeIXT6jqyemzYgxGCggY22dgg2Kj4cSaz6Wq1+ra12vqx99OaO3w1ZAU8wAzq6bBg==","signature_status":"signed_v1","signed_at":"2026-08-05T01:37:17.995270Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03874","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f969865b01e84c6c875dcf4c0b5199f5637cb0258e3cd306738223646465daaa","sha256:73aac5f115db1a575631dbe0e26cfb97fc6d7028a9912e0105bb0bebd4def1dc"],"state_sha256":"7e0a12877832bde59216661453c8bfe3041fe23a652f0a7afbd83f99974064be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"reT6d2Ypf5BUwn4vDKsQoGbK2ppv5GaP0AkndkWaHqdljkQLeQZ4eq1J1qXA59ahee0S7bmZYlBnCqvIKTlBCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T02:32:38.764817Z","bundle_sha256":"0e38cfa698a1b8928c2b824a800a5f1d5820c21d5884460b7bf6e0b854a19e30"}}