{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:RCF65HK36IPNXMUMKNPK36CCGZ","short_pith_number":"pith:RCF65HK3","canonical_record":{"source":{"id":"2604.08988","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-10T05:49:50Z","cross_cats_sorted":[],"title_canon_sha256":"91bcea8d3ea6453766ce8714ab436ac17368eb54a20d24573fc0b71276e4b085","abstract_canon_sha256":"25c4bca7fb3ad2de5949922b4df69798dfc61a08ba3dfd00145975b327d6836f"},"schema_version":"1.0"},"canonical_sha256":"888bee9d5bf21edbb28c535eadf8423679e0bbad79c4da371aa9d912cd88008f","source":{"kind":"arxiv","id":"2604.08988","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.08988","created_at":"2026-05-26T01:03:29Z"},{"alias_kind":"arxiv_version","alias_value":"2604.08988v3","created_at":"2026-05-26T01:03:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.08988","created_at":"2026-05-26T01:03:29Z"},{"alias_kind":"pith_short_12","alias_value":"RCF65HK36IPN","created_at":"2026-05-26T01:03:29Z"},{"alias_kind":"pith_short_16","alias_value":"RCF65HK36IPNXMUM","created_at":"2026-05-26T01:03:29Z"},{"alias_kind":"pith_short_8","alias_value":"RCF65HK3","created_at":"2026-05-26T01:03:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:RCF65HK36IPNXMUMKNPK36CCGZ","target":"record","payload":{"canonical_record":{"source":{"id":"2604.08988","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-10T05:49:50Z","cross_cats_sorted":[],"title_canon_sha256":"91bcea8d3ea6453766ce8714ab436ac17368eb54a20d24573fc0b71276e4b085","abstract_canon_sha256":"25c4bca7fb3ad2de5949922b4df69798dfc61a08ba3dfd00145975b327d6836f"},"schema_version":"1.0"},"canonical_sha256":"888bee9d5bf21edbb28c535eadf8423679e0bbad79c4da371aa9d912cd88008f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:29.708905Z","signature_b64":"XeINiZGR0LU3D5Ck11vkudxvrUV07mN8Zwvwv2fX3JFCr+TeevvDfKksuQZ1Mx9A24Wsr3WTLwahqdIy2BjCDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"888bee9d5bf21edbb28c535eadf8423679e0bbad79c4da371aa9d912cd88008f","last_reissued_at":"2026-05-26T01:03:29.708097Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:29.708097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.08988","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:03:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qE4fdC3BN4TzIX4HPrKeUlF4+nZ7oaeS1UYSrYHzgQFtTzxZOFgX3HkwQaQ566uNtEcm18CNK0exSJqtZeNRCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T17:00:06.832700Z"},"content_sha256":"0275062da5b4f7495325413b0594baf0343f965b6103db650c6f6095963efd53","schema_version":"1.0","event_id":"sha256:0275062da5b4f7495325413b0594baf0343f965b6103db650c6f6095963efd53"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:RCF65HK36IPNXMUMKNPK36CCGZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Success rate alone creates a capability illusion for LLM agents, while the sequential convergence of token consumption distinguishes genuine self-evolution from pseudo-evolution.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiaqing Liang, Jinghao Zhang, Keyi Wang, Lipeng Ma, Shisong Chen, Sihang Jiang, Tengfei Wang, Tianjun Pan, Weijia Li, Yanghua Xiao, Zhiyu Lu, Zhonghua Hong","submitted_at":"2026-04-10T05:49:50Z","abstract_excerpt":"Current LLM-based agents demonstrate strong performance in episodic task execution but remain constrained by static toolsets and episodic amnesia, failing to accumulate experience across task boundaries. This paper formalizes the Self-Evolving Agent (SEA) from the perspective of digital embodiment and continuous cross-task evolution, introduces the Evolutionary Flywheel as its minimal sufficient architecture, and presents SEA-Eval -- the first benchmark designed specifically for evaluating SEAs. Grounded in Flywheel theory, SEA-Eval establishes SR and T as primary metrics and, through sequenti"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"under identical success rates, token consumption differs by up to 31.2× across frameworks, with divergent evolutionary trajectories under sequential analysis -- demonstrating that success rate alone creates a capability illusion and that the sequential convergence of T is the key criterion for distinguishing genuine evolution from pseudo-evolution.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the sequential task stream design in SEA-Eval enables independent quantification of evolutionary gain, stability, and alignment without confounding from task similarity, agent initialization, or unstated priors in the Flywheel architecture.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SEA-Eval is the first benchmark for self-evolving agents that uses sequential tasks to show success rate alone misleads while convergence in token efficiency T distinguishes genuine evolution.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Success rate alone creates a capability illusion for LLM agents, while the sequential convergence of token consumption distinguishes genuine self-evolution from pseudo-evolution.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"db6caf6fbe4016db007fa5dd53f282b14c8c600035e1eaaa8e3d05d47dcbb344"},"source":{"id":"2604.08988","kind":"arxiv","version":3},"verdict":{"id":"22a8fe45-74b0-4695-bac5-298eec0eeba1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T17:48:15.540110Z","strongest_claim":"under identical success rates, token consumption differs by up to 31.2× across frameworks, with divergent evolutionary trajectories under sequential analysis -- demonstrating that success rate alone creates a capability illusion and that the sequential convergence of T is the key criterion for distinguishing genuine evolution from pseudo-evolution.","one_line_summary":"SEA-Eval is the first benchmark for self-evolving agents that uses sequential tasks to show success rate alone misleads while convergence in token efficiency T distinguishes genuine evolution.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the sequential task stream design in SEA-Eval enables independent quantification of evolutionary gain, stability, and alignment without confounding from task similarity, agent initialization, or unstated priors in the Flywheel architecture.","pith_extraction_headline":"Success rate alone creates a capability illusion for LLM agents, while the sequential convergence of token consumption distinguishes genuine self-evolution from pseudo-evolution."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.08988/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":2,"snapshot_sha256":"4871c66d70ec8ad33fb3e7069cad3e31d39cde3acad81e229eaad8a868c43bab"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"22a8fe45-74b0-4695-bac5-298eec0eeba1"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:03:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9kPcoib79i47w75aXlOKyCUYEwEdV7OI2ai60Hc1NQPPQDzg2LIC/zPxqML4A4bvCC2xRv/S9Wv7WihGX8rIDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T17:00:06.833192Z"},"content_sha256":"6c57098447a20ec189e6782f68e409d2d65aaf899d4cae3dca41cc5f15dd19e4","schema_version":"1.0","event_id":"sha256:6c57098447a20ec189e6782f68e409d2d65aaf899d4cae3dca41cc5f15dd19e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RCF65HK36IPNXMUMKNPK36CCGZ/bundle.json","state_url":"https://pith.science/pith/RCF65HK36IPNXMUMKNPK36CCGZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RCF65HK36IPNXMUMKNPK36CCGZ/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":"2026-06-01T17:00:06Z","links":{"resolver":"https://pith.science/pith/RCF65HK36IPNXMUMKNPK36CCGZ","bundle":"https://pith.science/pith/RCF65HK36IPNXMUMKNPK36CCGZ/bundle.json","state":"https://pith.science/pith/RCF65HK36IPNXMUMKNPK36CCGZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RCF65HK36IPNXMUMKNPK36CCGZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RCF65HK36IPNXMUMKNPK36CCGZ","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":"25c4bca7fb3ad2de5949922b4df69798dfc61a08ba3dfd00145975b327d6836f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-10T05:49:50Z","title_canon_sha256":"91bcea8d3ea6453766ce8714ab436ac17368eb54a20d24573fc0b71276e4b085"},"schema_version":"1.0","source":{"id":"2604.08988","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.08988","created_at":"2026-05-26T01:03:29Z"},{"alias_kind":"arxiv_version","alias_value":"2604.08988v3","created_at":"2026-05-26T01:03:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.08988","created_at":"2026-05-26T01:03:29Z"},{"alias_kind":"pith_short_12","alias_value":"RCF65HK36IPN","created_at":"2026-05-26T01:03:29Z"},{"alias_kind":"pith_short_16","alias_value":"RCF65HK36IPNXMUM","created_at":"2026-05-26T01:03:29Z"},{"alias_kind":"pith_short_8","alias_value":"RCF65HK3","created_at":"2026-05-26T01:03:29Z"}],"graph_snapshots":[{"event_id":"sha256:6c57098447a20ec189e6782f68e409d2d65aaf899d4cae3dca41cc5f15dd19e4","target":"graph","created_at":"2026-05-26T01:03:29Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"under identical success rates, token consumption differs by up to 31.2× across frameworks, with divergent evolutionary trajectories under sequential analysis -- demonstrating that success rate alone creates a capability illusion and that the sequential convergence of T is the key criterion for distinguishing genuine evolution from pseudo-evolution."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the sequential task stream design in SEA-Eval enables independent quantification of evolutionary gain, stability, and alignment without confounding from task similarity, agent initialization, or unstated priors in the Flywheel architecture."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SEA-Eval is the first benchmark for self-evolving agents that uses sequential tasks to show success rate alone misleads while convergence in token efficiency T distinguishes genuine evolution."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Success rate alone creates a capability illusion for LLM agents, while the sequential convergence of token consumption distinguishes genuine self-evolution from pseudo-evolution."}],"snapshot_sha256":"db6caf6fbe4016db007fa5dd53f282b14c8c600035e1eaaa8e3d05d47dcbb344"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"4871c66d70ec8ad33fb3e7069cad3e31d39cde3acad81e229eaad8a868c43bab"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.08988/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current LLM-based agents demonstrate strong performance in episodic task execution but remain constrained by static toolsets and episodic amnesia, failing to accumulate experience across task boundaries. This paper formalizes the Self-Evolving Agent (SEA) from the perspective of digital embodiment and continuous cross-task evolution, introduces the Evolutionary Flywheel as its minimal sufficient architecture, and presents SEA-Eval -- the first benchmark designed specifically for evaluating SEAs. Grounded in Flywheel theory, SEA-Eval establishes SR and T as primary metrics and, through sequenti","authors_text":"Jiaqing Liang, Jinghao Zhang, Keyi Wang, Lipeng Ma, Shisong Chen, Sihang Jiang, Tengfei Wang, Tianjun Pan, Weijia Li, Yanghua Xiao, Zhiyu Lu, Zhonghua Hong","cross_cats":[],"headline":"Success rate alone creates a capability illusion for LLM agents, while the sequential convergence of token consumption distinguishes genuine self-evolution from pseudo-evolution.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-10T05:49:50Z","title":"SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.08988","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-10T17:48:15.540110Z","id":"22a8fe45-74b0-4695-bac5-298eec0eeba1","model_set":{"reader":"grok-4.3"},"one_line_summary":"SEA-Eval is the first benchmark for self-evolving agents that uses sequential tasks to show success rate alone misleads while convergence in token efficiency T distinguishes genuine evolution.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Success rate alone creates a capability illusion for LLM agents, while the sequential convergence of token consumption distinguishes genuine self-evolution from pseudo-evolution.","strongest_claim":"under identical success rates, token consumption differs by up to 31.2× across frameworks, with divergent evolutionary trajectories under sequential analysis -- demonstrating that success rate alone creates a capability illusion and that the sequential convergence of T is the key criterion for distinguishing genuine evolution from pseudo-evolution.","weakest_assumption":"That the sequential task stream design in SEA-Eval enables independent quantification of evolutionary gain, stability, and alignment without confounding from task similarity, agent initialization, or unstated priors in the Flywheel architecture."}},"verdict_id":"22a8fe45-74b0-4695-bac5-298eec0eeba1"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0275062da5b4f7495325413b0594baf0343f965b6103db650c6f6095963efd53","target":"record","created_at":"2026-05-26T01:03:29Z","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":"25c4bca7fb3ad2de5949922b4df69798dfc61a08ba3dfd00145975b327d6836f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-10T05:49:50Z","title_canon_sha256":"91bcea8d3ea6453766ce8714ab436ac17368eb54a20d24573fc0b71276e4b085"},"schema_version":"1.0","source":{"id":"2604.08988","kind":"arxiv","version":3}},"canonical_sha256":"888bee9d5bf21edbb28c535eadf8423679e0bbad79c4da371aa9d912cd88008f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"888bee9d5bf21edbb28c535eadf8423679e0bbad79c4da371aa9d912cd88008f","first_computed_at":"2026-05-26T01:03:29.708097Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:29.708097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XeINiZGR0LU3D5Ck11vkudxvrUV07mN8Zwvwv2fX3JFCr+TeevvDfKksuQZ1Mx9A24Wsr3WTLwahqdIy2BjCDg==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:29.708905Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.08988","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0275062da5b4f7495325413b0594baf0343f965b6103db650c6f6095963efd53","sha256:6c57098447a20ec189e6782f68e409d2d65aaf899d4cae3dca41cc5f15dd19e4"],"state_sha256":"4b70128e9d6ab1cd34ba33a00cc6d71575391ad3874f4c03fac85db5545061b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VOXYZ9jIpllD6jaigNg7DJnJhBDrFcNkBe6PgHqOqSB4V9QM4FoW2LOcFJU6z+gk4u5LPuSeMp8b1HcKDVdRBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T17:00:06.835517Z","bundle_sha256":"993e40b024e3bfec179c4a5c69af49f0f6430e101d925456b415e2fa7795d1f9"}}