{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DEGV7IIVFYXYPULUVA2JKZESY3","short_pith_number":"pith:DEGV7IIV","canonical_record":{"source":{"id":"2601.18510","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-26T14:16:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e9d7ddadf31ed47c536d491f78a13b58489d1e1a9cabd5e0b029bfa2630684c7","abstract_canon_sha256":"79d6fdce703f78a9085265420514cff74f9514907c031115fe0c7cd703c242c9"},"schema_version":"1.0"},"canonical_sha256":"190d5fa1152e2f87d174a834956492c6f6b66e467199dbe0319641efc268f0dd","source":{"kind":"arxiv","id":"2601.18510","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.18510","created_at":"2026-06-08T01:03:56Z"},{"alias_kind":"arxiv_version","alias_value":"2601.18510v2","created_at":"2026-06-08T01:03:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.18510","created_at":"2026-06-08T01:03:56Z"},{"alias_kind":"pith_short_12","alias_value":"DEGV7IIVFYXY","created_at":"2026-06-08T01:03:56Z"},{"alias_kind":"pith_short_16","alias_value":"DEGV7IIVFYXYPULU","created_at":"2026-06-08T01:03:56Z"},{"alias_kind":"pith_short_8","alias_value":"DEGV7IIV","created_at":"2026-06-08T01:03:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DEGV7IIVFYXYPULUVA2JKZESY3","target":"record","payload":{"canonical_record":{"source":{"id":"2601.18510","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-26T14:16:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e9d7ddadf31ed47c536d491f78a13b58489d1e1a9cabd5e0b029bfa2630684c7","abstract_canon_sha256":"79d6fdce703f78a9085265420514cff74f9514907c031115fe0c7cd703c242c9"},"schema_version":"1.0"},"canonical_sha256":"190d5fa1152e2f87d174a834956492c6f6b66e467199dbe0319641efc268f0dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:03:56.377999Z","signature_b64":"3iKhF/u159mAsFKxg0EQ0gHCRsqvt6Wn7xkX9EVjp+dF+OiQcItB6D1VVkZ1L2DP7R2aoJSnSCW9RfX4iX9oAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"190d5fa1152e2f87d174a834956492c6f6b66e467199dbe0319641efc268f0dd","last_reissued_at":"2026-06-08T01:03:56.377023Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:03:56.377023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.18510","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-08T01:03:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UMgJCmZbLUHWJxglzeyhf+xuKCZaKtVlJ0Yw+pAoixTxQDA4ozpefTSyKl0Y3WQ/9bnOfzqCGTrd7euBi7YAAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T15:40:09.052615Z"},"content_sha256":"110478d12d4b956fa7208753eab6f6b87be98e712528b4e776f0bbdfcc92e7ae","schema_version":"1.0","event_id":"sha256:110478d12d4b956fa7208753eab6f6b87be98e712528b4e776f0bbdfcc92e7ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DEGV7IIVFYXYPULUVA2JKZESY3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ailin Deng, Bryan Hooi, Shuo Ji, Tri Cao, Xuan Zhang, Yibo Li, Yufei He, Zijie Lin","submitted_at":"2026-01-26T14:16:51Z","abstract_excerpt":"While Large Language Model (LLM) agents excel at general tasks, they inherently struggle with continual adaptation due to the frozen weights after deployment. Conventional reinforcement learning (RL) offers a solution but incurs prohibitive computational costs and the risk of catastrophic forgetting. We introduce Just-In-Time Reinforcement Learning (JitRL), a training-free framework that enables test-time policy optimization without any gradient updates. JitRL maintains a dynamic, non-parametric memory of experiences and retrieves relevant trajectories to estimate action advantages on-the-fly."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.18510","kind":"arxiv","version":2},"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/2601.18510/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":"2026-06-08T01:03:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rvm+TZA+WfAIj6oR56K9ijn9IU1JrTIabLvL1bHhnOpQjCzpq/6tmUjLDOCYTYKPC3YSivCwrUHXuOWM5jzzBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T15:40:09.053480Z"},"content_sha256":"400568541034fd2c8d14d8cde0e10615bd85e8ae07088e9ef55eeb6842223088","schema_version":"1.0","event_id":"sha256:400568541034fd2c8d14d8cde0e10615bd85e8ae07088e9ef55eeb6842223088"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DEGV7IIVFYXYPULUVA2JKZESY3/bundle.json","state_url":"https://pith.science/pith/DEGV7IIVFYXYPULUVA2JKZESY3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DEGV7IIVFYXYPULUVA2JKZESY3/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":"2026-06-08T15:40:09Z","links":{"resolver":"https://pith.science/pith/DEGV7IIVFYXYPULUVA2JKZESY3","bundle":"https://pith.science/pith/DEGV7IIVFYXYPULUVA2JKZESY3/bundle.json","state":"https://pith.science/pith/DEGV7IIVFYXYPULUVA2JKZESY3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DEGV7IIVFYXYPULUVA2JKZESY3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DEGV7IIVFYXYPULUVA2JKZESY3","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":"79d6fdce703f78a9085265420514cff74f9514907c031115fe0c7cd703c242c9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-26T14:16:51Z","title_canon_sha256":"e9d7ddadf31ed47c536d491f78a13b58489d1e1a9cabd5e0b029bfa2630684c7"},"schema_version":"1.0","source":{"id":"2601.18510","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.18510","created_at":"2026-06-08T01:03:56Z"},{"alias_kind":"arxiv_version","alias_value":"2601.18510v2","created_at":"2026-06-08T01:03:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.18510","created_at":"2026-06-08T01:03:56Z"},{"alias_kind":"pith_short_12","alias_value":"DEGV7IIVFYXY","created_at":"2026-06-08T01:03:56Z"},{"alias_kind":"pith_short_16","alias_value":"DEGV7IIVFYXYPULU","created_at":"2026-06-08T01:03:56Z"},{"alias_kind":"pith_short_8","alias_value":"DEGV7IIV","created_at":"2026-06-08T01:03:56Z"}],"graph_snapshots":[{"event_id":"sha256:400568541034fd2c8d14d8cde0e10615bd85e8ae07088e9ef55eeb6842223088","target":"graph","created_at":"2026-06-08T01:03:56Z","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/2601.18510/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Large Language Model (LLM) agents excel at general tasks, they inherently struggle with continual adaptation due to the frozen weights after deployment. Conventional reinforcement learning (RL) offers a solution but incurs prohibitive computational costs and the risk of catastrophic forgetting. We introduce Just-In-Time Reinforcement Learning (JitRL), a training-free framework that enables test-time policy optimization without any gradient updates. JitRL maintains a dynamic, non-parametric memory of experiences and retrieves relevant trajectories to estimate action advantages on-the-fly.","authors_text":"Ailin Deng, Bryan Hooi, Shuo Ji, Tri Cao, Xuan Zhang, Yibo Li, Yufei He, Zijie Lin","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-26T14:16:51Z","title":"Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.18510","kind":"arxiv","version":2},"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":"sha256:110478d12d4b956fa7208753eab6f6b87be98e712528b4e776f0bbdfcc92e7ae","target":"record","created_at":"2026-06-08T01:03:56Z","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":"79d6fdce703f78a9085265420514cff74f9514907c031115fe0c7cd703c242c9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-26T14:16:51Z","title_canon_sha256":"e9d7ddadf31ed47c536d491f78a13b58489d1e1a9cabd5e0b029bfa2630684c7"},"schema_version":"1.0","source":{"id":"2601.18510","kind":"arxiv","version":2}},"canonical_sha256":"190d5fa1152e2f87d174a834956492c6f6b66e467199dbe0319641efc268f0dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"190d5fa1152e2f87d174a834956492c6f6b66e467199dbe0319641efc268f0dd","first_computed_at":"2026-06-08T01:03:56.377023Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:03:56.377023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3iKhF/u159mAsFKxg0EQ0gHCRsqvt6Wn7xkX9EVjp+dF+OiQcItB6D1VVkZ1L2DP7R2aoJSnSCW9RfX4iX9oAw==","signature_status":"signed_v1","signed_at":"2026-06-08T01:03:56.377999Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.18510","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:110478d12d4b956fa7208753eab6f6b87be98e712528b4e776f0bbdfcc92e7ae","sha256:400568541034fd2c8d14d8cde0e10615bd85e8ae07088e9ef55eeb6842223088"],"state_sha256":"f04a52678ca8bb523bd3f7538a2fc25ab996d623a397612d12341574ebfd0e63"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2nx/wDCXiYnvqffqR1fr102v52wVp9PkoSenYUbhyCi0/5c7G/8VtLn6iBgT/BH6PrLs00+4DO1kWXO9238FCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T15:40:09.062015Z","bundle_sha256":"52b615cfce5a66df549c05fb6d3b34a1c5677cdda70cff01ac267f3450d383ee"}}