{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MPRKBPNKRNSRNUJ2S4ANRV4GQN","short_pith_number":"pith:MPRKBPNK","canonical_record":{"source":{"id":"2601.15141","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-21T16:14:30Z","cross_cats_sorted":[],"title_canon_sha256":"5aed5262275a4f40186f3d62c8ef9ceb0d2768511eea2d5082811e68352d4bb6","abstract_canon_sha256":"0b7663d1bb3c3095e0d7077456ffecb6d7cc1e8efba62005c306fd04379015a1"},"schema_version":"1.0"},"canonical_sha256":"63e2a0bdaa8b6516d13a9700d8d786834fba13baa3ba57b5f8d31bb8679ebf75","source":{"kind":"arxiv","id":"2601.15141","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.15141","created_at":"2026-07-07T01:16:04Z"},{"alias_kind":"arxiv_version","alias_value":"2601.15141v2","created_at":"2026-07-07T01:16:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.15141","created_at":"2026-07-07T01:16:04Z"},{"alias_kind":"pith_short_12","alias_value":"MPRKBPNKRNSR","created_at":"2026-07-07T01:16:04Z"},{"alias_kind":"pith_short_16","alias_value":"MPRKBPNKRNSRNUJ2","created_at":"2026-07-07T01:16:04Z"},{"alias_kind":"pith_short_8","alias_value":"MPRKBPNK","created_at":"2026-07-07T01:16:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MPRKBPNKRNSRNUJ2S4ANRV4GQN","target":"record","payload":{"canonical_record":{"source":{"id":"2601.15141","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-21T16:14:30Z","cross_cats_sorted":[],"title_canon_sha256":"5aed5262275a4f40186f3d62c8ef9ceb0d2768511eea2d5082811e68352d4bb6","abstract_canon_sha256":"0b7663d1bb3c3095e0d7077456ffecb6d7cc1e8efba62005c306fd04379015a1"},"schema_version":"1.0"},"canonical_sha256":"63e2a0bdaa8b6516d13a9700d8d786834fba13baa3ba57b5f8d31bb8679ebf75","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:16:04.615070Z","signature_b64":"avQoUFfBdYElyAesEcpzMtIZohCo6k4T/bAV+0F+bCAbj4EmgMX1QV358FRqEs+RBM3HFrrn6vAaMyCHGTL9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63e2a0bdaa8b6516d13a9700d8d786834fba13baa3ba57b5f8d31bb8679ebf75","last_reissued_at":"2026-07-07T01:16:04.614224Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:16:04.614224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.15141","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":"2026-07-07T01:16:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rn/FyI8h5OyL2Umttib+OTDT5YJqdbEVJxmllqXwXq+X7Vr6g3xUro+1QMGzq/a2NpMrCDTPGiJYmh8sTyxnAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:11:23.129036Z"},"content_sha256":"e3cb7df15744db2269ad3a94d11c7e147c1b0f9b28a921d39891297d5978d4bd","schema_version":"1.0","event_id":"sha256:e3cb7df15744db2269ad3a94d11c7e147c1b0f9b28a921d39891297d5978d4bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MPRKBPNKRNSRNUJ2S4ANRV4GQN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Meng Li, Tianshi Xu, Yuteng Chen","submitted_at":"2026-01-21T16:14:30Z","abstract_excerpt":"Agentic Reinforcement Learning (RL) has empowered Large Language Models (LLMs) to utilize tools like Python interpreters for complex problem-solving. However, for parameter-constrained models (e.g., 4B--7B), the exploration phase is often plagued by frequent execution failures, creating noisy trajectories that hinder policy optimization. Under standard outcome-based reward settings, this noise leads to a critical credit assignment issue, where erroneous actions are inadvertently reinforced alongside successful outcomes. Existing mitigations face a dilemma: dense rewards often trigger reward ha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.15141","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/2601.15141/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":"2026-07-07T01:16:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NN2ZFcizHlm6UdJwWLVyMaPSJWdEIk4vf6uDklZDks5pfhF4qSuIxFlcuOfZsP9wuwYg9qgM99s/n0uye1G5BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:11:23.129918Z"},"content_sha256":"1b7222615bf6fcd49371cc10f4eec5bf51346f16a2564333daa8a6bbc16f5c18","schema_version":"1.0","event_id":"sha256:1b7222615bf6fcd49371cc10f4eec5bf51346f16a2564333daa8a6bbc16f5c18"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MPRKBPNKRNSRNUJ2S4ANRV4GQN/bundle.json","state_url":"https://pith.science/pith/MPRKBPNKRNSRNUJ2S4ANRV4GQN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MPRKBPNKRNSRNUJ2S4ANRV4GQN/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":"2026-08-04T06:11:23Z","links":{"resolver":"https://pith.science/pith/MPRKBPNKRNSRNUJ2S4ANRV4GQN","bundle":"https://pith.science/pith/MPRKBPNKRNSRNUJ2S4ANRV4GQN/bundle.json","state":"https://pith.science/pith/MPRKBPNKRNSRNUJ2S4ANRV4GQN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MPRKBPNKRNSRNUJ2S4ANRV4GQN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MPRKBPNKRNSRNUJ2S4ANRV4GQN","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":"0b7663d1bb3c3095e0d7077456ffecb6d7cc1e8efba62005c306fd04379015a1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-21T16:14:30Z","title_canon_sha256":"5aed5262275a4f40186f3d62c8ef9ceb0d2768511eea2d5082811e68352d4bb6"},"schema_version":"1.0","source":{"id":"2601.15141","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.15141","created_at":"2026-07-07T01:16:04Z"},{"alias_kind":"arxiv_version","alias_value":"2601.15141v2","created_at":"2026-07-07T01:16:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.15141","created_at":"2026-07-07T01:16:04Z"},{"alias_kind":"pith_short_12","alias_value":"MPRKBPNKRNSR","created_at":"2026-07-07T01:16:04Z"},{"alias_kind":"pith_short_16","alias_value":"MPRKBPNKRNSRNUJ2","created_at":"2026-07-07T01:16:04Z"},{"alias_kind":"pith_short_8","alias_value":"MPRKBPNK","created_at":"2026-07-07T01:16:04Z"}],"graph_snapshots":[{"event_id":"sha256:1b7222615bf6fcd49371cc10f4eec5bf51346f16a2564333daa8a6bbc16f5c18","target":"graph","created_at":"2026-07-07T01:16:04Z","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/2601.15141/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agentic Reinforcement Learning (RL) has empowered Large Language Models (LLMs) to utilize tools like Python interpreters for complex problem-solving. However, for parameter-constrained models (e.g., 4B--7B), the exploration phase is often plagued by frequent execution failures, creating noisy trajectories that hinder policy optimization. Under standard outcome-based reward settings, this noise leads to a critical credit assignment issue, where erroneous actions are inadvertently reinforced alongside successful outcomes. Existing mitigations face a dilemma: dense rewards often trigger reward ha","authors_text":"Meng Li, Tianshi Xu, Yuteng Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-21T16:14:30Z","title":"CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.15141","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:e3cb7df15744db2269ad3a94d11c7e147c1b0f9b28a921d39891297d5978d4bd","target":"record","created_at":"2026-07-07T01:16:04Z","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":"0b7663d1bb3c3095e0d7077456ffecb6d7cc1e8efba62005c306fd04379015a1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-21T16:14:30Z","title_canon_sha256":"5aed5262275a4f40186f3d62c8ef9ceb0d2768511eea2d5082811e68352d4bb6"},"schema_version":"1.0","source":{"id":"2601.15141","kind":"arxiv","version":2}},"canonical_sha256":"63e2a0bdaa8b6516d13a9700d8d786834fba13baa3ba57b5f8d31bb8679ebf75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63e2a0bdaa8b6516d13a9700d8d786834fba13baa3ba57b5f8d31bb8679ebf75","first_computed_at":"2026-07-07T01:16:04.614224Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T01:16:04.614224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"avQoUFfBdYElyAesEcpzMtIZohCo6k4T/bAV+0F+bCAbj4EmgMX1QV358FRqEs+RBM3HFrrn6vAaMyCHGTL9BA==","signature_status":"signed_v1","signed_at":"2026-07-07T01:16:04.615070Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.15141","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3cb7df15744db2269ad3a94d11c7e147c1b0f9b28a921d39891297d5978d4bd","sha256:1b7222615bf6fcd49371cc10f4eec5bf51346f16a2564333daa8a6bbc16f5c18"],"state_sha256":"e0aa027d8c96ee835b7763331408b51e41141d560ef46f21441d70294308b01f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y6xUWv12IZ9iJSDT7XnIC+b+ibFwU2jGlF5csQzk+P8zZxZv9NF89NBW8LcXpa3+ORsW4c9KBloomWGYUivrDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T06:11:23.136327Z","bundle_sha256":"acbc1829ac4a59a202e66178347fb4d4ab4cebf2bbc8dfea273232bc022963eb"}}