{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JLMBWP2NFNZO4WCQPG4TZYH4U7","short_pith_number":"pith:JLMBWP2N","canonical_record":{"source":{"id":"2608.04788","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-05T12:52:14Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c0a696808b301e900dd9fc9c38b6d54f4b0afc8209bf30a53eb8e70d001a6eed","abstract_canon_sha256":"8ec78863f987dd4554302c1a6ae466048d2a08c4a2db11f79a00b5a5fff223c8"},"schema_version":"1.0"},"canonical_sha256":"4ad81b3f4d2b72ee585079b93ce0fca7dea626855ff72cc9cfe95cd6eb5ec4b0","source":{"kind":"arxiv","id":"2608.04788","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.04788","created_at":"2026-08-06T01:47:06Z"},{"alias_kind":"arxiv_version","alias_value":"2608.04788v1","created_at":"2026-08-06T01:47:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04788","created_at":"2026-08-06T01:47:06Z"},{"alias_kind":"pith_short_12","alias_value":"JLMBWP2NFNZO","created_at":"2026-08-06T01:47:06Z"},{"alias_kind":"pith_short_16","alias_value":"JLMBWP2NFNZO4WCQ","created_at":"2026-08-06T01:47:06Z"},{"alias_kind":"pith_short_8","alias_value":"JLMBWP2N","created_at":"2026-08-06T01:47:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JLMBWP2NFNZO4WCQPG4TZYH4U7","target":"record","payload":{"canonical_record":{"source":{"id":"2608.04788","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-05T12:52:14Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c0a696808b301e900dd9fc9c38b6d54f4b0afc8209bf30a53eb8e70d001a6eed","abstract_canon_sha256":"8ec78863f987dd4554302c1a6ae466048d2a08c4a2db11f79a00b5a5fff223c8"},"schema_version":"1.0"},"canonical_sha256":"4ad81b3f4d2b72ee585079b93ce0fca7dea626855ff72cc9cfe95cd6eb5ec4b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:47:06.984273Z","signature_b64":"WjHNMGMbo0NytZmAgiq2a5nbVj+h6KdunZzMWonXK6b948SbKoducAy6R7MeDlrOD5pDnuMH1byHH3DYqWvnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ad81b3f4d2b72ee585079b93ce0fca7dea626855ff72cc9cfe95cd6eb5ec4b0","last_reissued_at":"2026-08-06T01:47:06.982734Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:47:06.982734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.04788","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":"2026-08-06T01:47:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oyFtlZcTPdTwdeAlXrmedTsaxOzK3QYaSkm6ErTLAOmaJiYi8l/KOyeh+1YLie1XQhP2qY7VwzOGRHtZrHjsBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:48:10.827709Z"},"content_sha256":"b834a131a01a3f2e778efe0e0cc7302aac55dece4101435e41e4a3d391feb788","schema_version":"1.0","event_id":"sha256:b834a131a01a3f2e778efe0e0cc7302aac55dece4101435e41e4a3d391feb788"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JLMBWP2NFNZO4WCQPG4TZYH4U7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Cao Liu, Chishui Chen, Cong Qin, Jiaye Lin, Lu Pan, Qing Dong, Xiaodan Liu, Yan Zhang, Yi Feng, Yi Yang, Zhao Yang","submitted_at":"2026-08-05T12:52:14Z","abstract_excerpt":"Large language model agents are commonly trained through reinforcement learning with sparse trajectory-level rewards, which offer limited guidance on how strongly individual tokens should be updated. On-Policy Self-Distillation (OPSD) addresses this by re-scoring generated tokens under a privileged replay view to obtain dense, token-level supervision. However, we identify a confounding issue: the resulting support may reflect both the privileged information contained in the replay view and score shifts induced by the replay scaffold, making it difficult to attribute the support specifically to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04788","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/2608.04788/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":"2026-08-06T01:47:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iO/JD1CdVuDS+sjpu2ED2vguQKevD7wbNH3gFSAQ9qH/Djl5L26X0GZOhEJMLRo1378mSU51zDJwbpzjKOFNDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:48:10.828238Z"},"content_sha256":"86f418ed016b416b91d720e3a34dd4898f0504b288a45e098d1f89b9e488d8bd","schema_version":"1.0","event_id":"sha256:86f418ed016b416b91d720e3a34dd4898f0504b288a45e098d1f89b9e488d8bd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JLMBWP2NFNZO4WCQPG4TZYH4U7/bundle.json","state_url":"https://pith.science/pith/JLMBWP2NFNZO4WCQPG4TZYH4U7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JLMBWP2NFNZO4WCQPG4TZYH4U7/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":"2026-08-09T23:48:10Z","links":{"resolver":"https://pith.science/pith/JLMBWP2NFNZO4WCQPG4TZYH4U7","bundle":"https://pith.science/pith/JLMBWP2NFNZO4WCQPG4TZYH4U7/bundle.json","state":"https://pith.science/pith/JLMBWP2NFNZO4WCQPG4TZYH4U7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JLMBWP2NFNZO4WCQPG4TZYH4U7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JLMBWP2NFNZO4WCQPG4TZYH4U7","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":"8ec78863f987dd4554302c1a6ae466048d2a08c4a2db11f79a00b5a5fff223c8","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-05T12:52:14Z","title_canon_sha256":"c0a696808b301e900dd9fc9c38b6d54f4b0afc8209bf30a53eb8e70d001a6eed"},"schema_version":"1.0","source":{"id":"2608.04788","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.04788","created_at":"2026-08-06T01:47:06Z"},{"alias_kind":"arxiv_version","alias_value":"2608.04788v1","created_at":"2026-08-06T01:47:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04788","created_at":"2026-08-06T01:47:06Z"},{"alias_kind":"pith_short_12","alias_value":"JLMBWP2NFNZO","created_at":"2026-08-06T01:47:06Z"},{"alias_kind":"pith_short_16","alias_value":"JLMBWP2NFNZO4WCQ","created_at":"2026-08-06T01:47:06Z"},{"alias_kind":"pith_short_8","alias_value":"JLMBWP2N","created_at":"2026-08-06T01:47:06Z"}],"graph_snapshots":[{"event_id":"sha256:86f418ed016b416b91d720e3a34dd4898f0504b288a45e098d1f89b9e488d8bd","target":"graph","created_at":"2026-08-06T01:47:06Z","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/2608.04788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model agents are commonly trained through reinforcement learning with sparse trajectory-level rewards, which offer limited guidance on how strongly individual tokens should be updated. On-Policy Self-Distillation (OPSD) addresses this by re-scoring generated tokens under a privileged replay view to obtain dense, token-level supervision. However, we identify a confounding issue: the resulting support may reflect both the privileged information contained in the replay view and score shifts induced by the replay scaffold, making it difficult to attribute the support specifically to","authors_text":"Cao Liu, Chishui Chen, Cong Qin, Jiaye Lin, Lu Pan, Qing Dong, Xiaodan Liu, Yan Zhang, Yi Feng, Yi Yang, Zhao Yang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-05T12:52:14Z","title":"Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04788","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:b834a131a01a3f2e778efe0e0cc7302aac55dece4101435e41e4a3d391feb788","target":"record","created_at":"2026-08-06T01:47:06Z","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":"8ec78863f987dd4554302c1a6ae466048d2a08c4a2db11f79a00b5a5fff223c8","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-05T12:52:14Z","title_canon_sha256":"c0a696808b301e900dd9fc9c38b6d54f4b0afc8209bf30a53eb8e70d001a6eed"},"schema_version":"1.0","source":{"id":"2608.04788","kind":"arxiv","version":1}},"canonical_sha256":"4ad81b3f4d2b72ee585079b93ce0fca7dea626855ff72cc9cfe95cd6eb5ec4b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ad81b3f4d2b72ee585079b93ce0fca7dea626855ff72cc9cfe95cd6eb5ec4b0","first_computed_at":"2026-08-06T01:47:06.982734Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-06T01:47:06.982734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WjHNMGMbo0NytZmAgiq2a5nbVj+h6KdunZzMWonXK6b948SbKoducAy6R7MeDlrOD5pDnuMH1byHH3DYqWvnCw==","signature_status":"signed_v1","signed_at":"2026-08-06T01:47:06.984273Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.04788","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b834a131a01a3f2e778efe0e0cc7302aac55dece4101435e41e4a3d391feb788","sha256:86f418ed016b416b91d720e3a34dd4898f0504b288a45e098d1f89b9e488d8bd"],"state_sha256":"6b4f0d43a8dedb3b91a5e624632159f2ff42d2e04ab4bb6b976e2469a1753671"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xb/s4WWxh54wRcO2bEKtVjRnYBIyUnayXQ9ayjgs5Q4xhK8cZId+HTZ0rPkDbk7uoKCQqY+zjjVm/jla0H43CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T23:48:10.833741Z","bundle_sha256":"4c5c7964b5afa718b04ab0bcca3c1ec62562fde24ef7b4db27937c10e4de09cb"}}