{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QM5VVB336COC3HG3XM273LCC6X","short_pith_number":"pith:QM5VVB33","canonical_record":{"source":{"id":"2606.09348","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T11:20:58Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"72306d9c4b8e135399edb46c1b04668ce24e77259f9f28d8d391c4be93f3b23b","abstract_canon_sha256":"34c1cca698d470e0569f26f6b0e03aa3559a66aecaa0c0f69c912f5d3ee939b0"},"schema_version":"1.0"},"canonical_sha256":"833b5a877bf09c2d9cdbbb35fdac42f5ecc61b6cbfcda85068a87b399308037d","source":{"kind":"arxiv","id":"2606.09348","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09348","created_at":"2026-06-09T02:08:16Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09348v1","created_at":"2026-06-09T02:08:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09348","created_at":"2026-06-09T02:08:16Z"},{"alias_kind":"pith_short_12","alias_value":"QM5VVB336COC","created_at":"2026-06-09T02:08:16Z"},{"alias_kind":"pith_short_16","alias_value":"QM5VVB336COC3HG3","created_at":"2026-06-09T02:08:16Z"},{"alias_kind":"pith_short_8","alias_value":"QM5VVB33","created_at":"2026-06-09T02:08:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QM5VVB336COC3HG3XM273LCC6X","target":"record","payload":{"canonical_record":{"source":{"id":"2606.09348","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T11:20:58Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"72306d9c4b8e135399edb46c1b04668ce24e77259f9f28d8d391c4be93f3b23b","abstract_canon_sha256":"34c1cca698d470e0569f26f6b0e03aa3559a66aecaa0c0f69c912f5d3ee939b0"},"schema_version":"1.0"},"canonical_sha256":"833b5a877bf09c2d9cdbbb35fdac42f5ecc61b6cbfcda85068a87b399308037d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:16.877009Z","signature_b64":"amrUvlwbjLWosbHI5tjWUdK7jxNXXGJ8u5CSD/g7CBJs4IeDsuBOxKvGSm2NAMZelAIBl2g6vcYkxrDHMGh/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"833b5a877bf09c2d9cdbbb35fdac42f5ecc61b6cbfcda85068a87b399308037d","last_reissued_at":"2026-06-09T02:08:16.875933Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:16.875933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.09348","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":"2026-06-09T02:08:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SDKM6XnRb+HUL3LrMzCw+bySdaTTdQ9IuD9XxNKsElqIoBz+8XNqKMHcTSg6pUNFrzOZyaNhcmiCwvmFRRYSDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T02:57:35.096996Z"},"content_sha256":"8fae173c7c7b71703658e6024f9c77d79386506275e6850527eb6cf6b7e039c1","schema_version":"1.0","event_id":"sha256:8fae173c7c7b71703658e6024f9c77d79386506275e6850527eb6cf6b7e039c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QM5VVB336COC3HG3XM273LCC6X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Bo Zhao, Jiang Bian, Junjie Li, Lei Song, Rui Wang, Shizhao Sun, Xumeng Wen, Yang Tian","submitted_at":"2026-06-08T11:20:58Z","abstract_excerpt":"Long-horizon agentic tasks pose a fundamental credit assignment challenge for outcome-base reinforcement learning: trajectory-level rewards verify final correctness but provide limited guidance on which intermediate reasoning steps or tool interactions contribute to the outcome. The difficulty is especially pronounced in multi-turn search agents, where successful trajectories may contain misleading actions and failed trajectories may contain valuable evidence-gathering steps. We propose PBSD (Privileged Bayesian Self-Distillation), a Bayes-calibrated self-distillation method for fine-grained c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09348","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/2606.09348/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":"2026-06-09T02:08:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FAR68jZqBI/MTHrWn661sc5FbwbfQ7MHyiQ3E2gS8L3ocuJMyk5TsWN67JRPlX8qN/Se6d9wujYEpWouj6lwAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T02:57:35.097384Z"},"content_sha256":"269017115275755cbccf25e2fe8c86e84b3b9ab6435387b686fb76b60db3f93c","schema_version":"1.0","event_id":"sha256:269017115275755cbccf25e2fe8c86e84b3b9ab6435387b686fb76b60db3f93c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QM5VVB336COC3HG3XM273LCC6X/bundle.json","state_url":"https://pith.science/pith/QM5VVB336COC3HG3XM273LCC6X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QM5VVB336COC3HG3XM273LCC6X/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":"2026-06-20T02:57:35Z","links":{"resolver":"https://pith.science/pith/QM5VVB336COC3HG3XM273LCC6X","bundle":"https://pith.science/pith/QM5VVB336COC3HG3XM273LCC6X/bundle.json","state":"https://pith.science/pith/QM5VVB336COC3HG3XM273LCC6X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QM5VVB336COC3HG3XM273LCC6X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QM5VVB336COC3HG3XM273LCC6X","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":"34c1cca698d470e0569f26f6b0e03aa3559a66aecaa0c0f69c912f5d3ee939b0","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T11:20:58Z","title_canon_sha256":"72306d9c4b8e135399edb46c1b04668ce24e77259f9f28d8d391c4be93f3b23b"},"schema_version":"1.0","source":{"id":"2606.09348","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09348","created_at":"2026-06-09T02:08:16Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09348v1","created_at":"2026-06-09T02:08:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09348","created_at":"2026-06-09T02:08:16Z"},{"alias_kind":"pith_short_12","alias_value":"QM5VVB336COC","created_at":"2026-06-09T02:08:16Z"},{"alias_kind":"pith_short_16","alias_value":"QM5VVB336COC3HG3","created_at":"2026-06-09T02:08:16Z"},{"alias_kind":"pith_short_8","alias_value":"QM5VVB33","created_at":"2026-06-09T02:08:16Z"}],"graph_snapshots":[{"event_id":"sha256:269017115275755cbccf25e2fe8c86e84b3b9ab6435387b686fb76b60db3f93c","target":"graph","created_at":"2026-06-09T02:08:16Z","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/2606.09348/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-horizon agentic tasks pose a fundamental credit assignment challenge for outcome-base reinforcement learning: trajectory-level rewards verify final correctness but provide limited guidance on which intermediate reasoning steps or tool interactions contribute to the outcome. The difficulty is especially pronounced in multi-turn search agents, where successful trajectories may contain misleading actions and failed trajectories may contain valuable evidence-gathering steps. We propose PBSD (Privileged Bayesian Self-Distillation), a Bayes-calibrated self-distillation method for fine-grained c","authors_text":"Bo Zhao, Jiang Bian, Junjie Li, Lei Song, Rui Wang, Shizhao Sun, Xumeng Wen, Yang Tian","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T11:20:58Z","title":"PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09348","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":"sha256:8fae173c7c7b71703658e6024f9c77d79386506275e6850527eb6cf6b7e039c1","target":"record","created_at":"2026-06-09T02:08:16Z","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":"34c1cca698d470e0569f26f6b0e03aa3559a66aecaa0c0f69c912f5d3ee939b0","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T11:20:58Z","title_canon_sha256":"72306d9c4b8e135399edb46c1b04668ce24e77259f9f28d8d391c4be93f3b23b"},"schema_version":"1.0","source":{"id":"2606.09348","kind":"arxiv","version":1}},"canonical_sha256":"833b5a877bf09c2d9cdbbb35fdac42f5ecc61b6cbfcda85068a87b399308037d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"833b5a877bf09c2d9cdbbb35fdac42f5ecc61b6cbfcda85068a87b399308037d","first_computed_at":"2026-06-09T02:08:16.875933Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:08:16.875933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"amrUvlwbjLWosbHI5tjWUdK7jxNXXGJ8u5CSD/g7CBJs4IeDsuBOxKvGSm2NAMZelAIBl2g6vcYkxrDHMGh/DQ==","signature_status":"signed_v1","signed_at":"2026-06-09T02:08:16.877009Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09348","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fae173c7c7b71703658e6024f9c77d79386506275e6850527eb6cf6b7e039c1","sha256:269017115275755cbccf25e2fe8c86e84b3b9ab6435387b686fb76b60db3f93c"],"state_sha256":"f8fcf36af1707c03e69e1f0d1e10fec79ab0717e7806e9f78ba44a1b2964546d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iH4HXbTXrC1XaRTne3FJqVL0xwRi/ee6Zg7wOGrkAfwNY7EUfH3NHog66Ds92pWdpoqe1EY4IyYzhmSDKzTzBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T02:57:35.099385Z","bundle_sha256":"3ea9957273197e44258bef310d05faca3cf500a6bcf64207f1b5c4d97cee6a36"}}