{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IIOXBUCHGH6WRDPUIGUVHRKIVX","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":"954ca6c99d9d2557f6879222423e91bc239d36cfba366db0df30a0914b68c656","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-28T16:11:47Z","title_canon_sha256":"11c6cac05795cf8392f3b1588719906e2f5340d17a508ae2c5bf2e6e3bdf6b5d"},"schema_version":"1.0","source":{"id":"2606.29476","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29476","created_at":"2026-06-30T01:18:08Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29476v1","created_at":"2026-06-30T01:18:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29476","created_at":"2026-06-30T01:18:08Z"},{"alias_kind":"pith_short_12","alias_value":"IIOXBUCHGH6W","created_at":"2026-06-30T01:18:08Z"},{"alias_kind":"pith_short_16","alias_value":"IIOXBUCHGH6WRDPU","created_at":"2026-06-30T01:18:08Z"},{"alias_kind":"pith_short_8","alias_value":"IIOXBUCH","created_at":"2026-06-30T01:18:08Z"}],"graph_snapshots":[{"event_id":"sha256:882ce547fb6ddc148ab55f490e0bbf520bcd290360903ab58747500216fb34bd","target":"graph","created_at":"2026-06-30T01:18:08Z","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/2606.29476/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-distilled agentic reinforcement learning augments trajectory-level reward with a token-level distillation loss, using as its teacher the same policy conditioned on privileged context. The prevailing recipe gates this loss by a single scalar, the teacher-student log-probability gap. This signal is doubly limited: it is retrospective, scoring only the realised rollout and never the counterfactual ones, and it is sign-blind, never signalling when a teacher-preferred action would have harmed the trajectory. We introduce CRAFT, a three-pillar credit-assignment scheme that addresses both limita","authors_text":"Kani Chen, Zibin Meng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-28T16:11:47Z","title":"CRAFT: Counterfactual Credit Assignment from Free Sibling Rollouts for Self-Distilled Agentic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29476","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":"sha256:956ec7c8bf7e5309b67edaa9ea799e654f05955b4b747810eaa884873fa3a19d","target":"record","created_at":"2026-06-30T01:18:08Z","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":"954ca6c99d9d2557f6879222423e91bc239d36cfba366db0df30a0914b68c656","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-28T16:11:47Z","title_canon_sha256":"11c6cac05795cf8392f3b1588719906e2f5340d17a508ae2c5bf2e6e3bdf6b5d"},"schema_version":"1.0","source":{"id":"2606.29476","kind":"arxiv","version":1}},"canonical_sha256":"421d70d04731fd688df441a953c548adcf0b999ee28ad524f801bab02f0080a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"421d70d04731fd688df441a953c548adcf0b999ee28ad524f801bab02f0080a7","first_computed_at":"2026-06-30T01:18:08.051419Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:18:08.051419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TP2OEaNsG0rpWXqFl1IDDP38ekY/yBoyqWtShWZEM/0e3XY8ZUwDN0iqkK/EFQaVK3AmcPc6ypMdizWqDQZUCQ==","signature_status":"signed_v1","signed_at":"2026-06-30T01:18:08.052081Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29476","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:956ec7c8bf7e5309b67edaa9ea799e654f05955b4b747810eaa884873fa3a19d","sha256:882ce547fb6ddc148ab55f490e0bbf520bcd290360903ab58747500216fb34bd"],"state_sha256":"98e55d277980fc4f7661497564d3d0bb924cc1c512f9ad573de9bbc6e254779f"}