{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IIOXBUCHGH6WRDPUIGUVHRKIVX","short_pith_number":"pith:IIOXBUCH","schema_version":"1.0","canonical_sha256":"421d70d04731fd688df441a953c548adcf0b999ee28ad524f801bab02f0080a7","source":{"kind":"arxiv","id":"2606.29476","version":1},"attestation_state":"computed","paper":{"title":"CRAFT: Counterfactual Credit Assignment from Free Sibling Rollouts for Self-Distilled Agentic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kani Chen, Zibin Meng","submitted_at":"2026-06-28T16:11:47Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.29476","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-28T16:11:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"11c6cac05795cf8392f3b1588719906e2f5340d17a508ae2c5bf2e6e3bdf6b5d","abstract_canon_sha256":"954ca6c99d9d2557f6879222423e91bc239d36cfba366db0df30a0914b68c656"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:18:08.052081Z","signature_b64":"TP2OEaNsG0rpWXqFl1IDDP38ekY/yBoyqWtShWZEM/0e3XY8ZUwDN0iqkK/EFQaVK3AmcPc6ypMdizWqDQZUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"421d70d04731fd688df441a953c548adcf0b999ee28ad524f801bab02f0080a7","last_reissued_at":"2026-06-30T01:18:08.051419Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:18:08.051419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CRAFT: Counterfactual Credit Assignment from Free Sibling Rollouts for Self-Distilled Agentic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kani Chen, Zibin Meng","submitted_at":"2026-06-28T16:11:47Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29476","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/2606.29476/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.29476","created_at":"2026-06-30T01:18:08.051518+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29476v1","created_at":"2026-06-30T01:18:08.051518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29476","created_at":"2026-06-30T01:18:08.051518+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIOXBUCHGH6W","created_at":"2026-06-30T01:18:08.051518+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIOXBUCHGH6WRDPU","created_at":"2026-06-30T01:18:08.051518+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIOXBUCH","created_at":"2026-06-30T01:18:08.051518+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IIOXBUCHGH6WRDPUIGUVHRKIVX","json":"https://pith.science/pith/IIOXBUCHGH6WRDPUIGUVHRKIVX.json","graph_json":"https://pith.science/api/pith-number/IIOXBUCHGH6WRDPUIGUVHRKIVX/graph.json","events_json":"https://pith.science/api/pith-number/IIOXBUCHGH6WRDPUIGUVHRKIVX/events.json","paper":"https://pith.science/paper/IIOXBUCH"},"agent_actions":{"view_html":"https://pith.science/pith/IIOXBUCHGH6WRDPUIGUVHRKIVX","download_json":"https://pith.science/pith/IIOXBUCHGH6WRDPUIGUVHRKIVX.json","view_paper":"https://pith.science/paper/IIOXBUCH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29476&json=true","fetch_graph":"https://pith.science/api/pith-number/IIOXBUCHGH6WRDPUIGUVHRKIVX/graph.json","fetch_events":"https://pith.science/api/pith-number/IIOXBUCHGH6WRDPUIGUVHRKIVX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIOXBUCHGH6WRDPUIGUVHRKIVX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIOXBUCHGH6WRDPUIGUVHRKIVX/action/storage_attestation","attest_author":"https://pith.science/pith/IIOXBUCHGH6WRDPUIGUVHRKIVX/action/author_attestation","sign_citation":"https://pith.science/pith/IIOXBUCHGH6WRDPUIGUVHRKIVX/action/citation_signature","submit_replication":"https://pith.science/pith/IIOXBUCHGH6WRDPUIGUVHRKIVX/action/replication_record"}},"created_at":"2026-06-30T01:18:08.051518+00:00","updated_at":"2026-06-30T01:18:08.051518+00:00"}