{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:U4OWUOB73OG6PYPAOZZJZ7QHD3","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":"36b073b4f41ab8cab6d2bb6d0daac8658756d44259fd59163e4dd9b91a9048b2","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-25T23:17:37Z","title_canon_sha256":"33a3be9329d7bdca8fe0c8318e88d207f9f41ff374e50b4ea34706df0e92d725"},"schema_version":"1.0","source":{"id":"2605.26385","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26385","created_at":"2026-05-27T01:05:15Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26385v1","created_at":"2026-05-27T01:05:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26385","created_at":"2026-05-27T01:05:15Z"},{"alias_kind":"pith_short_12","alias_value":"U4OWUOB73OG6","created_at":"2026-05-27T01:05:15Z"},{"alias_kind":"pith_short_16","alias_value":"U4OWUOB73OG6PYPA","created_at":"2026-05-27T01:05:15Z"},{"alias_kind":"pith_short_8","alias_value":"U4OWUOB7","created_at":"2026-05-27T01:05:15Z"}],"graph_snapshots":[{"event_id":"sha256:6331c9c53c70f00fe53fecbba13503cf9a8da7d2dc95e4a8e42a79727870298d","target":"graph","created_at":"2026-05-27T01:05:15Z","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/2605.26385/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale search, recommendation, and retrieval-augmented generation (RAG) systems typically employ a two-stage architecture: an early-stage ranker (ESR) generates a candidate set, which is subsequently re-ranked by a late-stage ranker (LSR). While there are many reinforcement learning (RL) methods for training the LSR, end-to-end training of the ESR has proven challenging. In particular, naive application of \"vanilla\" policy gradient (V-PG) is not scalable for candidate-set sizes relevant for practical use due to exploding variance. This issue arises because V-PG propagates the gradient to ","authors_text":"Ana-Roxana Pop, Ariel Evnine, Haruka Kiyohara, Israel Nir, Mihaela Curmei, Nitzan Razin, Sarah Dean, Shankar Kalyanaraman, Thorsten Joachims, Udi Weinsberg","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-25T23:17:37Z","title":"Credit-assigned Policy Gradient for Early Stage Retrieval in Two-stage Ranking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26385","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":"sha256:118efe8fd4ca886c92c1f657e0bd69b37742c8f67ba46c302fcfa7e22f0b31f5","target":"record","created_at":"2026-05-27T01:05:15Z","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":"36b073b4f41ab8cab6d2bb6d0daac8658756d44259fd59163e4dd9b91a9048b2","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-25T23:17:37Z","title_canon_sha256":"33a3be9329d7bdca8fe0c8318e88d207f9f41ff374e50b4ea34706df0e92d725"},"schema_version":"1.0","source":{"id":"2605.26385","kind":"arxiv","version":1}},"canonical_sha256":"a71d6a383fdb8de7e1e076729cfe071eff41e61b1d0ea079170403cf1f798677","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a71d6a383fdb8de7e1e076729cfe071eff41e61b1d0ea079170403cf1f798677","first_computed_at":"2026-05-27T01:05:15.397023Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:15.397023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CSjqDmbiryapVjbE3UurqaEmLDU9hEMidUOhYFVfkuI1BSxKTDAetEZb2L2sCuMPA2jqyk0fTnMgSdLxfJJhCg==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:15.397817Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26385","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:118efe8fd4ca886c92c1f657e0bd69b37742c8f67ba46c302fcfa7e22f0b31f5","sha256:6331c9c53c70f00fe53fecbba13503cf9a8da7d2dc95e4a8e42a79727870298d"],"state_sha256":"0fb27ce7366748a11b32e21cd4930b6ee165d9c83636d1b2109354cf434ae975"}