{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2XUFY5JNOTBF6ZTGYFJIX5BU4N","short_pith_number":"pith:2XUFY5JN","schema_version":"1.0","canonical_sha256":"d5e85c752d74c25f6666c1528bf434e365084e184a079927cdfb72ef54633507","source":{"kind":"arxiv","id":"2608.01303","version":1},"attestation_state":"computed","paper":{"title":"AlphaG-OPD: Reliability-Gated Sibling Counterfactuals for On-Policy Distillation in Symbolic Alpha Factor Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Yaoyu Su","submitted_at":"2026-08-02T15:12:58Z","abstract_excerpt":"Symbolic alpha factor discovery can score a completed expression, but it provides no direct label for the structural decisions that produced it. Generative flow networks (GFlowNets) preserve a diverse, reward-proportional distribution over complete expressions, yet their trajectory-level objective does not compare unchosen sibling actions at an intermediate state. We introduce AlphaG-OPD, a structural on-policy distillation framework that turns terminal factor evaluations into local action guidance. Its design separates three decisions. Component I determines where to teach by exposing grammar"},"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":"2608.01303","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-02T15:12:58Z","cross_cats_sorted":[],"title_canon_sha256":"449ff0f4577838fc902c64d2cd0d1fb070dbd2223d7126914768c19feec86292","abstract_canon_sha256":"c13381d77c4702aa00587ce732999c165e76638d5f939b17abf73b77362cbe50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:03:30.745960Z","signature_b64":"RdkbkFDSDvHOeIrVUDmckKY69ltBtLydz518a5pNhwqb8mwA70suwLCy0fCM6XHhGdaYroTGtiAiEZZ6es9wBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5e85c752d74c25f6666c1528bf434e365084e184a079927cdfb72ef54633507","last_reissued_at":"2026-08-04T02:03:30.744104Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:03:30.744104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AlphaG-OPD: Reliability-Gated Sibling Counterfactuals for On-Policy Distillation in Symbolic Alpha Factor Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Yaoyu Su","submitted_at":"2026-08-02T15:12:58Z","abstract_excerpt":"Symbolic alpha factor discovery can score a completed expression, but it provides no direct label for the structural decisions that produced it. Generative flow networks (GFlowNets) preserve a diverse, reward-proportional distribution over complete expressions, yet their trajectory-level objective does not compare unchosen sibling actions at an intermediate state. We introduce AlphaG-OPD, a structural on-policy distillation framework that turns terminal factor evaluations into local action guidance. Its design separates three decisions. Component I determines where to teach by exposing grammar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01303","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/2608.01303/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":"2608.01303","created_at":"2026-08-04T02:03:30.745757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01303v1","created_at":"2026-08-04T02:03:30.745757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01303","created_at":"2026-08-04T02:03:30.745757+00:00"},{"alias_kind":"pith_short_12","alias_value":"2XUFY5JNOTBF","created_at":"2026-08-04T02:03:30.745757+00:00"},{"alias_kind":"pith_short_16","alias_value":"2XUFY5JNOTBF6ZTG","created_at":"2026-08-04T02:03:30.745757+00:00"},{"alias_kind":"pith_short_8","alias_value":"2XUFY5JN","created_at":"2026-08-04T02:03:30.745757+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/2XUFY5JNOTBF6ZTGYFJIX5BU4N","json":"https://pith.science/pith/2XUFY5JNOTBF6ZTGYFJIX5BU4N.json","graph_json":"https://pith.science/api/pith-number/2XUFY5JNOTBF6ZTGYFJIX5BU4N/graph.json","events_json":"https://pith.science/api/pith-number/2XUFY5JNOTBF6ZTGYFJIX5BU4N/events.json","paper":"https://pith.science/paper/2XUFY5JN"},"agent_actions":{"view_html":"https://pith.science/pith/2XUFY5JNOTBF6ZTGYFJIX5BU4N","download_json":"https://pith.science/pith/2XUFY5JNOTBF6ZTGYFJIX5BU4N.json","view_paper":"https://pith.science/paper/2XUFY5JN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01303&json=true","fetch_graph":"https://pith.science/api/pith-number/2XUFY5JNOTBF6ZTGYFJIX5BU4N/graph.json","fetch_events":"https://pith.science/api/pith-number/2XUFY5JNOTBF6ZTGYFJIX5BU4N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2XUFY5JNOTBF6ZTGYFJIX5BU4N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2XUFY5JNOTBF6ZTGYFJIX5BU4N/action/storage_attestation","attest_author":"https://pith.science/pith/2XUFY5JNOTBF6ZTGYFJIX5BU4N/action/author_attestation","sign_citation":"https://pith.science/pith/2XUFY5JNOTBF6ZTGYFJIX5BU4N/action/citation_signature","submit_replication":"https://pith.science/pith/2XUFY5JNOTBF6ZTGYFJIX5BU4N/action/replication_record"}},"created_at":"2026-08-04T02:03:30.745757+00:00","updated_at":"2026-08-04T02:03:30.745757+00:00"}