{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GDHHNTTHXRGUWOL4CSKEUIU2PD","short_pith_number":"pith:GDHHNTTH","schema_version":"1.0","canonical_sha256":"30ce76ce67bc4d4b397c14944a229a78dd89e33f71a72f4c4b8c062ce83fc679","source":{"kind":"arxiv","id":"2608.07147","version":1},"attestation_state":"computed","paper":{"title":"DiDPO: Diff-in-Diff Policy Optimization for Coding Agent Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Di Wu, Liheng Yu, Pengkun Wang, Xiaofeng Cao, Xucong Wang, Zhe Zhao","submitted_at":"2026-08-07T12:07:12Z","abstract_excerpt":"Reinforcement learning with Verifiable Reward (RLVR) has emerged as a powerful paradigm for training coding agents, where the execution feedback from compilation and tests provides objective verification. However, unlike agent tasks, coding agents face a unique and finer-grained credit assignment challenge: at each step, coding actions simultaneously pack varying changes into different regions of a code version, which makes the contribution of independent change indistinguishable. Existing RLVR methods mostly leverage the outcome reward or step-level reward, which fails to dive into a code dif"},"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":"2608.07147","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-07T12:07:12Z","cross_cats_sorted":[],"title_canon_sha256":"f6b42280574d67e894dd4544483aaccbc9af332c91ddd5554f53ac31774e36a3","abstract_canon_sha256":"8c1e89ea2f4092cd715a4047a4376e7772152139d0e5da65715f89541ed24475"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:13:31.698805Z","signature_b64":"j5Z+Dj1/mssYwNTsIlYgTOokc8Y/IjJVMQCyyAxCyZWF0v6SawjP358lMznoN+P+AU++/Uig2fcsQRsYLkWlBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30ce76ce67bc4d4b397c14944a229a78dd89e33f71a72f4c4b8c062ce83fc679","last_reissued_at":"2026-08-10T01:13:31.696383Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:13:31.696383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiDPO: Diff-in-Diff Policy Optimization for Coding Agent Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Di Wu, Liheng Yu, Pengkun Wang, Xiaofeng Cao, Xucong Wang, Zhe Zhao","submitted_at":"2026-08-07T12:07:12Z","abstract_excerpt":"Reinforcement learning with Verifiable Reward (RLVR) has emerged as a powerful paradigm for training coding agents, where the execution feedback from compilation and tests provides objective verification. However, unlike agent tasks, coding agents face a unique and finer-grained credit assignment challenge: at each step, coding actions simultaneously pack varying changes into different regions of a code version, which makes the contribution of independent change indistinguishable. Existing RLVR methods mostly leverage the outcome reward or step-level reward, which fails to dive into a code dif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07147","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/2608.07147/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":"2608.07147","created_at":"2026-08-10T01:13:31.697329+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.07147v1","created_at":"2026-08-10T01:13:31.697329+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07147","created_at":"2026-08-10T01:13:31.697329+00:00"},{"alias_kind":"pith_short_12","alias_value":"GDHHNTTHXRGU","created_at":"2026-08-10T01:13:31.697329+00:00"},{"alias_kind":"pith_short_16","alias_value":"GDHHNTTHXRGUWOL4","created_at":"2026-08-10T01:13:31.697329+00:00"},{"alias_kind":"pith_short_8","alias_value":"GDHHNTTH","created_at":"2026-08-10T01:13:31.697329+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/GDHHNTTHXRGUWOL4CSKEUIU2PD","json":"https://pith.science/pith/GDHHNTTHXRGUWOL4CSKEUIU2PD.json","graph_json":"https://pith.science/api/pith-number/GDHHNTTHXRGUWOL4CSKEUIU2PD/graph.json","events_json":"https://pith.science/api/pith-number/GDHHNTTHXRGUWOL4CSKEUIU2PD/events.json","paper":"https://pith.science/paper/GDHHNTTH"},"agent_actions":{"view_html":"https://pith.science/pith/GDHHNTTHXRGUWOL4CSKEUIU2PD","download_json":"https://pith.science/pith/GDHHNTTHXRGUWOL4CSKEUIU2PD.json","view_paper":"https://pith.science/paper/GDHHNTTH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.07147&json=true","fetch_graph":"https://pith.science/api/pith-number/GDHHNTTHXRGUWOL4CSKEUIU2PD/graph.json","fetch_events":"https://pith.science/api/pith-number/GDHHNTTHXRGUWOL4CSKEUIU2PD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GDHHNTTHXRGUWOL4CSKEUIU2PD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GDHHNTTHXRGUWOL4CSKEUIU2PD/action/storage_attestation","attest_author":"https://pith.science/pith/GDHHNTTHXRGUWOL4CSKEUIU2PD/action/author_attestation","sign_citation":"https://pith.science/pith/GDHHNTTHXRGUWOL4CSKEUIU2PD/action/citation_signature","submit_replication":"https://pith.science/pith/GDHHNTTHXRGUWOL4CSKEUIU2PD/action/replication_record"}},"created_at":"2026-08-10T01:13:31.697329+00:00","updated_at":"2026-08-10T01:13:31.697329+00:00"}