{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GDHHNTTHXRGUWOL4CSKEUIU2PD","short_pith_number":"pith:GDHHNTTH","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"},"canonical_sha256":"30ce76ce67bc4d4b397c14944a229a78dd89e33f71a72f4c4b8c062ce83fc679","source":{"kind":"arxiv","id":"2608.07147","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.07147","created_at":"2026-08-10T01:13:31Z"},{"alias_kind":"arxiv_version","alias_value":"2608.07147v1","created_at":"2026-08-10T01:13:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07147","created_at":"2026-08-10T01:13:31Z"},{"alias_kind":"pith_short_12","alias_value":"GDHHNTTHXRGU","created_at":"2026-08-10T01:13:31Z"},{"alias_kind":"pith_short_16","alias_value":"GDHHNTTHXRGUWOL4","created_at":"2026-08-10T01:13:31Z"},{"alias_kind":"pith_short_8","alias_value":"GDHHNTTH","created_at":"2026-08-10T01:13:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GDHHNTTHXRGUWOL4CSKEUIU2PD","target":"record","payload":{"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"},"canonical_sha256":"30ce76ce67bc4d4b397c14944a229a78dd89e33f71a72f4c4b8c062ce83fc679","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"},"source_kind":"arxiv","source_id":"2608.07147","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-10T01:13:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rFIdhngtRi5MCHA62vfovq0oGZwV+Gx1xBjRhchrrZeTG59sDfBGYSBZjU2NVTF6CVAkUykH5Zr8cqJw0O+7Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T03:31:16.256257Z"},"content_sha256":"7c41686299edb5eac7cef208f2c32a226c51533b631b155d365579ed701b9344","schema_version":"1.0","event_id":"sha256:7c41686299edb5eac7cef208f2c32a226c51533b631b155d365579ed701b9344"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GDHHNTTHXRGUWOL4CSKEUIU2PD","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-10T01:13:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XtFZ1c8ys8zyOfyCe9Fki/jzD+J7bRn5O5JYI4nNTWKhf1MHCbypn5w1mWFBoDKc2/6KbKEnR/wIywQjrUNjAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T03:31:16.258113Z"},"content_sha256":"99186be99c1c850ec5cca6567efc71474c5e264c6b91afe44da55c1b2cbebb84","schema_version":"1.0","event_id":"sha256:99186be99c1c850ec5cca6567efc71474c5e264c6b91afe44da55c1b2cbebb84"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GDHHNTTHXRGUWOL4CSKEUIU2PD/bundle.json","state_url":"https://pith.science/pith/GDHHNTTHXRGUWOL4CSKEUIU2PD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GDHHNTTHXRGUWOL4CSKEUIU2PD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-15T03:31:16Z","links":{"resolver":"https://pith.science/pith/GDHHNTTHXRGUWOL4CSKEUIU2PD","bundle":"https://pith.science/pith/GDHHNTTHXRGUWOL4CSKEUIU2PD/bundle.json","state":"https://pith.science/pith/GDHHNTTHXRGUWOL4CSKEUIU2PD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GDHHNTTHXRGUWOL4CSKEUIU2PD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GDHHNTTHXRGUWOL4CSKEUIU2PD","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":"8c1e89ea2f4092cd715a4047a4376e7772152139d0e5da65715f89541ed24475","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-07T12:07:12Z","title_canon_sha256":"f6b42280574d67e894dd4544483aaccbc9af332c91ddd5554f53ac31774e36a3"},"schema_version":"1.0","source":{"id":"2608.07147","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.07147","created_at":"2026-08-10T01:13:31Z"},{"alias_kind":"arxiv_version","alias_value":"2608.07147v1","created_at":"2026-08-10T01:13:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07147","created_at":"2026-08-10T01:13:31Z"},{"alias_kind":"pith_short_12","alias_value":"GDHHNTTHXRGU","created_at":"2026-08-10T01:13:31Z"},{"alias_kind":"pith_short_16","alias_value":"GDHHNTTHXRGUWOL4","created_at":"2026-08-10T01:13:31Z"},{"alias_kind":"pith_short_8","alias_value":"GDHHNTTH","created_at":"2026-08-10T01:13:31Z"}],"graph_snapshots":[{"event_id":"sha256:99186be99c1c850ec5cca6567efc71474c5e264c6b91afe44da55c1b2cbebb84","target":"graph","created_at":"2026-08-10T01:13:31Z","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/2608.07147/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Di Wu, Liheng Yu, Pengkun Wang, Xiaofeng Cao, Xucong Wang, Zhe Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-07T12:07:12Z","title":"DiDPO: Diff-in-Diff Policy Optimization for Coding Agent Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07147","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":"sha256:7c41686299edb5eac7cef208f2c32a226c51533b631b155d365579ed701b9344","target":"record","created_at":"2026-08-10T01:13:31Z","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":"8c1e89ea2f4092cd715a4047a4376e7772152139d0e5da65715f89541ed24475","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-07T12:07:12Z","title_canon_sha256":"f6b42280574d67e894dd4544483aaccbc9af332c91ddd5554f53ac31774e36a3"},"schema_version":"1.0","source":{"id":"2608.07147","kind":"arxiv","version":1}},"canonical_sha256":"30ce76ce67bc4d4b397c14944a229a78dd89e33f71a72f4c4b8c062ce83fc679","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30ce76ce67bc4d4b397c14944a229a78dd89e33f71a72f4c4b8c062ce83fc679","first_computed_at":"2026-08-10T01:13:31.696383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-10T01:13:31.696383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j5Z+Dj1/mssYwNTsIlYgTOokc8Y/IjJVMQCyyAxCyZWF0v6SawjP358lMznoN+P+AU++/Uig2fcsQRsYLkWlBw==","signature_status":"signed_v1","signed_at":"2026-08-10T01:13:31.698805Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.07147","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c41686299edb5eac7cef208f2c32a226c51533b631b155d365579ed701b9344","sha256:99186be99c1c850ec5cca6567efc71474c5e264c6b91afe44da55c1b2cbebb84"],"state_sha256":"ce509e9e2c018526f2e6cf59f12b3278941c6ba770a4f761a32173c4cedbb56c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lc51f9CsYODfknpWzo76qAaY+Gqz2LCDDKZ12JWd9Cwxo1xTQ67DDw3uaHymlIwjmLNsVW1pEG2tJlBeb4TVBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T03:31:16.268205Z","bundle_sha256":"55055e52fcce68779793a5016c98a7724639623c87c8b8b3a3b5b39f9862fd86"}}