{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:D33CMHNP43PWCIXWRC6TIUO7AD","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":"3520390a71a608336616305619ca4e48bc165897ea2a1f76dd19c6c6d6dc4837","cross_cats_sorted":["cs.CV","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T05:30:40Z","title_canon_sha256":"88a1847c84ddc9bc19218371e6fa982c1640fb2e0bce7fb6ab6a3848cbe27a07"},"schema_version":"1.0","source":{"id":"2607.17572","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.17572","created_at":"2026-07-21T01:21:52Z"},{"alias_kind":"arxiv_version","alias_value":"2607.17572v1","created_at":"2026-07-21T01:21:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17572","created_at":"2026-07-21T01:21:52Z"},{"alias_kind":"pith_short_12","alias_value":"D33CMHNP43PW","created_at":"2026-07-21T01:21:52Z"},{"alias_kind":"pith_short_16","alias_value":"D33CMHNP43PWCIXW","created_at":"2026-07-21T01:21:52Z"},{"alias_kind":"pith_short_8","alias_value":"D33CMHNP","created_at":"2026-07-21T01:21:52Z"}],"graph_snapshots":[{"event_id":"sha256:2141c88223bb3a8b5f52771eea0017ec32b53c6e78648a06652d05bef78c91f9","target":"graph","created_at":"2026-07-21T01:21:52Z","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/2607.17572/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Group Relative Policy Optimization (GRPO) is a powerful reinforcement learning algorithm for aligning generative models with human preferences. While successful in large language models~\\cite{shao2024deepseekmathpushinglimitsmathematical}, its extension to diffusion and flow matching models introduces a severe computational bottleneck: gradients must be back-propagated through the high-capacity DiT backbone at \\emph{every} timestep of the sampling trajectory, making high-resolution text-to-image (T2I) training prohibitively expensive. Training-free DiT inference acceleration methods (e.g., $\\D","authors_text":"Chengru Song, He Kang, Jie Li, Ruiyi Ding, Yuan Chen, Ziyan Liu","cross_cats":["cs.CV","cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T05:30:40Z","title":"AGG: Jacobian-Aggregated Group Gradient for Efficient GRPO Training of Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17572","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":"sha256:919c8b3d2c83f88e9a7ffd026f28af07c3cf746c81f02d6f94c3c127c7faf827","target":"record","created_at":"2026-07-21T01:21:52Z","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":"3520390a71a608336616305619ca4e48bc165897ea2a1f76dd19c6c6d6dc4837","cross_cats_sorted":["cs.CV","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T05:30:40Z","title_canon_sha256":"88a1847c84ddc9bc19218371e6fa982c1640fb2e0bce7fb6ab6a3848cbe27a07"},"schema_version":"1.0","source":{"id":"2607.17572","kind":"arxiv","version":1}},"canonical_sha256":"1ef6261dafe6df6122f688bd3451df00d3e2bd12cf3af0fed2dc648e386f4bd1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ef6261dafe6df6122f688bd3451df00d3e2bd12cf3af0fed2dc648e386f4bd1","first_computed_at":"2026-07-21T01:21:52.968895Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T01:21:52.968895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8DvF8XcmxXroRASXBrTdTxuI5edtgBS7NAtvY45vRiGwloIrFNi7Z7hsROPeIHgKd6+Om4RjoUWar+SOKqYOAg==","signature_status":"signed_v1","signed_at":"2026-07-21T01:21:52.969755Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.17572","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:919c8b3d2c83f88e9a7ffd026f28af07c3cf746c81f02d6f94c3c127c7faf827","sha256:2141c88223bb3a8b5f52771eea0017ec32b53c6e78648a06652d05bef78c91f9"],"state_sha256":"b71e2e3d6671f5e06719775a8dd65466399179d57a1426d883f73f5a00b7f35f"}