{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D75O2IKGNKCKW5XHQADKDWGECG","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":"5b07e18d5a28c1f7f614e522654c4509ac3e4bb6d3b96e39108460bcec8c418e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-24T17:56:03Z","title_canon_sha256":"f04499cc2fe213d17289ceb65724354c5be0721b4721111a834e069342883c7e"},"schema_version":"1.0","source":{"id":"2511.19356","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.19356","created_at":"2026-07-17T01:21:44Z"},{"alias_kind":"arxiv_version","alias_value":"2511.19356v3","created_at":"2026-07-17T01:21:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.19356","created_at":"2026-07-17T01:21:44Z"},{"alias_kind":"pith_short_12","alias_value":"D75O2IKGNKCK","created_at":"2026-07-17T01:21:44Z"},{"alias_kind":"pith_short_16","alias_value":"D75O2IKGNKCKW5XH","created_at":"2026-07-17T01:21:44Z"},{"alias_kind":"pith_short_8","alias_value":"D75O2IKG","created_at":"2026-07-17T01:21:44Z"}],"graph_snapshots":[{"event_id":"sha256:0e0a91bc95c3021de4b008eaa9a46a448baf88cf151126beff0843f3a5a60be2","target":"graph","created_at":"2026-07-17T01:21:44Z","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/2511.19356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Group Relative Policy Optimization (GRPO) enables stable and preference-oriented updates via group-wise comparisons for post-training video generation. However, GRPO directly optimizes reward-induced advantages. Under sustained optimization, the reward score can lose fidelity as a proxy for true video quality, consistent with the phenomenon described by Goodhart's Law. This leads to two recurring issues: (i) shortcut-driven optimization under composite objectives and (ii) reward saturation within prompt groups. To address these issues, we introduce TaRoS, a Target-Robust Reward Signaling frame","authors_text":"Chi Zhang, Haibin Huang, Rui Li, Xuelong Li, Yuanzhi Liang, Ziqi Ni","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-24T17:56:03Z","title":"Rethinking Reward Signals in Video GRPO: When Scores Become Targets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.19356","kind":"arxiv","version":3},"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":"sha256:367018e03f8f60e9e67de6e574ee90c42f2f8bacce2e3b86b65f6892b2659cfe","target":"record","created_at":"2026-07-17T01:21:44Z","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":"5b07e18d5a28c1f7f614e522654c4509ac3e4bb6d3b96e39108460bcec8c418e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-24T17:56:03Z","title_canon_sha256":"f04499cc2fe213d17289ceb65724354c5be0721b4721111a834e069342883c7e"},"schema_version":"1.0","source":{"id":"2511.19356","kind":"arxiv","version":3}},"canonical_sha256":"1ffaed21466a84ab76e78006a1d8c411a3bebae8bc55f71293dd1b390651cdf7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ffaed21466a84ab76e78006a1d8c411a3bebae8bc55f71293dd1b390651cdf7","first_computed_at":"2026-07-17T01:21:44.510937Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T01:21:44.510937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EnXPCPxMqcd3aDTK+baH8Xa2X6nOctIEfxOQi0hQeaWUp4PArQn7V0cmQ+f+VN1WEUAEkwaIvKW20/xAPouWAQ==","signature_status":"signed_v1","signed_at":"2026-07-17T01:21:44.511860Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.19356","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:367018e03f8f60e9e67de6e574ee90c42f2f8bacce2e3b86b65f6892b2659cfe","sha256:0e0a91bc95c3021de4b008eaa9a46a448baf88cf151126beff0843f3a5a60be2"],"state_sha256":"2770cb72881df45376046ba804f32fabe5070a737b808749d9ac94192f0fb79b"}