{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:R3DOCPPMSIZHUHGBWMVW6CKOVS","short_pith_number":"pith:R3DOCPPM","schema_version":"1.0","canonical_sha256":"8ec6e13dec92327a1cc1b32b6f094eaca57b06dc1a6093d0fe8d25d9f861a226","source":{"kind":"arxiv","id":"2606.11838","version":1},"attestation_state":"computed","paper":{"title":"Plan-and-Verify Video Reward Reasoning with Spatio-Temporal Scene Graph Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hyomin Kim, Joanie Hayoun Chung, Junghye Kim, Kyungjae Lee, Sungbin Lim, Sungwoong Kim, Yoonjin Oh","submitted_at":"2026-06-10T09:18:14Z","abstract_excerpt":"Reward models for text-to-video (T2V) generation guide post-training but often fail at fine-grained semantic alignment. We trace this to two structural weaknesses in existing reasoning-based reward models: they do not systematically verify every condition described in the prompt, and the visual evidence supporting each judgment remains implicit in their free-form reasoning. We propose SG-PVR, a video reward model that addresses these limitations through plan-and-verify reasoning grounded in spatio-temporal scene graphs. The verification plan decomposes the prompt into atomic claims, ensuring e"},"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":"2606.11838","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T09:18:14Z","cross_cats_sorted":[],"title_canon_sha256":"cea37d5bdd6403aeeec8685670b35d88b23b7f367a4ad88387a91f66ca309588","abstract_canon_sha256":"241cf0625382047274e3afa06b14b2cab899de907e48de8a240980ed15aecdfe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:11.029446Z","signature_b64":"JV3pO99hCtPBQKP9391PJD/9Ptme6HYb0YzyA2ORiVUZVpj0/1KNVYaeiMaS9wp2DmcAgLLfYErsMv6Y22+/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ec6e13dec92327a1cc1b32b6f094eaca57b06dc1a6093d0fe8d25d9f861a226","last_reissued_at":"2026-06-11T01:10:11.028598Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:11.028598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Plan-and-Verify Video Reward Reasoning with Spatio-Temporal Scene Graph Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hyomin Kim, Joanie Hayoun Chung, Junghye Kim, Kyungjae Lee, Sungbin Lim, Sungwoong Kim, Yoonjin Oh","submitted_at":"2026-06-10T09:18:14Z","abstract_excerpt":"Reward models for text-to-video (T2V) generation guide post-training but often fail at fine-grained semantic alignment. We trace this to two structural weaknesses in existing reasoning-based reward models: they do not systematically verify every condition described in the prompt, and the visual evidence supporting each judgment remains implicit in their free-form reasoning. We propose SG-PVR, a video reward model that addresses these limitations through plan-and-verify reasoning grounded in spatio-temporal scene graphs. The verification plan decomposes the prompt into atomic claims, ensuring e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11838","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/2606.11838/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":"2606.11838","created_at":"2026-06-11T01:10:11.028736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11838v1","created_at":"2026-06-11T01:10:11.028736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11838","created_at":"2026-06-11T01:10:11.028736+00:00"},{"alias_kind":"pith_short_12","alias_value":"R3DOCPPMSIZH","created_at":"2026-06-11T01:10:11.028736+00:00"},{"alias_kind":"pith_short_16","alias_value":"R3DOCPPMSIZHUHGB","created_at":"2026-06-11T01:10:11.028736+00:00"},{"alias_kind":"pith_short_8","alias_value":"R3DOCPPM","created_at":"2026-06-11T01:10:11.028736+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/R3DOCPPMSIZHUHGBWMVW6CKOVS","json":"https://pith.science/pith/R3DOCPPMSIZHUHGBWMVW6CKOVS.json","graph_json":"https://pith.science/api/pith-number/R3DOCPPMSIZHUHGBWMVW6CKOVS/graph.json","events_json":"https://pith.science/api/pith-number/R3DOCPPMSIZHUHGBWMVW6CKOVS/events.json","paper":"https://pith.science/paper/R3DOCPPM"},"agent_actions":{"view_html":"https://pith.science/pith/R3DOCPPMSIZHUHGBWMVW6CKOVS","download_json":"https://pith.science/pith/R3DOCPPMSIZHUHGBWMVW6CKOVS.json","view_paper":"https://pith.science/paper/R3DOCPPM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11838&json=true","fetch_graph":"https://pith.science/api/pith-number/R3DOCPPMSIZHUHGBWMVW6CKOVS/graph.json","fetch_events":"https://pith.science/api/pith-number/R3DOCPPMSIZHUHGBWMVW6CKOVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R3DOCPPMSIZHUHGBWMVW6CKOVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R3DOCPPMSIZHUHGBWMVW6CKOVS/action/storage_attestation","attest_author":"https://pith.science/pith/R3DOCPPMSIZHUHGBWMVW6CKOVS/action/author_attestation","sign_citation":"https://pith.science/pith/R3DOCPPMSIZHUHGBWMVW6CKOVS/action/citation_signature","submit_replication":"https://pith.science/pith/R3DOCPPMSIZHUHGBWMVW6CKOVS/action/replication_record"}},"created_at":"2026-06-11T01:10:11.028736+00:00","updated_at":"2026-06-11T01:10:11.028736+00:00"}