{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KDUTNEVMEVKMJHB6CFJF3Q36LB","short_pith_number":"pith:KDUTNEVM","schema_version":"1.0","canonical_sha256":"50e93692ac2554c49c3e11525dc37e58402c9f08a8c856d0ff4255fbf465e489","source":{"kind":"arxiv","id":"2608.00584","version":1},"attestation_state":"computed","paper":{"title":"Element-Aware Group Learning for E-Commerce Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiahui Wang, Jingtong Chen, Minghao Li, Shaoguo Liu, Xue Zhao","submitted_at":"2026-08-01T10:45:03Z","abstract_excerpt":"Recent advances in image generation and editing have made prompt quality a key bottleneck for e-commerce creatives. Vision-language models (VLMs) can generate image-editing prompts from product images and metadata, but further improving their prompt-writing capabilities requires post-training with feedback from the generated images. Group Relative Policy Optimization (GRPO) is a natural framework for such outcome-level reward optimization. However, it assigns credit only at the full-prompt level, even though image quality often depends on specific design elements such as composition, backgroun"},"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":"2608.00584","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-01T10:45:03Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6a5d7e46f323f8817c53dbc9063d74f4a5917a07ea1bd1c0e1c3449706c289c2","abstract_canon_sha256":"fbaae616cf4c868a3c1c72587244c61da77f07474a59b1b2b9e86b224c9bb9e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:37:37.122588Z","signature_b64":"+BSyQtw5Jvv9pU0E7O3AiDSli36NcHGKUyazgtvSoWtaUq5IKRvzUdsTtGZ71+oSrNBtTOPecVS6dZM4LTe3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50e93692ac2554c49c3e11525dc37e58402c9f08a8c856d0ff4255fbf465e489","last_reissued_at":"2026-08-04T00:37:37.121147Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:37:37.121147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Element-Aware Group Learning for E-Commerce Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiahui Wang, Jingtong Chen, Minghao Li, Shaoguo Liu, Xue Zhao","submitted_at":"2026-08-01T10:45:03Z","abstract_excerpt":"Recent advances in image generation and editing have made prompt quality a key bottleneck for e-commerce creatives. Vision-language models (VLMs) can generate image-editing prompts from product images and metadata, but further improving their prompt-writing capabilities requires post-training with feedback from the generated images. Group Relative Policy Optimization (GRPO) is a natural framework for such outcome-level reward optimization. However, it assigns credit only at the full-prompt level, even though image quality often depends on specific design elements such as composition, backgroun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00584","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/2608.00584/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":"2608.00584","created_at":"2026-08-04T00:37:37.122330+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00584v1","created_at":"2026-08-04T00:37:37.122330+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00584","created_at":"2026-08-04T00:37:37.122330+00:00"},{"alias_kind":"pith_short_12","alias_value":"KDUTNEVMEVKM","created_at":"2026-08-04T00:37:37.122330+00:00"},{"alias_kind":"pith_short_16","alias_value":"KDUTNEVMEVKMJHB6","created_at":"2026-08-04T00:37:37.122330+00:00"},{"alias_kind":"pith_short_8","alias_value":"KDUTNEVM","created_at":"2026-08-04T00:37:37.122330+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/KDUTNEVMEVKMJHB6CFJF3Q36LB","json":"https://pith.science/pith/KDUTNEVMEVKMJHB6CFJF3Q36LB.json","graph_json":"https://pith.science/api/pith-number/KDUTNEVMEVKMJHB6CFJF3Q36LB/graph.json","events_json":"https://pith.science/api/pith-number/KDUTNEVMEVKMJHB6CFJF3Q36LB/events.json","paper":"https://pith.science/paper/KDUTNEVM"},"agent_actions":{"view_html":"https://pith.science/pith/KDUTNEVMEVKMJHB6CFJF3Q36LB","download_json":"https://pith.science/pith/KDUTNEVMEVKMJHB6CFJF3Q36LB.json","view_paper":"https://pith.science/paper/KDUTNEVM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00584&json=true","fetch_graph":"https://pith.science/api/pith-number/KDUTNEVMEVKMJHB6CFJF3Q36LB/graph.json","fetch_events":"https://pith.science/api/pith-number/KDUTNEVMEVKMJHB6CFJF3Q36LB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KDUTNEVMEVKMJHB6CFJF3Q36LB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KDUTNEVMEVKMJHB6CFJF3Q36LB/action/storage_attestation","attest_author":"https://pith.science/pith/KDUTNEVMEVKMJHB6CFJF3Q36LB/action/author_attestation","sign_citation":"https://pith.science/pith/KDUTNEVMEVKMJHB6CFJF3Q36LB/action/citation_signature","submit_replication":"https://pith.science/pith/KDUTNEVMEVKMJHB6CFJF3Q36LB/action/replication_record"}},"created_at":"2026-08-04T00:37:37.122330+00:00","updated_at":"2026-08-04T00:37:37.122330+00:00"}