{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YXCNXVAI3HBTGIOSQ2QYOWC5PF","short_pith_number":"pith:YXCNXVAI","schema_version":"1.0","canonical_sha256":"c5c4dbd408d9c33321d286a187585d7961dc54a5b460d56f91473be5deeae372","source":{"kind":"arxiv","id":"2605.15951","version":1},"attestation_state":"computed","paper":{"title":"From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anjie Le, Can Peng, Fengbei Liu, Jiajun Deng, Jiayuan Zhu, Jiazhen Pan, Junde Wu, Yiping Ji, Yuyuan Liu","submitted_at":"2026-05-15T13:41:41Z","abstract_excerpt":"Finetuning Large Vision-Language Models with reinforcement learning has emerged as a promising approach to enhance their capability in object-level grounding. However, existing methods, mainly based on GRPO, assign rewards at the response level. Such sparse reward, often criterion-induced, leads to minimal learning signals when all candidate responses fail in challenging scenarios. In this work, we propose a group-revision optimisation paradigm that enhances learning on hard cases. It begins with a sampled initial response and generates a set of revised candidates to explore improved grounding"},"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":"2605.15951","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T13:41:41Z","cross_cats_sorted":[],"title_canon_sha256":"7492bd5e7fced7df61e49125f5b496213d3c4972afe5a24529f0bb23faacbe1c","abstract_canon_sha256":"4b62ce5656dda1202a8f3ac1039d51dc07535ceb0643bb9a5d33be8914c4e138"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:46.363127Z","signature_b64":"o/ARvKDrCa5zrYu7l47HaYI3R462C6yiuQ6u6OZryY8xQ16Mv5UZ0ocRg8UMKL9TgboNnmmjoYvFzTWJnuCrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5c4dbd408d9c33321d286a187585d7961dc54a5b460d56f91473be5deeae372","last_reissued_at":"2026-05-20T00:01:46.362599Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:46.362599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anjie Le, Can Peng, Fengbei Liu, Jiajun Deng, Jiayuan Zhu, Jiazhen Pan, Junde Wu, Yiping Ji, Yuyuan Liu","submitted_at":"2026-05-15T13:41:41Z","abstract_excerpt":"Finetuning Large Vision-Language Models with reinforcement learning has emerged as a promising approach to enhance their capability in object-level grounding. However, existing methods, mainly based on GRPO, assign rewards at the response level. Such sparse reward, often criterion-induced, leads to minimal learning signals when all candidate responses fail in challenging scenarios. In this work, we propose a group-revision optimisation paradigm that enhances learning on hard cases. It begins with a sampled initial response and generates a set of revised candidates to explore improved grounding"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15951","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/2605.15951/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:44.880901Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:01:55.713491Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"3b0782faac250be0b2ef5d856eba0687f6288359726966820024c091e9ad22a1"},"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":"2605.15951","created_at":"2026-05-20T00:01:46.362676+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15951v1","created_at":"2026-05-20T00:01:46.362676+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15951","created_at":"2026-05-20T00:01:46.362676+00:00"},{"alias_kind":"pith_short_12","alias_value":"YXCNXVAI3HBT","created_at":"2026-05-20T00:01:46.362676+00:00"},{"alias_kind":"pith_short_16","alias_value":"YXCNXVAI3HBTGIOS","created_at":"2026-05-20T00:01:46.362676+00:00"},{"alias_kind":"pith_short_8","alias_value":"YXCNXVAI","created_at":"2026-05-20T00:01:46.362676+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/YXCNXVAI3HBTGIOSQ2QYOWC5PF","json":"https://pith.science/pith/YXCNXVAI3HBTGIOSQ2QYOWC5PF.json","graph_json":"https://pith.science/api/pith-number/YXCNXVAI3HBTGIOSQ2QYOWC5PF/graph.json","events_json":"https://pith.science/api/pith-number/YXCNXVAI3HBTGIOSQ2QYOWC5PF/events.json","paper":"https://pith.science/paper/YXCNXVAI"},"agent_actions":{"view_html":"https://pith.science/pith/YXCNXVAI3HBTGIOSQ2QYOWC5PF","download_json":"https://pith.science/pith/YXCNXVAI3HBTGIOSQ2QYOWC5PF.json","view_paper":"https://pith.science/paper/YXCNXVAI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15951&json=true","fetch_graph":"https://pith.science/api/pith-number/YXCNXVAI3HBTGIOSQ2QYOWC5PF/graph.json","fetch_events":"https://pith.science/api/pith-number/YXCNXVAI3HBTGIOSQ2QYOWC5PF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YXCNXVAI3HBTGIOSQ2QYOWC5PF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YXCNXVAI3HBTGIOSQ2QYOWC5PF/action/storage_attestation","attest_author":"https://pith.science/pith/YXCNXVAI3HBTGIOSQ2QYOWC5PF/action/author_attestation","sign_citation":"https://pith.science/pith/YXCNXVAI3HBTGIOSQ2QYOWC5PF/action/citation_signature","submit_replication":"https://pith.science/pith/YXCNXVAI3HBTGIOSQ2QYOWC5PF/action/replication_record"}},"created_at":"2026-05-20T00:01:46.362676+00:00","updated_at":"2026-05-20T00:01:46.362676+00:00"}