{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DHYJO2YMROG6OHWU5KOBW4BB6E","short_pith_number":"pith:DHYJO2YM","schema_version":"1.0","canonical_sha256":"19f0976b0c8b8de71ed4ea9c1b7021f108ffc419ecb73c71c5100f7010d819ef","source":{"kind":"arxiv","id":"2607.13033","version":1},"attestation_state":"computed","paper":{"title":"DenseReward: Dense Reward Learning via Failure Synthesis for Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Daniel Szafir, Huaxiu Yao, Jiaqi Liu, Li Erran Li, Mingxiao Huo, Mingyu Ding, Wanxi Dong, Yao Mu, Yue Yang, Yu Fang","submitted_at":"2026-07-14T17:59:29Z","abstract_excerpt":"Reinforcement learning holds great promise for improving robot policies beyond the limits of imitation learning. However, its practical adoption remains bottlenecked by the lack of reliable vision-language reward models that provide dense and informative feedback. Two key challenges remain: acquiring diverse failure data at scale and obtaining fine-grained reward signals beyond sparse trajectory-level success labels. Collecting failure trajectories typically requires laborious human effort, while pseudo-failures constructed by relabeling successful demonstrations fail to capture the diverse ph"},"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":"2607.13033","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-14T17:59:29Z","cross_cats_sorted":[],"title_canon_sha256":"8ea7396974908c6e481ffefafa03b93d2ee43db3161d734bb19541b01ec41f24","abstract_canon_sha256":"55ef7d30a9ebcb9a6f81f983bf8eb9538dc7dd701c0f3bf5273a805e0d89c20e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-15T01:22:32.648644Z","signature_b64":"eFsNO1K0Jdq166YPspmaqx8olydvmVx/MX+5DnM3fq6RXO9hD57A4UrfahumYZ9FFj6F8UL63WshdWoykijrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19f0976b0c8b8de71ed4ea9c1b7021f108ffc419ecb73c71c5100f7010d819ef","last_reissued_at":"2026-07-15T01:22:32.647789Z","signature_status":"signed_v1","first_computed_at":"2026-07-15T01:22:32.647789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DenseReward: Dense Reward Learning via Failure Synthesis for Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Daniel Szafir, Huaxiu Yao, Jiaqi Liu, Li Erran Li, Mingxiao Huo, Mingyu Ding, Wanxi Dong, Yao Mu, Yue Yang, Yu Fang","submitted_at":"2026-07-14T17:59:29Z","abstract_excerpt":"Reinforcement learning holds great promise for improving robot policies beyond the limits of imitation learning. However, its practical adoption remains bottlenecked by the lack of reliable vision-language reward models that provide dense and informative feedback. Two key challenges remain: acquiring diverse failure data at scale and obtaining fine-grained reward signals beyond sparse trajectory-level success labels. Collecting failure trajectories typically requires laborious human effort, while pseudo-failures constructed by relabeling successful demonstrations fail to capture the diverse ph"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13033","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/2607.13033/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":"2607.13033","created_at":"2026-07-15T01:22:32.648219+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.13033v1","created_at":"2026-07-15T01:22:32.648219+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13033","created_at":"2026-07-15T01:22:32.648219+00:00"},{"alias_kind":"pith_short_12","alias_value":"DHYJO2YMROG6","created_at":"2026-07-15T01:22:32.648219+00:00"},{"alias_kind":"pith_short_16","alias_value":"DHYJO2YMROG6OHWU","created_at":"2026-07-15T01:22:32.648219+00:00"},{"alias_kind":"pith_short_8","alias_value":"DHYJO2YM","created_at":"2026-07-15T01:22:32.648219+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/DHYJO2YMROG6OHWU5KOBW4BB6E","json":"https://pith.science/pith/DHYJO2YMROG6OHWU5KOBW4BB6E.json","graph_json":"https://pith.science/api/pith-number/DHYJO2YMROG6OHWU5KOBW4BB6E/graph.json","events_json":"https://pith.science/api/pith-number/DHYJO2YMROG6OHWU5KOBW4BB6E/events.json","paper":"https://pith.science/paper/DHYJO2YM"},"agent_actions":{"view_html":"https://pith.science/pith/DHYJO2YMROG6OHWU5KOBW4BB6E","download_json":"https://pith.science/pith/DHYJO2YMROG6OHWU5KOBW4BB6E.json","view_paper":"https://pith.science/paper/DHYJO2YM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.13033&json=true","fetch_graph":"https://pith.science/api/pith-number/DHYJO2YMROG6OHWU5KOBW4BB6E/graph.json","fetch_events":"https://pith.science/api/pith-number/DHYJO2YMROG6OHWU5KOBW4BB6E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DHYJO2YMROG6OHWU5KOBW4BB6E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DHYJO2YMROG6OHWU5KOBW4BB6E/action/storage_attestation","attest_author":"https://pith.science/pith/DHYJO2YMROG6OHWU5KOBW4BB6E/action/author_attestation","sign_citation":"https://pith.science/pith/DHYJO2YMROG6OHWU5KOBW4BB6E/action/citation_signature","submit_replication":"https://pith.science/pith/DHYJO2YMROG6OHWU5KOBW4BB6E/action/replication_record"}},"created_at":"2026-07-15T01:22:32.648219+00:00","updated_at":"2026-07-15T01:22:32.648219+00:00"}