{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DD35A4VXP3LHLLJCX7CR2OQPLV","short_pith_number":"pith:DD35A4VX","schema_version":"1.0","canonical_sha256":"18f7d072b77ed675ad22bfc51d3a0f5d4453365a86c425e95a5d1e85f1f59b3f","source":{"kind":"arxiv","id":"2607.21655","version":1},"attestation_state":"computed","paper":{"title":"Progress Reward Modeling for Robotic Learning: A Comprehensive Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.RO","authors_text":"Anbang Liu, Ce Zhang, Chengxuan Qian, Guo Ye, Han Liu, Haoran Lu, Jianshu Zhang, Keliang Wu, Weijie Yin, Xiyuan Yang, Zhenyu Pan","submitted_at":"2026-07-22T19:29:52Z","abstract_excerpt":"Robotic learning takes place in dynamic environments with large behavior spaces. A terminal success signal only tells the robot whether the task is completed. It does not explain whether the current behavior is making progress, remaining unchanged, or undoing earlier progress. For this reason, recent studies have increasingly explored progress rewards that provide feedback during task execution. However, the current literature lacks a shared framework. Existing methods use different observations, goal specifications, output signals, supervision sources, and evaluation protocols. This makes it "},"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":"2607.21655","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-22T19:29:52Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1cd7396315cce3ab7b87a1c7e188b8e0d803d59d5656b56069673a5e5df86274","abstract_canon_sha256":"2d1b15bd3f25886ed9af59a202847d024d3a6d3bc9783f4c227679a30c7c968f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T00:20:13.435202Z","signature_b64":"RFiBHVhhyJlvc94AnIgnYie8SihSSWoAXKLA7zVEXIfGPtDwua3xhsZHjkeXXoctp6BZdCOtrQjvbu68JUvpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18f7d072b77ed675ad22bfc51d3a0f5d4453365a86c425e95a5d1e85f1f59b3f","last_reissued_at":"2026-07-27T00:20:13.434298Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T00:20:13.434298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Progress Reward Modeling for Robotic Learning: A Comprehensive Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.RO","authors_text":"Anbang Liu, Ce Zhang, Chengxuan Qian, Guo Ye, Han Liu, Haoran Lu, Jianshu Zhang, Keliang Wu, Weijie Yin, Xiyuan Yang, Zhenyu Pan","submitted_at":"2026-07-22T19:29:52Z","abstract_excerpt":"Robotic learning takes place in dynamic environments with large behavior spaces. A terminal success signal only tells the robot whether the task is completed. It does not explain whether the current behavior is making progress, remaining unchanged, or undoing earlier progress. For this reason, recent studies have increasingly explored progress rewards that provide feedback during task execution. However, the current literature lacks a shared framework. Existing methods use different observations, goal specifications, output signals, supervision sources, and evaluation protocols. This makes it "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21655","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/2607.21655/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":"2607.21655","created_at":"2026-07-27T00:20:13.434776+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.21655v1","created_at":"2026-07-27T00:20:13.434776+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21655","created_at":"2026-07-27T00:20:13.434776+00:00"},{"alias_kind":"pith_short_12","alias_value":"DD35A4VXP3LH","created_at":"2026-07-27T00:20:13.434776+00:00"},{"alias_kind":"pith_short_16","alias_value":"DD35A4VXP3LHLLJC","created_at":"2026-07-27T00:20:13.434776+00:00"},{"alias_kind":"pith_short_8","alias_value":"DD35A4VX","created_at":"2026-07-27T00:20:13.434776+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/DD35A4VXP3LHLLJCX7CR2OQPLV","json":"https://pith.science/pith/DD35A4VXP3LHLLJCX7CR2OQPLV.json","graph_json":"https://pith.science/api/pith-number/DD35A4VXP3LHLLJCX7CR2OQPLV/graph.json","events_json":"https://pith.science/api/pith-number/DD35A4VXP3LHLLJCX7CR2OQPLV/events.json","paper":"https://pith.science/paper/DD35A4VX"},"agent_actions":{"view_html":"https://pith.science/pith/DD35A4VXP3LHLLJCX7CR2OQPLV","download_json":"https://pith.science/pith/DD35A4VXP3LHLLJCX7CR2OQPLV.json","view_paper":"https://pith.science/paper/DD35A4VX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.21655&json=true","fetch_graph":"https://pith.science/api/pith-number/DD35A4VXP3LHLLJCX7CR2OQPLV/graph.json","fetch_events":"https://pith.science/api/pith-number/DD35A4VXP3LHLLJCX7CR2OQPLV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DD35A4VXP3LHLLJCX7CR2OQPLV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DD35A4VXP3LHLLJCX7CR2OQPLV/action/storage_attestation","attest_author":"https://pith.science/pith/DD35A4VXP3LHLLJCX7CR2OQPLV/action/author_attestation","sign_citation":"https://pith.science/pith/DD35A4VXP3LHLLJCX7CR2OQPLV/action/citation_signature","submit_replication":"https://pith.science/pith/DD35A4VXP3LHLLJCX7CR2OQPLV/action/replication_record"}},"created_at":"2026-07-27T00:20:13.434776+00:00","updated_at":"2026-07-27T00:20:13.434776+00:00"}