{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QDHBP43TIUURC2QY6M5P52GP7R","short_pith_number":"pith:QDHBP43T","canonical_record":{"source":{"id":"2507.23391","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-31T10:07:49Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"a3e53122af9f199a7345ee6fda2225ee332164307d90189105900a33f007d6a9","abstract_canon_sha256":"0ecef0af0fae645a2f41f76a3250f8e90d8c9e37983dea139e899ae81df7ef9b"},"schema_version":"1.0"},"canonical_sha256":"80ce17f3734529116a18f33afee8cffc4713f4d54bcae9d50dbcf48154fb999b","source":{"kind":"arxiv","id":"2507.23391","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.23391","created_at":"2026-07-05T11:46:11Z"},{"alias_kind":"arxiv_version","alias_value":"2507.23391v1","created_at":"2026-07-05T11:46:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23391","created_at":"2026-07-05T11:46:11Z"},{"alias_kind":"pith_short_12","alias_value":"QDHBP43TIUUR","created_at":"2026-07-05T11:46:11Z"},{"alias_kind":"pith_short_16","alias_value":"QDHBP43TIUURC2QY","created_at":"2026-07-05T11:46:11Z"},{"alias_kind":"pith_short_8","alias_value":"QDHBP43T","created_at":"2026-07-05T11:46:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QDHBP43TIUURC2QY6M5P52GP7R","target":"record","payload":{"canonical_record":{"source":{"id":"2507.23391","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-31T10:07:49Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"a3e53122af9f199a7345ee6fda2225ee332164307d90189105900a33f007d6a9","abstract_canon_sha256":"0ecef0af0fae645a2f41f76a3250f8e90d8c9e37983dea139e899ae81df7ef9b"},"schema_version":"1.0"},"canonical_sha256":"80ce17f3734529116a18f33afee8cffc4713f4d54bcae9d50dbcf48154fb999b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:11.321196Z","signature_b64":"jxSJ4Q/0oQB9daTpR/jOORQm6gFGf2ICHkc0935VIZspe2Kz0Z0l31FBbcTVPV9AxC6wKMvUbjgEOpEQZ3axAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80ce17f3734529116a18f33afee8cffc4713f4d54bcae9d50dbcf48154fb999b","last_reissued_at":"2026-07-05T11:46:11.320777Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:11.320777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.23391","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:46:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qN7O5XBs0iUZAIjgxLlz/5KdD1Hn9m9q6Hswxa5jjYwuJWvd5vAQ27LwN/IHWh1Kkrk7YHs9Wkr4eOg9aLUQBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:45:32.177725Z"},"content_sha256":"6e6775e3978f79d97ec8e7ff67997b695c5f21113f8675e43fb61c9d31d2f545","schema_version":"1.0","event_id":"sha256:6e6775e3978f79d97ec8e7ff67997b695c5f21113f8675e43fb61c9d31d2f545"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QDHBP43TIUURC2QY6M5P52GP7R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy Learning from Large Vision-Language Model Feedback without Reward Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Chang D. Yoo, Donghoon Lee, Tung M. Luu, Younghwan Lee","submitted_at":"2025-07-31T10:07:49Z","abstract_excerpt":"Offline reinforcement learning (RL) provides a powerful framework for training robotic agents using pre-collected, suboptimal datasets, eliminating the need for costly, time-consuming, and potentially hazardous online interactions. This is particularly useful in safety-critical real-world applications, where online data collection is expensive and impractical. However, existing offline RL algorithms typically require reward labeled data, which introduces an additional bottleneck: reward function design is itself costly, labor-intensive, and requires significant domain expertise. In this paper,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23391","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/2507.23391/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:46:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"irgKdZQRnQG6n4IwtBPTI7CpV2yF6/FXNh6a7afEc6opkFb1CCZ0meOzI0kUdfWU7DEQsfzEBpCp3rnpZxE2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:45:32.178253Z"},"content_sha256":"2891951f80cac849f5f6e5790c9dd388549b9f2dddd79e00acd4febbf0aa7670","schema_version":"1.0","event_id":"sha256:2891951f80cac849f5f6e5790c9dd388549b9f2dddd79e00acd4febbf0aa7670"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QDHBP43TIUURC2QY6M5P52GP7R/bundle.json","state_url":"https://pith.science/pith/QDHBP43TIUURC2QY6M5P52GP7R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QDHBP43TIUURC2QY6M5P52GP7R/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T01:45:32Z","links":{"resolver":"https://pith.science/pith/QDHBP43TIUURC2QY6M5P52GP7R","bundle":"https://pith.science/pith/QDHBP43TIUURC2QY6M5P52GP7R/bundle.json","state":"https://pith.science/pith/QDHBP43TIUURC2QY6M5P52GP7R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QDHBP43TIUURC2QY6M5P52GP7R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QDHBP43TIUURC2QY6M5P52GP7R","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0ecef0af0fae645a2f41f76a3250f8e90d8c9e37983dea139e899ae81df7ef9b","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-31T10:07:49Z","title_canon_sha256":"a3e53122af9f199a7345ee6fda2225ee332164307d90189105900a33f007d6a9"},"schema_version":"1.0","source":{"id":"2507.23391","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.23391","created_at":"2026-07-05T11:46:11Z"},{"alias_kind":"arxiv_version","alias_value":"2507.23391v1","created_at":"2026-07-05T11:46:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23391","created_at":"2026-07-05T11:46:11Z"},{"alias_kind":"pith_short_12","alias_value":"QDHBP43TIUUR","created_at":"2026-07-05T11:46:11Z"},{"alias_kind":"pith_short_16","alias_value":"QDHBP43TIUURC2QY","created_at":"2026-07-05T11:46:11Z"},{"alias_kind":"pith_short_8","alias_value":"QDHBP43T","created_at":"2026-07-05T11:46:11Z"}],"graph_snapshots":[{"event_id":"sha256:2891951f80cac849f5f6e5790c9dd388549b9f2dddd79e00acd4febbf0aa7670","target":"graph","created_at":"2026-07-05T11:46:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.23391/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) provides a powerful framework for training robotic agents using pre-collected, suboptimal datasets, eliminating the need for costly, time-consuming, and potentially hazardous online interactions. This is particularly useful in safety-critical real-world applications, where online data collection is expensive and impractical. However, existing offline RL algorithms typically require reward labeled data, which introduces an additional bottleneck: reward function design is itself costly, labor-intensive, and requires significant domain expertise. In this paper,","authors_text":"Chang D. Yoo, Donghoon Lee, Tung M. Luu, Younghwan Lee","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-31T10:07:49Z","title":"Policy Learning from Large Vision-Language Model Feedback without Reward Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23391","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6e6775e3978f79d97ec8e7ff67997b695c5f21113f8675e43fb61c9d31d2f545","target":"record","created_at":"2026-07-05T11:46:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0ecef0af0fae645a2f41f76a3250f8e90d8c9e37983dea139e899ae81df7ef9b","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-31T10:07:49Z","title_canon_sha256":"a3e53122af9f199a7345ee6fda2225ee332164307d90189105900a33f007d6a9"},"schema_version":"1.0","source":{"id":"2507.23391","kind":"arxiv","version":1}},"canonical_sha256":"80ce17f3734529116a18f33afee8cffc4713f4d54bcae9d50dbcf48154fb999b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80ce17f3734529116a18f33afee8cffc4713f4d54bcae9d50dbcf48154fb999b","first_computed_at":"2026-07-05T11:46:11.320777Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:46:11.320777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jxSJ4Q/0oQB9daTpR/jOORQm6gFGf2ICHkc0935VIZspe2Kz0Z0l31FBbcTVPV9AxC6wKMvUbjgEOpEQZ3axAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:46:11.321196Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.23391","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e6775e3978f79d97ec8e7ff67997b695c5f21113f8675e43fb61c9d31d2f545","sha256:2891951f80cac849f5f6e5790c9dd388549b9f2dddd79e00acd4febbf0aa7670"],"state_sha256":"a4e15c6f724ae27edc32f3ddb98fbd52326e3f092e6c2f9c63fa5af273360544"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MSh3/rg8IpUtfm0sXrrnc8kfCukG+vu6x9XJ6pCa7pHfMi/9uG2txtnGhu2MEwqYaLK9ic2FfFGmjbydkLUnAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:45:32.181888Z","bundle_sha256":"8a5cf63e1360219ca5dda50712fdddc8516aa2a59bc182b51f9659816a4fd404"}}