{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FMQNDG2SJ7MZJUQWTINBHAOXL6","short_pith_number":"pith:FMQNDG2S","canonical_record":{"source":{"id":"2502.11918","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T15:32:14Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"1ea5d20d84acc4c80dcbafbffe9b644df7fb546fa44b10ce89c92fe22aa61d67","abstract_canon_sha256":"7ba1aa97661907df77fed04d60ad09727d0440681512bcab5e6bc15375c37845"},"schema_version":"1.0"},"canonical_sha256":"2b20d19b524fd994d2169a1a1381d75fa094c55c1e5645f80a6d2745776dd791","source":{"kind":"arxiv","id":"2502.11918","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11918","created_at":"2026-07-05T10:15:36Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11918v1","created_at":"2026-07-05T10:15:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11918","created_at":"2026-07-05T10:15:36Z"},{"alias_kind":"pith_short_12","alias_value":"FMQNDG2SJ7MZ","created_at":"2026-07-05T10:15:36Z"},{"alias_kind":"pith_short_16","alias_value":"FMQNDG2SJ7MZJUQW","created_at":"2026-07-05T10:15:36Z"},{"alias_kind":"pith_short_8","alias_value":"FMQNDG2S","created_at":"2026-07-05T10:15:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FMQNDG2SJ7MZJUQWTINBHAOXL6","target":"record","payload":{"canonical_record":{"source":{"id":"2502.11918","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T15:32:14Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"1ea5d20d84acc4c80dcbafbffe9b644df7fb546fa44b10ce89c92fe22aa61d67","abstract_canon_sha256":"7ba1aa97661907df77fed04d60ad09727d0440681512bcab5e6bc15375c37845"},"schema_version":"1.0"},"canonical_sha256":"2b20d19b524fd994d2169a1a1381d75fa094c55c1e5645f80a6d2745776dd791","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:36.052461Z","signature_b64":"9rfne49xXfGXbP1WylOjCKU7/749v9vWHkyJ5VzKvdWKOspCbnCAjeuhsk+MGRPrV07E/a8Gjge6rHQAT+UYDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b20d19b524fd994d2169a1a1381d75fa094c55c1e5645f80a6d2745776dd791","last_reissued_at":"2026-07-05T10:15:36.051980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:36.051980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.11918","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":"2026-07-05T10:15:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dUuI0notHkNrUmfsy04N1EAjWIK4eUE5gFkROOnFyHlyLCeSF/PVnsq1j3x5ZuDmXa0Ndu6z4rOPpHOU4Kx2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T01:52:31.377243Z"},"content_sha256":"78943766b1e4983e91b4e95d26a76967874789906eb517aa33d07083d2ae0f10","schema_version":"1.0","event_id":"sha256:78943766b1e4983e91b4e95d26a76967874789906eb517aa33d07083d2ae0f10"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FMQNDG2SJ7MZJUQWTINBHAOXL6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VLP: Vision-Language Preference Learning for Embodied Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Chenjia Bai, Jiafei Lyu, Runze Liu, Shengjie Sun, Xiu Li, Yali Du","submitted_at":"2025-02-17T15:32:14Z","abstract_excerpt":"Reward engineering is one of the key challenges in Reinforcement Learning (RL). Preference-based RL effectively addresses this issue by learning from human feedback. However, it is both time-consuming and expensive to collect human preference labels. In this paper, we propose a novel \\textbf{V}ision-\\textbf{L}anguage \\textbf{P}reference learning framework, named \\textbf{VLP}, which learns a vision-language preference model to provide preference feedback for embodied manipulation tasks. To achieve this, we define three types of language-conditioned preferences and construct a vision-language pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11918","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/2502.11918/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":"2026-07-05T10:15:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lex9ovKTMpi4VEI9d/4ialcRl/uN69Tg5gRgyE/4oYnEUnOzVELWOIZuU7RxM8fZWlFh7NcmBUUUvQ1LpBY+Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T01:52:31.378103Z"},"content_sha256":"c7b5adfb3b3620208815b3078717a8865bba4d9767bf955427cb2516a4de4c4b","schema_version":"1.0","event_id":"sha256:c7b5adfb3b3620208815b3078717a8865bba4d9767bf955427cb2516a4de4c4b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FMQNDG2SJ7MZJUQWTINBHAOXL6/bundle.json","state_url":"https://pith.science/pith/FMQNDG2SJ7MZJUQWTINBHAOXL6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FMQNDG2SJ7MZJUQWTINBHAOXL6/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":"2026-08-21T01:52:31Z","links":{"resolver":"https://pith.science/pith/FMQNDG2SJ7MZJUQWTINBHAOXL6","bundle":"https://pith.science/pith/FMQNDG2SJ7MZJUQWTINBHAOXL6/bundle.json","state":"https://pith.science/pith/FMQNDG2SJ7MZJUQWTINBHAOXL6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FMQNDG2SJ7MZJUQWTINBHAOXL6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FMQNDG2SJ7MZJUQWTINBHAOXL6","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":"7ba1aa97661907df77fed04d60ad09727d0440681512bcab5e6bc15375c37845","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T15:32:14Z","title_canon_sha256":"1ea5d20d84acc4c80dcbafbffe9b644df7fb546fa44b10ce89c92fe22aa61d67"},"schema_version":"1.0","source":{"id":"2502.11918","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11918","created_at":"2026-07-05T10:15:36Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11918v1","created_at":"2026-07-05T10:15:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11918","created_at":"2026-07-05T10:15:36Z"},{"alias_kind":"pith_short_12","alias_value":"FMQNDG2SJ7MZ","created_at":"2026-07-05T10:15:36Z"},{"alias_kind":"pith_short_16","alias_value":"FMQNDG2SJ7MZJUQW","created_at":"2026-07-05T10:15:36Z"},{"alias_kind":"pith_short_8","alias_value":"FMQNDG2S","created_at":"2026-07-05T10:15:36Z"}],"graph_snapshots":[{"event_id":"sha256:c7b5adfb3b3620208815b3078717a8865bba4d9767bf955427cb2516a4de4c4b","target":"graph","created_at":"2026-07-05T10:15:36Z","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/2502.11918/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward engineering is one of the key challenges in Reinforcement Learning (RL). Preference-based RL effectively addresses this issue by learning from human feedback. However, it is both time-consuming and expensive to collect human preference labels. In this paper, we propose a novel \\textbf{V}ision-\\textbf{L}anguage \\textbf{P}reference learning framework, named \\textbf{VLP}, which learns a vision-language preference model to provide preference feedback for embodied manipulation tasks. To achieve this, we define three types of language-conditioned preferences and construct a vision-language pr","authors_text":"Chenjia Bai, Jiafei Lyu, Runze Liu, Shengjie Sun, Xiu Li, Yali Du","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T15:32:14Z","title":"VLP: Vision-Language Preference Learning for Embodied Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11918","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":"sha256:78943766b1e4983e91b4e95d26a76967874789906eb517aa33d07083d2ae0f10","target":"record","created_at":"2026-07-05T10:15:36Z","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":"7ba1aa97661907df77fed04d60ad09727d0440681512bcab5e6bc15375c37845","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T15:32:14Z","title_canon_sha256":"1ea5d20d84acc4c80dcbafbffe9b644df7fb546fa44b10ce89c92fe22aa61d67"},"schema_version":"1.0","source":{"id":"2502.11918","kind":"arxiv","version":1}},"canonical_sha256":"2b20d19b524fd994d2169a1a1381d75fa094c55c1e5645f80a6d2745776dd791","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b20d19b524fd994d2169a1a1381d75fa094c55c1e5645f80a6d2745776dd791","first_computed_at":"2026-07-05T10:15:36.051980Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:15:36.051980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9rfne49xXfGXbP1WylOjCKU7/749v9vWHkyJ5VzKvdWKOspCbnCAjeuhsk+MGRPrV07E/a8Gjge6rHQAT+UYDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:15:36.052461Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.11918","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78943766b1e4983e91b4e95d26a76967874789906eb517aa33d07083d2ae0f10","sha256:c7b5adfb3b3620208815b3078717a8865bba4d9767bf955427cb2516a4de4c4b"],"state_sha256":"31aa796a6a2a268d650dee834c657bb120aef94526c2f45023450098484d1c22"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eBYCzxKqj6i0I0PMP+k+Vx8V2HBi1hUDTP05sQnUukVd77UvPEzghlrcuMq7XFjyw4MG7CH+ef+QxAG+TTTOCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T01:52:31.383848Z","bundle_sha256":"4c49c992aa5f54e6b5084f924fa00df82dc9bad4ab9ce5a0eeb32163897af7e2"}}