{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:2MNSEPXWX4NPATR2UXQ4QSNTX7","short_pith_number":"pith:2MNSEPXW","canonical_record":{"source":{"id":"2310.12921","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-19T17:17:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3b1916a403453d8261ec074ad619beaee32e2b5a019f3a5f89894a7a8ff6561d","abstract_canon_sha256":"d475c89ac3c1840711c23841f8011cef58d2f7921d73da5de123a40e1dde866d"},"schema_version":"1.0"},"canonical_sha256":"d31b223ef6bf1af04e3aa5e1c849b3bfed563bdd7fcb1a687dfd3d4957be0f13","source":{"kind":"arxiv","id":"2310.12921","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.12921","created_at":"2026-07-05T07:56:00Z"},{"alias_kind":"arxiv_version","alias_value":"2310.12921v2","created_at":"2026-07-05T07:56:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12921","created_at":"2026-07-05T07:56:00Z"},{"alias_kind":"pith_short_12","alias_value":"2MNSEPXWX4NP","created_at":"2026-07-05T07:56:00Z"},{"alias_kind":"pith_short_16","alias_value":"2MNSEPXWX4NPATR2","created_at":"2026-07-05T07:56:00Z"},{"alias_kind":"pith_short_8","alias_value":"2MNSEPXW","created_at":"2026-07-05T07:56:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:2MNSEPXWX4NPATR2UXQ4QSNTX7","target":"record","payload":{"canonical_record":{"source":{"id":"2310.12921","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-19T17:17:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3b1916a403453d8261ec074ad619beaee32e2b5a019f3a5f89894a7a8ff6561d","abstract_canon_sha256":"d475c89ac3c1840711c23841f8011cef58d2f7921d73da5de123a40e1dde866d"},"schema_version":"1.0"},"canonical_sha256":"d31b223ef6bf1af04e3aa5e1c849b3bfed563bdd7fcb1a687dfd3d4957be0f13","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:00.617943Z","signature_b64":"HBdaziHK/nWJXVyjo8BOZWBhx3q/2j3JyzHR1ihYXcmKsCjJpfyH8r9baEMmXWIzAx3PSS3nmWu1ebc+UfGkCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d31b223ef6bf1af04e3aa5e1c849b3bfed563bdd7fcb1a687dfd3d4957be0f13","last_reissued_at":"2026-07-05T07:56:00.617394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:00.617394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.12921","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:56:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kC4hTxSsG0PbYrLx3JBoZqHSmA5NDdiClX5WwMCh2JX1w9XUqtnlX7ZpskW9Sp9NGRyvjl/eAptORzQnA583Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T04:18:09.031530Z"},"content_sha256":"1188f7ad7ba77770d4875577db5bf810b10512923b06e5ddb37872ad32eee93c","schema_version":"1.0","event_id":"sha256:1188f7ad7ba77770d4875577db5bf810b10512923b06e5ddb37872ad32eee93c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:2MNSEPXWX4NPATR2UXQ4QSNTX7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Lindner, Elvis Nava, Ethan Perez, Juan Rocamonde, Victoriano Montesinos","submitted_at":"2023-10-19T17:17:06Z","abstract_excerpt":"Reinforcement learning (RL) requires either manually specifying a reward function, which is often infeasible, or learning a reward model from a large amount of human feedback, which is often very expensive. We study a more sample-efficient alternative: using pretrained vision-language models (VLMs) as zero-shot reward models (RMs) to specify tasks via natural language. We propose a natural and general approach to using VLMs as reward models, which we call VLM-RMs. We use VLM-RMs based on CLIP to train a MuJoCo humanoid to learn complex tasks without a manually specified reward function, such a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12921","kind":"arxiv","version":2},"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/2310.12921/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":"2026-07-05T07:56:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qeVBNiaaFN7/gC+PdsvocsbOPo0+8eYRE5fvct6CinXEdv4GYrJP/4MsF668aFsCTi0bIcg7ewfsDZ6fVXDeCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T04:18:09.031916Z"},"content_sha256":"e7cc698687fd9a658cb5a308aa4d3c7a06272dc04fb4fdbd868b60cc868f5a0d","schema_version":"1.0","event_id":"sha256:e7cc698687fd9a658cb5a308aa4d3c7a06272dc04fb4fdbd868b60cc868f5a0d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2MNSEPXWX4NPATR2UXQ4QSNTX7/bundle.json","state_url":"https://pith.science/pith/2MNSEPXWX4NPATR2UXQ4QSNTX7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2MNSEPXWX4NPATR2UXQ4QSNTX7/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":"2026-07-16T04:18:09Z","links":{"resolver":"https://pith.science/pith/2MNSEPXWX4NPATR2UXQ4QSNTX7","bundle":"https://pith.science/pith/2MNSEPXWX4NPATR2UXQ4QSNTX7/bundle.json","state":"https://pith.science/pith/2MNSEPXWX4NPATR2UXQ4QSNTX7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2MNSEPXWX4NPATR2UXQ4QSNTX7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2MNSEPXWX4NPATR2UXQ4QSNTX7","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":"d475c89ac3c1840711c23841f8011cef58d2f7921d73da5de123a40e1dde866d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-19T17:17:06Z","title_canon_sha256":"3b1916a403453d8261ec074ad619beaee32e2b5a019f3a5f89894a7a8ff6561d"},"schema_version":"1.0","source":{"id":"2310.12921","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.12921","created_at":"2026-07-05T07:56:00Z"},{"alias_kind":"arxiv_version","alias_value":"2310.12921v2","created_at":"2026-07-05T07:56:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12921","created_at":"2026-07-05T07:56:00Z"},{"alias_kind":"pith_short_12","alias_value":"2MNSEPXWX4NP","created_at":"2026-07-05T07:56:00Z"},{"alias_kind":"pith_short_16","alias_value":"2MNSEPXWX4NPATR2","created_at":"2026-07-05T07:56:00Z"},{"alias_kind":"pith_short_8","alias_value":"2MNSEPXW","created_at":"2026-07-05T07:56:00Z"}],"graph_snapshots":[{"event_id":"sha256:e7cc698687fd9a658cb5a308aa4d3c7a06272dc04fb4fdbd868b60cc868f5a0d","target":"graph","created_at":"2026-07-05T07:56:00Z","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/2310.12921/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) requires either manually specifying a reward function, which is often infeasible, or learning a reward model from a large amount of human feedback, which is often very expensive. We study a more sample-efficient alternative: using pretrained vision-language models (VLMs) as zero-shot reward models (RMs) to specify tasks via natural language. We propose a natural and general approach to using VLMs as reward models, which we call VLM-RMs. We use VLM-RMs based on CLIP to train a MuJoCo humanoid to learn complex tasks without a manually specified reward function, such a","authors_text":"David Lindner, Elvis Nava, Ethan Perez, Juan Rocamonde, Victoriano Montesinos","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-19T17:17:06Z","title":"Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12921","kind":"arxiv","version":2},"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":"sha256:1188f7ad7ba77770d4875577db5bf810b10512923b06e5ddb37872ad32eee93c","target":"record","created_at":"2026-07-05T07:56:00Z","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":"d475c89ac3c1840711c23841f8011cef58d2f7921d73da5de123a40e1dde866d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-19T17:17:06Z","title_canon_sha256":"3b1916a403453d8261ec074ad619beaee32e2b5a019f3a5f89894a7a8ff6561d"},"schema_version":"1.0","source":{"id":"2310.12921","kind":"arxiv","version":2}},"canonical_sha256":"d31b223ef6bf1af04e3aa5e1c849b3bfed563bdd7fcb1a687dfd3d4957be0f13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d31b223ef6bf1af04e3aa5e1c849b3bfed563bdd7fcb1a687dfd3d4957be0f13","first_computed_at":"2026-07-05T07:56:00.617394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:56:00.617394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HBdaziHK/nWJXVyjo8BOZWBhx3q/2j3JyzHR1ihYXcmKsCjJpfyH8r9baEMmXWIzAx3PSS3nmWu1ebc+UfGkCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:56:00.617943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.12921","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1188f7ad7ba77770d4875577db5bf810b10512923b06e5ddb37872ad32eee93c","sha256:e7cc698687fd9a658cb5a308aa4d3c7a06272dc04fb4fdbd868b60cc868f5a0d"],"state_sha256":"4216edd0caadac5cb9ad18a6105572fb053c34bc59beb0cf7018141eb041b9a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BLrQmskxfzoVYNvetchmnnLiAN+bHH7aQCex0ioku4fs0mpjb74nuqD3JQF1rI1bC0iUTpL6ZfTwPau++z9jDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T04:18:09.034050Z","bundle_sha256":"f0789a74d81aaa98a3668ad8787a1861f06d77925af8bed0f03be5e3cf41f923"}}