{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZSHAAIW2VLJM3S7GOTND7BT46Q","short_pith_number":"pith:ZSHAAIW2","canonical_record":{"source":{"id":"2308.12270","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-23T17:37:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"645f809d48b0364cf4c6ec996da917f8a200da33675b7825d5c140c76b3e961a","abstract_canon_sha256":"67debeee9eba82d7a3bcc5a68b822049c890a24fb39ff99e246d03d39eded4fb"},"schema_version":"1.0"},"canonical_sha256":"cc8e0022daaad2cdcbe674da3f867cf430ab7c07390c978a3971a868b602c853","source":{"kind":"arxiv","id":"2308.12270","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.12270","created_at":"2026-07-05T06:44:02Z"},{"alias_kind":"arxiv_version","alias_value":"2308.12270v1","created_at":"2026-07-05T06:44:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12270","created_at":"2026-07-05T06:44:02Z"},{"alias_kind":"pith_short_12","alias_value":"ZSHAAIW2VLJM","created_at":"2026-07-05T06:44:02Z"},{"alias_kind":"pith_short_16","alias_value":"ZSHAAIW2VLJM3S7G","created_at":"2026-07-05T06:44:02Z"},{"alias_kind":"pith_short_8","alias_value":"ZSHAAIW2","created_at":"2026-07-05T06:44:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZSHAAIW2VLJM3S7GOTND7BT46Q","target":"record","payload":{"canonical_record":{"source":{"id":"2308.12270","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-23T17:37:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"645f809d48b0364cf4c6ec996da917f8a200da33675b7825d5c140c76b3e961a","abstract_canon_sha256":"67debeee9eba82d7a3bcc5a68b822049c890a24fb39ff99e246d03d39eded4fb"},"schema_version":"1.0"},"canonical_sha256":"cc8e0022daaad2cdcbe674da3f867cf430ab7c07390c978a3971a868b602c853","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:02.357626Z","signature_b64":"Gy+q6WwzasnDEcWn9tqhziu7lDGYiw+cMvMMVDmBWoxedNfREvq/BlfFdTF6+j7KzC7qxPvXl1iEfaZyTF1RDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc8e0022daaad2cdcbe674da3f867cf430ab7c07390c978a3971a868b602c853","last_reissued_at":"2026-07-05T06:44:02.356796Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:02.356796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.12270","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":"2026-07-05T06:44:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jjapku8MBDNBghjOHeme29wfkL5cavHUfOVKY2IDlbkgVqAgg6mY+feeYyZhxfQ8hcOEcpB7r1x5nt1DERvSAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T17:49:15.916696Z"},"content_sha256":"607a3de792935fb6d0763abeb47b1ef610cbebd48d821d63f0a6d97abd16ad72","schema_version":"1.0","event_id":"sha256:607a3de792935fb6d0763abeb47b1ef610cbebd48d821d63f0a6d97abd16ad72"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZSHAAIW2VLJM3S7GOTND7BT46Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language Reward Modulation for Pretraining Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ademi Adeniji, Amber Xie, Carmelo Sferrazza, Pieter Abbeel, Stephen James, Younggyo Seo","submitted_at":"2023-08-23T17:37:51Z","abstract_excerpt":"Using learned reward functions (LRFs) as a means to solve sparse-reward reinforcement learning (RL) tasks has yielded some steady progress in task-complexity through the years. In this work, we question whether today's LRFs are best-suited as a direct replacement for task rewards. Instead, we propose leveraging the capabilities of LRFs as a pretraining signal for RL. Concretely, we propose $\\textbf{LA}$nguage Reward $\\textbf{M}$odulated $\\textbf{P}$retraining (LAMP) which leverages the zero-shot capabilities of Vision-Language Models (VLMs) as a $\\textit{pretraining}$ utility for RL as opposed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12270","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/2308.12270/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":"2026-07-05T06:44:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UijBItEML0BBQAbe8yjdOo/IwGzIBFZd/nOI/R7hM6KaHiv/tTVD2G+W1kQg07ZJUlo1+fFXbk9EMmWWIFNpDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T17:49:15.917422Z"},"content_sha256":"db9609eb68b396fae18585e2b99137acee786c4f5c87d6efd86d41a494274c4d","schema_version":"1.0","event_id":"sha256:db9609eb68b396fae18585e2b99137acee786c4f5c87d6efd86d41a494274c4d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZSHAAIW2VLJM3S7GOTND7BT46Q/bundle.json","state_url":"https://pith.science/pith/ZSHAAIW2VLJM3S7GOTND7BT46Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZSHAAIW2VLJM3S7GOTND7BT46Q/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":"2026-08-10T17:49:15Z","links":{"resolver":"https://pith.science/pith/ZSHAAIW2VLJM3S7GOTND7BT46Q","bundle":"https://pith.science/pith/ZSHAAIW2VLJM3S7GOTND7BT46Q/bundle.json","state":"https://pith.science/pith/ZSHAAIW2VLJM3S7GOTND7BT46Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZSHAAIW2VLJM3S7GOTND7BT46Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZSHAAIW2VLJM3S7GOTND7BT46Q","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":"67debeee9eba82d7a3bcc5a68b822049c890a24fb39ff99e246d03d39eded4fb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-23T17:37:51Z","title_canon_sha256":"645f809d48b0364cf4c6ec996da917f8a200da33675b7825d5c140c76b3e961a"},"schema_version":"1.0","source":{"id":"2308.12270","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.12270","created_at":"2026-07-05T06:44:02Z"},{"alias_kind":"arxiv_version","alias_value":"2308.12270v1","created_at":"2026-07-05T06:44:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12270","created_at":"2026-07-05T06:44:02Z"},{"alias_kind":"pith_short_12","alias_value":"ZSHAAIW2VLJM","created_at":"2026-07-05T06:44:02Z"},{"alias_kind":"pith_short_16","alias_value":"ZSHAAIW2VLJM3S7G","created_at":"2026-07-05T06:44:02Z"},{"alias_kind":"pith_short_8","alias_value":"ZSHAAIW2","created_at":"2026-07-05T06:44:02Z"}],"graph_snapshots":[{"event_id":"sha256:db9609eb68b396fae18585e2b99137acee786c4f5c87d6efd86d41a494274c4d","target":"graph","created_at":"2026-07-05T06:44:02Z","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/2308.12270/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Using learned reward functions (LRFs) as a means to solve sparse-reward reinforcement learning (RL) tasks has yielded some steady progress in task-complexity through the years. In this work, we question whether today's LRFs are best-suited as a direct replacement for task rewards. Instead, we propose leveraging the capabilities of LRFs as a pretraining signal for RL. Concretely, we propose $\\textbf{LA}$nguage Reward $\\textbf{M}$odulated $\\textbf{P}$retraining (LAMP) which leverages the zero-shot capabilities of Vision-Language Models (VLMs) as a $\\textit{pretraining}$ utility for RL as opposed","authors_text":"Ademi Adeniji, Amber Xie, Carmelo Sferrazza, Pieter Abbeel, Stephen James, Younggyo Seo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-23T17:37:51Z","title":"Language Reward Modulation for Pretraining Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12270","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":"sha256:607a3de792935fb6d0763abeb47b1ef610cbebd48d821d63f0a6d97abd16ad72","target":"record","created_at":"2026-07-05T06:44:02Z","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":"67debeee9eba82d7a3bcc5a68b822049c890a24fb39ff99e246d03d39eded4fb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-23T17:37:51Z","title_canon_sha256":"645f809d48b0364cf4c6ec996da917f8a200da33675b7825d5c140c76b3e961a"},"schema_version":"1.0","source":{"id":"2308.12270","kind":"arxiv","version":1}},"canonical_sha256":"cc8e0022daaad2cdcbe674da3f867cf430ab7c07390c978a3971a868b602c853","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc8e0022daaad2cdcbe674da3f867cf430ab7c07390c978a3971a868b602c853","first_computed_at":"2026-07-05T06:44:02.356796Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:44:02.356796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gy+q6WwzasnDEcWn9tqhziu7lDGYiw+cMvMMVDmBWoxedNfREvq/BlfFdTF6+j7KzC7qxPvXl1iEfaZyTF1RDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:44:02.357626Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.12270","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:607a3de792935fb6d0763abeb47b1ef610cbebd48d821d63f0a6d97abd16ad72","sha256:db9609eb68b396fae18585e2b99137acee786c4f5c87d6efd86d41a494274c4d"],"state_sha256":"507f9bb54cc041fe1f99ec8a9f13016f5db5dc33c6087c9496178f1e4fd98dcd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b9OrARgAjAAn+E8ErtBz4BbehUrR2g9HreDrZtpoj5/I093CV8oby+0qMqMxG8Fi6JwqMHvHeKvygfSW6sogBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T17:49:15.923197Z","bundle_sha256":"73857ceeaae9f1e51535eaa4cb797d93286666de518bc3d0888bd621556f74ab"}}