{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:B4PBXILFMETNCJTLJQY5ATBTIE","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":"3909ff753807c78f92ce0397a7c3f9004159bc4ed950c580f0cf2cae08d3d6cc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-09T13:34:45Z","title_canon_sha256":"736cdb18e639a5dcb850225eddecd1bf21d691cc3548ebfdd59f777c0b5cac84"},"schema_version":"1.0","source":{"id":"2211.04878","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.04878","created_at":"2026-07-05T05:14:42Z"},{"alias_kind":"arxiv_version","alias_value":"2211.04878v1","created_at":"2026-07-05T05:14:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.04878","created_at":"2026-07-05T05:14:42Z"},{"alias_kind":"pith_short_12","alias_value":"B4PBXILFMETN","created_at":"2026-07-05T05:14:42Z"},{"alias_kind":"pith_short_16","alias_value":"B4PBXILFMETNCJTL","created_at":"2026-07-05T05:14:42Z"},{"alias_kind":"pith_short_8","alias_value":"B4PBXILF","created_at":"2026-07-05T05:14:42Z"}],"graph_snapshots":[{"event_id":"sha256:dfc136b9251e33eb5780ce7d04fb8a042e312f04a62bfc03bb497a49c6b6bbb0","target":"graph","created_at":"2026-07-05T05:14:42Z","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/2211.04878/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Effectively exploring the environment is a key challenge in reinforcement learning (RL). We address this challenge by defining a novel intrinsic reward based on a foundation model, such as contrastive language image pretraining (CLIP), which can encode a wealth of domain-independent semantic visual-language knowledge about the world. Specifically, our intrinsic reward is defined based on pre-trained CLIP embeddings without any fine-tuning or learning on the target RL task. We demonstrate that CLIP-based intrinsic rewards can drive exploration towards semantically meaningful states and outperfo","authors_text":"Danfei Xu, Marco Pavone, Peter Karkus, Tarun Gupta, Tong Che","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-09T13:34:45Z","title":"Foundation Models for Semantic Novelty in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.04878","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":"sha256:7ef9a1f9084124b3a585ae1cf1e6d2c154bc8cf8c87c20098babe65e1e2f4af0","target":"record","created_at":"2026-07-05T05:14:42Z","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":"3909ff753807c78f92ce0397a7c3f9004159bc4ed950c580f0cf2cae08d3d6cc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-09T13:34:45Z","title_canon_sha256":"736cdb18e639a5dcb850225eddecd1bf21d691cc3548ebfdd59f777c0b5cac84"},"schema_version":"1.0","source":{"id":"2211.04878","kind":"arxiv","version":1}},"canonical_sha256":"0f1e1ba1656126d1266b4c31d04c33412f04d01f74b5bd28e47588ebed03ea50","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f1e1ba1656126d1266b4c31d04c33412f04d01f74b5bd28e47588ebed03ea50","first_computed_at":"2026-07-05T05:14:42.851722Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:14:42.851722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xSSrOB4f/6FGd9LMNE6MnmBulEoeTh5ZuOR0q5ksilqM8tJ1pfP3wrTfm6PwOzsNAkrJZTTuz4zewLdeDSs5BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:14:42.852103Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.04878","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ef9a1f9084124b3a585ae1cf1e6d2c154bc8cf8c87c20098babe65e1e2f4af0","sha256:dfc136b9251e33eb5780ce7d04fb8a042e312f04a62bfc03bb497a49c6b6bbb0"],"state_sha256":"2128e0917bc69db567544765b2ebf7bde78630d85cc1d338c2462ee89d54f7fd"}