{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TDYZT7BLHR5RGKDEYN5LAI6ICB","short_pith_number":"pith:TDYZT7BL","schema_version":"1.0","canonical_sha256":"98f199fc2b3c7b132864c37ab023c8105ae2335fb8591cb741c8adb65c36cb2a","source":{"kind":"arxiv","id":"2306.00958","version":1},"attestation_state":"computed","paper":{"title":"LIV: Language-Image Representations and Rewards for Robotic Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Amy Zhang, Dinesh Jayaraman, Osbert Bastani, Vaidehi Som, Vikash Kumar, William Liang, Yecheng Jason Ma","submitted_at":"2023-06-01T17:52:23Z","abstract_excerpt":"We present Language-Image Value learning (LIV), a unified objective for vision-language representation and reward learning from action-free videos with text annotations. Exploiting a novel connection between dual reinforcement learning and mutual information contrastive learning, the LIV objective trains a multi-modal representation that implicitly encodes a universal value function for tasks specified as language or image goals. We use LIV to pre-train the first control-centric vision-language representation from large human video datasets such as EpicKitchen. Given only a language or image g"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2306.00958","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-06-01T17:52:23Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"48ecbf941bc721fcc50dbfdf247721edb9eeb3d8d09427688c780d1da6f7debc","abstract_canon_sha256":"891c046d9fc5bb822b160e79fc4c4471994b6c7a3f9526aeebf7341fe66d51d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:33.797651Z","signature_b64":"tDzS67AxVkCk0FtT/smorgiq96tFfByoG4iEQxN8O2S9Ob32H6arD50o2DptIC0G9N1zQqZwfmAvwKssRUbXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98f199fc2b3c7b132864c37ab023c8105ae2335fb8591cb741c8adb65c36cb2a","last_reissued_at":"2026-07-05T06:16:33.797161Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:33.797161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LIV: Language-Image Representations and Rewards for Robotic Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Amy Zhang, Dinesh Jayaraman, Osbert Bastani, Vaidehi Som, Vikash Kumar, William Liang, Yecheng Jason Ma","submitted_at":"2023-06-01T17:52:23Z","abstract_excerpt":"We present Language-Image Value learning (LIV), a unified objective for vision-language representation and reward learning from action-free videos with text annotations. Exploiting a novel connection between dual reinforcement learning and mutual information contrastive learning, the LIV objective trains a multi-modal representation that implicitly encodes a universal value function for tasks specified as language or image goals. We use LIV to pre-train the first control-centric vision-language representation from large human video datasets such as EpicKitchen. Given only a language or image g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00958","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/2306.00958/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2306.00958","created_at":"2026-07-05T06:16:33.797219+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.00958v1","created_at":"2026-07-05T06:16:33.797219+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00958","created_at":"2026-07-05T06:16:33.797219+00:00"},{"alias_kind":"pith_short_12","alias_value":"TDYZT7BLHR5R","created_at":"2026-07-05T06:16:33.797219+00:00"},{"alias_kind":"pith_short_16","alias_value":"TDYZT7BLHR5RGKDE","created_at":"2026-07-05T06:16:33.797219+00:00"},{"alias_kind":"pith_short_8","alias_value":"TDYZT7BL","created_at":"2026-07-05T06:16:33.797219+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05391","citing_title":"LLM-as-a-Verifier: A General-Purpose Verification Framework","ref_index":76,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21139","citing_title":"PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19333","citing_title":"Do as I Do: Dexterous Manipulation Data from Everyday Human Videos","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00483","citing_title":"VLM-AR3L: Vision-Language Models for Absolute and Relative Rewards in Reinforcement Learning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00483","citing_title":"VLM-AR3L: Vision-Language Models for Absolute and Relative Rewards in Reinforcement Learning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31377","citing_title":"Stage-Transition Dense Reward Modeling for Reinforcement Learning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17077","citing_title":"How to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2310.10639","citing_title":"Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04974","citing_title":"From Video to Control: A Survey of Learning Manipulation Interfaces from Temporal Visual Data","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10809","citing_title":"WARPED: Wrist-Aligned Rendering for Robot Policy Learning from Egocentric Human Demonstrations","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TDYZT7BLHR5RGKDEYN5LAI6ICB","json":"https://pith.science/pith/TDYZT7BLHR5RGKDEYN5LAI6ICB.json","graph_json":"https://pith.science/api/pith-number/TDYZT7BLHR5RGKDEYN5LAI6ICB/graph.json","events_json":"https://pith.science/api/pith-number/TDYZT7BLHR5RGKDEYN5LAI6ICB/events.json","paper":"https://pith.science/paper/TDYZT7BL"},"agent_actions":{"view_html":"https://pith.science/pith/TDYZT7BLHR5RGKDEYN5LAI6ICB","download_json":"https://pith.science/pith/TDYZT7BLHR5RGKDEYN5LAI6ICB.json","view_paper":"https://pith.science/paper/TDYZT7BL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.00958&json=true","fetch_graph":"https://pith.science/api/pith-number/TDYZT7BLHR5RGKDEYN5LAI6ICB/graph.json","fetch_events":"https://pith.science/api/pith-number/TDYZT7BLHR5RGKDEYN5LAI6ICB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TDYZT7BLHR5RGKDEYN5LAI6ICB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TDYZT7BLHR5RGKDEYN5LAI6ICB/action/storage_attestation","attest_author":"https://pith.science/pith/TDYZT7BLHR5RGKDEYN5LAI6ICB/action/author_attestation","sign_citation":"https://pith.science/pith/TDYZT7BLHR5RGKDEYN5LAI6ICB/action/citation_signature","submit_replication":"https://pith.science/pith/TDYZT7BLHR5RGKDEYN5LAI6ICB/action/replication_record"}},"created_at":"2026-07-05T06:16:33.797219+00:00","updated_at":"2026-07-05T06:16:33.797219+00:00"}