{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OCN5YETNF2I4MQBYBAEI734YCT","short_pith_number":"pith:OCN5YETN","schema_version":"1.0","canonical_sha256":"709bdc126d2e91c6403808088fef9814ca947d1a79d1394cd845a92e18109dd1","source":{"kind":"arxiv","id":"2306.13229","version":3},"attestation_state":"computed","paper":{"title":"TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Furong Huang, Hal Daum\\'e III, Huazhe Xu, Jieyu Zhao, Ruijie Zheng, Shuang Ma, Xiyao Wang, Yanchao Sun","submitted_at":"2023-06-22T22:21:53Z","abstract_excerpt":"Despite recent progress in reinforcement learning (RL) from raw pixel data, sample inefficiency continues to present a substantial obstacle. Prior works have attempted to address this challenge by creating self-supervised auxiliary tasks, aiming to enrich the agent's learned representations with control-relevant information for future state prediction. However, these objectives are often insufficient to learn representations that can represent the optimal policy or value function, and they often consider tasks with small, abstract discrete action spaces and thus overlook the importance of acti"},"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":"2306.13229","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-22T22:21:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"accd847416318dc1d051b116f25949af1be340327492e1f39799fd7228bd873f","abstract_canon_sha256":"b29ff36b87188c8cb2d972de65f2c9ec55e927eaaa986a50b5f7fbb05715212f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:32.194114Z","signature_b64":"Mh2iCqOvuopMGRaXqfwjY0DSGRA5RBw519dYdDd59QEnAEA8gY5PBeEx6vTpNADdBfJBpuEEv0oPpacvIpQzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"709bdc126d2e91c6403808088fef9814ca947d1a79d1394cd845a92e18109dd1","last_reissued_at":"2026-07-05T08:22:32.193579Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:32.193579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Furong Huang, Hal Daum\\'e III, Huazhe Xu, Jieyu Zhao, Ruijie Zheng, Shuang Ma, Xiyao Wang, Yanchao Sun","submitted_at":"2023-06-22T22:21:53Z","abstract_excerpt":"Despite recent progress in reinforcement learning (RL) from raw pixel data, sample inefficiency continues to present a substantial obstacle. Prior works have attempted to address this challenge by creating self-supervised auxiliary tasks, aiming to enrich the agent's learned representations with control-relevant information for future state prediction. However, these objectives are often insufficient to learn representations that can represent the optimal policy or value function, and they often consider tasks with small, abstract discrete action spaces and thus overlook the importance of acti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.13229","kind":"arxiv","version":3},"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/2306.13229/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":"2306.13229","created_at":"2026-07-05T08:22:32.193642+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.13229v3","created_at":"2026-07-05T08:22:32.193642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.13229","created_at":"2026-07-05T08:22:32.193642+00:00"},{"alias_kind":"pith_short_12","alias_value":"OCN5YETNF2I4","created_at":"2026-07-05T08:22:32.193642+00:00"},{"alias_kind":"pith_short_16","alias_value":"OCN5YETNF2I4MQBY","created_at":"2026-07-05T08:22:32.193642+00:00"},{"alias_kind":"pith_short_8","alias_value":"OCN5YETN","created_at":"2026-07-05T08:22:32.193642+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.02635","citing_title":"Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OCN5YETNF2I4MQBYBAEI734YCT","json":"https://pith.science/pith/OCN5YETNF2I4MQBYBAEI734YCT.json","graph_json":"https://pith.science/api/pith-number/OCN5YETNF2I4MQBYBAEI734YCT/graph.json","events_json":"https://pith.science/api/pith-number/OCN5YETNF2I4MQBYBAEI734YCT/events.json","paper":"https://pith.science/paper/OCN5YETN"},"agent_actions":{"view_html":"https://pith.science/pith/OCN5YETNF2I4MQBYBAEI734YCT","download_json":"https://pith.science/pith/OCN5YETNF2I4MQBYBAEI734YCT.json","view_paper":"https://pith.science/paper/OCN5YETN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.13229&json=true","fetch_graph":"https://pith.science/api/pith-number/OCN5YETNF2I4MQBYBAEI734YCT/graph.json","fetch_events":"https://pith.science/api/pith-number/OCN5YETNF2I4MQBYBAEI734YCT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OCN5YETNF2I4MQBYBAEI734YCT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OCN5YETNF2I4MQBYBAEI734YCT/action/storage_attestation","attest_author":"https://pith.science/pith/OCN5YETNF2I4MQBYBAEI734YCT/action/author_attestation","sign_citation":"https://pith.science/pith/OCN5YETNF2I4MQBYBAEI734YCT/action/citation_signature","submit_replication":"https://pith.science/pith/OCN5YETNF2I4MQBYBAEI734YCT/action/replication_record"}},"created_at":"2026-07-05T08:22:32.193642+00:00","updated_at":"2026-07-05T08:22:32.193642+00:00"}