{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TDM4CSZ2MAND5JWKYETSJ3IXMO","short_pith_number":"pith:TDM4CSZ2","canonical_record":{"source":{"id":"2306.02451","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-04T19:47:46Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"135b4dbf5417342812431b8019a46e25d52a7e0c909dd1186fc886552d95ad6d","abstract_canon_sha256":"e98e56c9bfa2b93dd8a52069d87d735e77fd0ee4de9487c1e3862ee4435cafd2"},"schema_version":"1.0"},"canonical_sha256":"98d9c14b3a601a3ea6cac12724ed1763887d98f8335e304dba423b91d404db3c","source":{"kind":"arxiv","id":"2306.02451","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02451","created_at":"2026-07-05T07:08:58Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02451v2","created_at":"2026-07-05T07:08:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02451","created_at":"2026-07-05T07:08:58Z"},{"alias_kind":"pith_short_12","alias_value":"TDM4CSZ2MAND","created_at":"2026-07-05T07:08:58Z"},{"alias_kind":"pith_short_16","alias_value":"TDM4CSZ2MAND5JWK","created_at":"2026-07-05T07:08:58Z"},{"alias_kind":"pith_short_8","alias_value":"TDM4CSZ2","created_at":"2026-07-05T07:08:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TDM4CSZ2MAND5JWKYETSJ3IXMO","target":"record","payload":{"canonical_record":{"source":{"id":"2306.02451","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-04T19:47:46Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"135b4dbf5417342812431b8019a46e25d52a7e0c909dd1186fc886552d95ad6d","abstract_canon_sha256":"e98e56c9bfa2b93dd8a52069d87d735e77fd0ee4de9487c1e3862ee4435cafd2"},"schema_version":"1.0"},"canonical_sha256":"98d9c14b3a601a3ea6cac12724ed1763887d98f8335e304dba423b91d404db3c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:58.538863Z","signature_b64":"uNQ14ox9Uf50mhifvyly+HpHzPjBjmK0BtCrWm8NU5BGNvOKE+kYhfudouBgFNhEYrAAOhc4fUXErpKQh6q+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98d9c14b3a601a3ea6cac12724ed1763887d98f8335e304dba423b91d404db3c","last_reissued_at":"2026-07-05T07:08:58.538388Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:58.538388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.02451","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":"2026-07-05T07:08:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8aAfrrIRzVPSsYizF/PZhhGCTfifiYo6OtZgvOoK/yo02SPZ4jVKCHSJBKm9sSZPJ0UKYHYq+1FWnmlvr50AAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:13:04.786136Z"},"content_sha256":"74ca7006e844b69d3ff7c6e2348880319fe176abf511cf0de6567d7227ea031a","schema_version":"1.0","event_id":"sha256:74ca7006e844b69d3ff7c6e2348880319fe176abf511cf0de6567d7227ea031a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TDM4CSZ2MAND5JWKYETSJ3IXMO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Meger, Doina Precup, Edward J. Smith, Scott Fujimoto, Shixiang Shane Gu, Wei-Di Chang","submitted_at":"2023-06-04T19:47:46Z","abstract_excerpt":"In the field of reinforcement learning (RL), representation learning is a proven tool for complex image-based tasks, but is often overlooked for environments with low-level states, such as physical control problems. This paper introduces SALE, a novel approach for learning embeddings that model the nuanced interaction between state and action, enabling effective representation learning from low-level states. We extensively study the design space of these embeddings and highlight important design considerations. We integrate SALE and an adaptation of checkpoints for RL into TD3 to form the TD7 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02451","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/2306.02451/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":"2026-07-05T07:08:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JteWBF9yFOx9p5nJnMxtC28gvJqUOW/xkm5zHRXhlJY0+2EBkG8w0B2KhZzIN+ybXmHTzXwbJ2mnkiykDlXkCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:13:04.786527Z"},"content_sha256":"9e2b63ee164eb07fc37eb76f1f76f89508356f025d3d7d00de1452ff3dd9399f","schema_version":"1.0","event_id":"sha256:9e2b63ee164eb07fc37eb76f1f76f89508356f025d3d7d00de1452ff3dd9399f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TDM4CSZ2MAND5JWKYETSJ3IXMO/bundle.json","state_url":"https://pith.science/pith/TDM4CSZ2MAND5JWKYETSJ3IXMO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TDM4CSZ2MAND5JWKYETSJ3IXMO/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":"2026-08-06T18:13:04Z","links":{"resolver":"https://pith.science/pith/TDM4CSZ2MAND5JWKYETSJ3IXMO","bundle":"https://pith.science/pith/TDM4CSZ2MAND5JWKYETSJ3IXMO/bundle.json","state":"https://pith.science/pith/TDM4CSZ2MAND5JWKYETSJ3IXMO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TDM4CSZ2MAND5JWKYETSJ3IXMO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TDM4CSZ2MAND5JWKYETSJ3IXMO","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":"e98e56c9bfa2b93dd8a52069d87d735e77fd0ee4de9487c1e3862ee4435cafd2","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-04T19:47:46Z","title_canon_sha256":"135b4dbf5417342812431b8019a46e25d52a7e0c909dd1186fc886552d95ad6d"},"schema_version":"1.0","source":{"id":"2306.02451","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02451","created_at":"2026-07-05T07:08:58Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02451v2","created_at":"2026-07-05T07:08:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02451","created_at":"2026-07-05T07:08:58Z"},{"alias_kind":"pith_short_12","alias_value":"TDM4CSZ2MAND","created_at":"2026-07-05T07:08:58Z"},{"alias_kind":"pith_short_16","alias_value":"TDM4CSZ2MAND5JWK","created_at":"2026-07-05T07:08:58Z"},{"alias_kind":"pith_short_8","alias_value":"TDM4CSZ2","created_at":"2026-07-05T07:08:58Z"}],"graph_snapshots":[{"event_id":"sha256:9e2b63ee164eb07fc37eb76f1f76f89508356f025d3d7d00de1452ff3dd9399f","target":"graph","created_at":"2026-07-05T07:08:58Z","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/2306.02451/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the field of reinforcement learning (RL), representation learning is a proven tool for complex image-based tasks, but is often overlooked for environments with low-level states, such as physical control problems. This paper introduces SALE, a novel approach for learning embeddings that model the nuanced interaction between state and action, enabling effective representation learning from low-level states. We extensively study the design space of these embeddings and highlight important design considerations. We integrate SALE and an adaptation of checkpoints for RL into TD3 to form the TD7 ","authors_text":"David Meger, Doina Precup, Edward J. Smith, Scott Fujimoto, Shixiang Shane Gu, Wei-Di Chang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-04T19:47:46Z","title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02451","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":"sha256:74ca7006e844b69d3ff7c6e2348880319fe176abf511cf0de6567d7227ea031a","target":"record","created_at":"2026-07-05T07:08:58Z","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":"e98e56c9bfa2b93dd8a52069d87d735e77fd0ee4de9487c1e3862ee4435cafd2","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-04T19:47:46Z","title_canon_sha256":"135b4dbf5417342812431b8019a46e25d52a7e0c909dd1186fc886552d95ad6d"},"schema_version":"1.0","source":{"id":"2306.02451","kind":"arxiv","version":2}},"canonical_sha256":"98d9c14b3a601a3ea6cac12724ed1763887d98f8335e304dba423b91d404db3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98d9c14b3a601a3ea6cac12724ed1763887d98f8335e304dba423b91d404db3c","first_computed_at":"2026-07-05T07:08:58.538388Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:08:58.538388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uNQ14ox9Uf50mhifvyly+HpHzPjBjmK0BtCrWm8NU5BGNvOKE+kYhfudouBgFNhEYrAAOhc4fUXErpKQh6q+Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T07:08:58.538863Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.02451","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74ca7006e844b69d3ff7c6e2348880319fe176abf511cf0de6567d7227ea031a","sha256:9e2b63ee164eb07fc37eb76f1f76f89508356f025d3d7d00de1452ff3dd9399f"],"state_sha256":"7dd30c16ccd02e2853e10d79d6c179bda48c55adb365d5544c69c9af43c8d999"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T/pyafosjYwmD7HkeysAdm1KwL8F65p+QWhGTrBVouMh+oqSkgXpTcOpwzgEWB5vGDEdzWtCxhp+60hCNc99CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T18:13:04.789266Z","bundle_sha256":"26722bebd1ad11116c3c05178d99189a1c8e6128004c3fbbe9d67e871bc326c2"}}