{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_6eaad97814bc7ab0226d4cc9a4d04963af3e0e960a979040496114f53341dda3","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_6eaad97814bc7ab0226d4cc9a4d04963af3e0e960a979040496114f53341dda3","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"1debf3ba4643af44ae1f9e49fbb03e1b8426224a21459930a736d8ff1595b93f","published":"Thu, 09 Jul 2026 00:00:00 -0400","receipt_hash":"1debf3ba4643af44ae1f9e49fbb03e1b8426224a21459930a736d8ff1595b93f","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"1debf3ba4643af44ae1f9e49fbb03e1b8426224a21459930a736d8ff1595b93f","observed_at":"2026-07-09T04:43:38.345231Z","parent_run_hash":"3e22c7c40abc4d94232acf1766a43492b8b8d51d10a58f1109535988a16554e6","published":"Thu, 09 Jul 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2602.11399v2 Announce Type: replace-cross \nAbstract: As unsupervised pretraining becomes increasingly ubiquitous in reinforcement learning, a more thorough theoretical understanding of these methods becomes of equal importance to their empirical success. We focus on the setting of unsupervised learning via interaction, where the forward-backward (FB) representation learning serves as a prototypical and popular example. In this paper, we shed light on FB by formally contextualizing the method within a broader class of recent methods that use regression to obtain a low-rank approximation of a successor measure ratio. Our analysis clarifies when FB representations can exist and how the low-rank approximation converges in practice. Building upon the theory, we propose a variant of FB that is both more amenable to theoretical understanding and simpler to optimize in practice. Experiments in didactic settings, as well as in $10$ state-based and image-based continuous control domains, d","title":"Can We Really Learn One Representation to Optimize All Rewards?","url":"https://arxiv.org/abs/2602.11399","vendor":"arxiv_cs_ai"},"summary":"arXiv:2602.11399v2 Announce Type: replace-cross \nAbstract: As unsupervised pretraining becomes increasingly ubiquitous in reinforcement learning, a more thorough theoretical understanding of these methods becomes of equal importance to their empirical success. We focus on the setting of unsupervised learning via interaction, where the forward-backward (FB) representation learning serves as a prototypical and popular example. In this paper, we shed light on FB by formally contextualizing the method within a broader class of recent methods that use regression to obtain a low-rank approximation of a successor measure ratio. Our analysis clarifies when FB representations can exist and how the low-rank approximation converges in practice. Building upon the theory, we propose a variant of FB that is both more amenable to theoretical understanding and simpler to optimize in practice. Experiments in didactic settings, as well as in $10$ state-based and image-based continuous control domains, d","title":"Can We Really Learn One Representation to Optimize All Rewards?","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-09T04:43:38Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2602.11399"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:6e1847a33ecc62f1482981473fb53ed36eab178a56ef7cbedfc1d36538a8ebe1e8a8d7c3fcc4c54303060ed847744a6d11ca5fd5f3a60dcc1bcf4e3d06b65c0c","signer":"crovia.substrate","subject":{"observed_at":"2026-07-09T04:43:38Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2602.11399"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"329e4ea05775196fea8a806155e22232f3a6ba8870fe081b1e94b6c4b1eebe38","leaf_index":296200,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"557d0cd0259c0922f2e05304d295d0b1f2e927c5e0f972f3e5c54c01bd729bf8","side":"right"},{"sibling":"861c3fc4d5fd18164591f20a09594478736b24630ba697bdd00ca2d57dece5d9","side":"right"},{"sibling":"464973ded3cb2213df92e594b5307bf4d15265c5851deb9c909027ef3e0d279e","side":"right"},{"sibling":"9902e0b5a9fdfd298a145d679b1b9fdd41d4a0ec721bb9e8701307cedaa30e7e","side":"left"},{"sibling":"dde79360e10599351071fbdcee52966463363049eaa0337ebc84d617378d0b4d","side":"right"},{"sibling":"ace5a3f2050e78da7dd2955ab530824f2a9340695d4197907b0a394fdec55cff","side":"right"},{"sibling":"c1193f457d0e7dce4ce89a015613466e62a77899d32cead956eebabef151ea39","side":"right"},{"sibling":"eecf5c0fb9ff7f19cf2016a2e611cc319e1bc910d0ece4f3db0063057b173a3a","side":"right"},{"sibling":"5bce7a29b5c407f5c9394caba7039b9f154bb72c56823211779a518e91e5dca7","side":"left"},{"sibling":"92bb57de69c78fd32ac7108b10d81676c184265a5a53de3c4b22d8cf3b54b499","side":"right"},{"sibling":"85a226efd14acc17835b04bc26706fa44595edbd531f194faf59f60ab72d4bb8","side":"left"},{"sibling":"da38b05536b12aee196b6ac988739211c257d32da790faccf5ac4b0cbc1bb15c","side":"right"},{"sibling":"d438dc3eddb0b14dc8b97cd021a4f44545ce5a8e827f3ea4044fd32b1877475e","side":"right"},{"sibling":"f73ad10346837ae47f59f0647f79b9416e1d499bf2b90af44448e7f09372200a","side":"right"},{"sibling":"bdc09902fcd434c0f7d3e680bf550e560777228c0b085ce80c637ce97fc4104c","side":"right"},{"sibling":"d8b9143917b539c543cf4448cec00131f8b807bd8004979c54ebe09798748c66","side":"left"},{"sibling":"ba603dffe985ef518e3a72793a3eaca83a7f1a79e5491fd0f62f421339f2d137","side":"right"},{"sibling":"be20b90931f0a14e3558ea4387537200fcbd14e019b3c5ed07a2ae4c62fc7c42","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":296360,"merkle_root":"64af62f723a5bc02adfa98b77e2006fc634de4ebf68626694f052342a200bea2","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260709T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-09T05:38:18Z","sig_algorithm":"ed25519","signature":"92ece7411e0d82898aac164e7d6573a6d0f7a595aad0780d710d873e548a061d2a8678cef4d237d3bf0eabe0a5f766b41cbc0b4bada2801e7532026291b4a309","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_6eaad97814bc7ab0226d4cc9a4d04963af3e0e960a979040496114f53341dda3"}}