{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZLUVBY7X3RIUVFP7IIY6ERV5TE","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":"bb22d7184e254517ce0d054372a9ab4c399918d71c0c2cb75a4b63804bcc9620","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-05T16:47:36Z","title_canon_sha256":"d85d09b85ea10b4ff3ea6932385c4d40a957da37436d6b1aaaa788e22b6130c5"},"schema_version":"1.0","source":{"id":"2503.03660","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.03660","created_at":"2026-06-08T01:03:43Z"},{"alias_kind":"arxiv_version","alias_value":"2503.03660v4","created_at":"2026-06-08T01:03:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03660","created_at":"2026-06-08T01:03:43Z"},{"alias_kind":"pith_short_12","alias_value":"ZLUVBY7X3RIU","created_at":"2026-06-08T01:03:43Z"},{"alias_kind":"pith_short_16","alias_value":"ZLUVBY7X3RIUVFP7","created_at":"2026-06-08T01:03:43Z"},{"alias_kind":"pith_short_8","alias_value":"ZLUVBY7X","created_at":"2026-06-08T01:03:43Z"}],"graph_snapshots":[{"event_id":"sha256:ae23502373e0cf9e52f9bc50e0cba417f446fbf30bb6fc9e8f0cd410ceb362ad","target":"graph","created_at":"2026-06-08T01:03:43Z","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/2503.03660/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a sequence-conditioned critic for Soft Actor-Critic (SAC) that models trajectory context with a lightweight Transformer and trains on aggregated $N$-step targets. Unlike prior approaches that (i) score state-action pairs in isolation or (ii) rely on actor-side action chunking to handle long horizons, our method strengthens the critic itself by conditioning on short trajectory segments and integrating multi-step returns -- without importance sampling (IS). The resulting sequence-aware value estimates capture the critical temporal structure for extended-horizon and sparse-reward pro","authors_text":"Dong Tian, Gerhard Neumann, Onur Celik","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-05T16:47:36Z","title":"Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03660","kind":"arxiv","version":4},"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:dbad271a763cd8b25e85fff441f69ab0ab0292f332ddab3e065215a907005593","target":"record","created_at":"2026-06-08T01:03:43Z","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":"bb22d7184e254517ce0d054372a9ab4c399918d71c0c2cb75a4b63804bcc9620","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-05T16:47:36Z","title_canon_sha256":"d85d09b85ea10b4ff3ea6932385c4d40a957da37436d6b1aaaa788e22b6130c5"},"schema_version":"1.0","source":{"id":"2503.03660","kind":"arxiv","version":4}},"canonical_sha256":"cae950e3f7dc514a95ff4231e246bd9929f93c9f12bd9c060e47a7305cd5a0f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cae950e3f7dc514a95ff4231e246bd9929f93c9f12bd9c060e47a7305cd5a0f4","first_computed_at":"2026-06-08T01:03:43.719115Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:03:43.719115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AUdINjTtq+Xs38tlRyDFgxbC9BfKhsDnBoe04xDe1sm9IkjsJaq2IEEh2St/JJpGVTqWiKeoqtAB/cxj5v90Bg==","signature_status":"signed_v1","signed_at":"2026-06-08T01:03:43.719998Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.03660","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbad271a763cd8b25e85fff441f69ab0ab0292f332ddab3e065215a907005593","sha256:ae23502373e0cf9e52f9bc50e0cba417f446fbf30bb6fc9e8f0cd410ceb362ad"],"state_sha256":"31e2c2735846e133028ab4dae0769a0d6817eb28dccd008026cf88f1af1569d9"}