{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Y7W63XFCYIRXEHIIT27TSNTVU3","short_pith_number":"pith:Y7W63XFC","schema_version":"1.0","canonical_sha256":"c7ededdca2c223721d089ebf393675a6c6eb7623cdef4d18bea4d720b5f842b5","source":{"kind":"arxiv","id":"2607.00452","version":1},"attestation_state":"computed","paper":{"title":"Gauging, Measuring, and Controlling Critic Complexity in Actor-Critic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Konstantin Garbers","submitted_at":"2026-07-01T05:10:14Z","abstract_excerpt":"Actor-critic methods depend on learned critics, but critic quality is often evaluated only indirectly through return, temporal-difference error, or value loss. Critic complexity is introduced as an additional diagnostic and intervention dimension for actor-critic reinforcement learning. The analysis uses spectral effective-rank entropy, a rank-like summary of the singular-value distributions of critic weight matrices, to assess critic model complexity. Across TD3 and PPO experiments, critic complexity is tracked together with return and Monte Carlo value-estimation bias. The results show that "},"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":"2607.00452","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T05:10:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bb9707c7a3fe97e60f75fe917f4e2744393f4d9f0e9519569a21d7bb5cc37658","abstract_canon_sha256":"cf69469c705b6677a6314d15b65e174edc64d4b1a5f793e1bcdf65c806ef3247"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:17:43.790050Z","signature_b64":"VDwF7oa4kwA69YFyO4T9N/5RAreP2AhEzL+0EWS+iZdoqO0Fdm9jf6j1zEBEV/bKE0GwYMiY4GIKDT+ZGbSTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7ededdca2c223721d089ebf393675a6c6eb7623cdef4d18bea4d720b5f842b5","last_reissued_at":"2026-07-02T01:17:43.789646Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:17:43.789646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gauging, Measuring, and Controlling Critic Complexity in Actor-Critic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Konstantin Garbers","submitted_at":"2026-07-01T05:10:14Z","abstract_excerpt":"Actor-critic methods depend on learned critics, but critic quality is often evaluated only indirectly through return, temporal-difference error, or value loss. Critic complexity is introduced as an additional diagnostic and intervention dimension for actor-critic reinforcement learning. The analysis uses spectral effective-rank entropy, a rank-like summary of the singular-value distributions of critic weight matrices, to assess critic model complexity. Across TD3 and PPO experiments, critic complexity is tracked together with return and Monte Carlo value-estimation bias. The results show that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00452","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/2607.00452/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":"2607.00452","created_at":"2026-07-02T01:17:43.789711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00452v1","created_at":"2026-07-02T01:17:43.789711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00452","created_at":"2026-07-02T01:17:43.789711+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y7W63XFCYIRX","created_at":"2026-07-02T01:17:43.789711+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y7W63XFCYIRXEHII","created_at":"2026-07-02T01:17:43.789711+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y7W63XFC","created_at":"2026-07-02T01:17:43.789711+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y7W63XFCYIRXEHIIT27TSNTVU3","json":"https://pith.science/pith/Y7W63XFCYIRXEHIIT27TSNTVU3.json","graph_json":"https://pith.science/api/pith-number/Y7W63XFCYIRXEHIIT27TSNTVU3/graph.json","events_json":"https://pith.science/api/pith-number/Y7W63XFCYIRXEHIIT27TSNTVU3/events.json","paper":"https://pith.science/paper/Y7W63XFC"},"agent_actions":{"view_html":"https://pith.science/pith/Y7W63XFCYIRXEHIIT27TSNTVU3","download_json":"https://pith.science/pith/Y7W63XFCYIRXEHIIT27TSNTVU3.json","view_paper":"https://pith.science/paper/Y7W63XFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00452&json=true","fetch_graph":"https://pith.science/api/pith-number/Y7W63XFCYIRXEHIIT27TSNTVU3/graph.json","fetch_events":"https://pith.science/api/pith-number/Y7W63XFCYIRXEHIIT27TSNTVU3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y7W63XFCYIRXEHIIT27TSNTVU3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y7W63XFCYIRXEHIIT27TSNTVU3/action/storage_attestation","attest_author":"https://pith.science/pith/Y7W63XFCYIRXEHIIT27TSNTVU3/action/author_attestation","sign_citation":"https://pith.science/pith/Y7W63XFCYIRXEHIIT27TSNTVU3/action/citation_signature","submit_replication":"https://pith.science/pith/Y7W63XFCYIRXEHIIT27TSNTVU3/action/replication_record"}},"created_at":"2026-07-02T01:17:43.789711+00:00","updated_at":"2026-07-02T01:17:43.789711+00:00"}