{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZTTPSLJXNLFMRHOVQEC7ADDS4Z","short_pith_number":"pith:ZTTPSLJX","canonical_record":{"source":{"id":"2104.07361","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-15T10:37:38Z","cross_cats_sorted":[],"title_canon_sha256":"d29ac2276d2c25aa0e8c9bfc3cc90ca477eee79c36af2f79c223a763418bdb60","abstract_canon_sha256":"6144efbb040f19c754707d28747f9e4cdbc018d98d173e87035ee57179604072"},"schema_version":"1.0"},"canonical_sha256":"cce6f92d376acac89dd58105f00c72e66622109acfa8b20ce09f62404f241334","source":{"kind":"arxiv","id":"2104.07361","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.07361","created_at":"2026-07-05T04:27:05Z"},{"alias_kind":"arxiv_version","alias_value":"2104.07361v2","created_at":"2026-07-05T04:27:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.07361","created_at":"2026-07-05T04:27:05Z"},{"alias_kind":"pith_short_12","alias_value":"ZTTPSLJXNLFM","created_at":"2026-07-05T04:27:05Z"},{"alias_kind":"pith_short_16","alias_value":"ZTTPSLJXNLFMRHOV","created_at":"2026-07-05T04:27:05Z"},{"alias_kind":"pith_short_8","alias_value":"ZTTPSLJX","created_at":"2026-07-05T04:27:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZTTPSLJXNLFMRHOVQEC7ADDS4Z","target":"record","payload":{"canonical_record":{"source":{"id":"2104.07361","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-15T10:37:38Z","cross_cats_sorted":[],"title_canon_sha256":"d29ac2276d2c25aa0e8c9bfc3cc90ca477eee79c36af2f79c223a763418bdb60","abstract_canon_sha256":"6144efbb040f19c754707d28747f9e4cdbc018d98d173e87035ee57179604072"},"schema_version":"1.0"},"canonical_sha256":"cce6f92d376acac89dd58105f00c72e66622109acfa8b20ce09f62404f241334","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:05.323115Z","signature_b64":"FNmKkM93Tab+8WLhmKmfib3BT2rYSUEyUOmMDFkI8iA+iB0o7paeqYMTJGVoPS+tGjxbEi8LHVfjsHmss/waBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cce6f92d376acac89dd58105f00c72e66622109acfa8b20ce09f62404f241334","last_reissued_at":"2026-07-05T04:27:05.322710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:05.322710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.07361","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":"2026-07-05T04:27:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+oWi36wmSPXNLQgZ5A9AK4ab3QmkYs7odMlyEkU6jw7tlIuzGTEEvakvjb9SA9HZLW2hCkyUOcC07cnUWJGiAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:08:26.190400Z"},"content_sha256":"0f59ecc290ecf05e6318a542e6d57e085bbfc6f8585c06a6047ff7627637836c","schema_version":"1.0","event_id":"sha256:0f59ecc290ecf05e6318a542e6d57e085bbfc6f8585c06a6047ff7627637836c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZTTPSLJXNLFMRHOVQEC7ADDS4Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scale Invariant Monte Carlo under Linear Function Approximation with Curvature based step-size","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hemanta Makwana, Rahul Madhavan","submitted_at":"2021-04-15T10:37:38Z","abstract_excerpt":"We study the feature-scaled version of the Monte Carlo algorithm with linear function approximation. This algorithm converges to a scale-invariant solution, which is not unduly affected by states having feature vectors with large norms. The usual versions of the MCMC algorithm, obtained by minimizing the least-squares criterion, do not produce solutions that give equal importance to all states irrespective of feature-vector norm -- a requirement that may be critical in many reinforcement learning contexts. To speed up convergence in our algorithm, we introduce an adaptive step-size based on th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.07361","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/2104.07361/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":"2026-07-05T04:27:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SOKVPcuv1+tZ+F9DlMdk9rBKLbCLrO+ckdv8+WTpwtk9bocguIyUb1HvHsv2rw5gBo/Gs58srs4r8joRmwf+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:08:26.190774Z"},"content_sha256":"5643695f4227c2427b48f83501ad7f9db6933461ce63dd212ea708f2492b747e","schema_version":"1.0","event_id":"sha256:5643695f4227c2427b48f83501ad7f9db6933461ce63dd212ea708f2492b747e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZTTPSLJXNLFMRHOVQEC7ADDS4Z/bundle.json","state_url":"https://pith.science/pith/ZTTPSLJXNLFMRHOVQEC7ADDS4Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZTTPSLJXNLFMRHOVQEC7ADDS4Z/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":"2026-07-06T18:08:26Z","links":{"resolver":"https://pith.science/pith/ZTTPSLJXNLFMRHOVQEC7ADDS4Z","bundle":"https://pith.science/pith/ZTTPSLJXNLFMRHOVQEC7ADDS4Z/bundle.json","state":"https://pith.science/pith/ZTTPSLJXNLFMRHOVQEC7ADDS4Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZTTPSLJXNLFMRHOVQEC7ADDS4Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZTTPSLJXNLFMRHOVQEC7ADDS4Z","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":"6144efbb040f19c754707d28747f9e4cdbc018d98d173e87035ee57179604072","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-15T10:37:38Z","title_canon_sha256":"d29ac2276d2c25aa0e8c9bfc3cc90ca477eee79c36af2f79c223a763418bdb60"},"schema_version":"1.0","source":{"id":"2104.07361","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.07361","created_at":"2026-07-05T04:27:05Z"},{"alias_kind":"arxiv_version","alias_value":"2104.07361v2","created_at":"2026-07-05T04:27:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.07361","created_at":"2026-07-05T04:27:05Z"},{"alias_kind":"pith_short_12","alias_value":"ZTTPSLJXNLFM","created_at":"2026-07-05T04:27:05Z"},{"alias_kind":"pith_short_16","alias_value":"ZTTPSLJXNLFMRHOV","created_at":"2026-07-05T04:27:05Z"},{"alias_kind":"pith_short_8","alias_value":"ZTTPSLJX","created_at":"2026-07-05T04:27:05Z"}],"graph_snapshots":[{"event_id":"sha256:5643695f4227c2427b48f83501ad7f9db6933461ce63dd212ea708f2492b747e","target":"graph","created_at":"2026-07-05T04:27:05Z","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/2104.07361/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the feature-scaled version of the Monte Carlo algorithm with linear function approximation. This algorithm converges to a scale-invariant solution, which is not unduly affected by states having feature vectors with large norms. The usual versions of the MCMC algorithm, obtained by minimizing the least-squares criterion, do not produce solutions that give equal importance to all states irrespective of feature-vector norm -- a requirement that may be critical in many reinforcement learning contexts. To speed up convergence in our algorithm, we introduce an adaptive step-size based on th","authors_text":"Hemanta Makwana, Rahul Madhavan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-15T10:37:38Z","title":"Scale Invariant Monte Carlo under Linear Function Approximation with Curvature based step-size"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.07361","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":"sha256:0f59ecc290ecf05e6318a542e6d57e085bbfc6f8585c06a6047ff7627637836c","target":"record","created_at":"2026-07-05T04:27:05Z","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":"6144efbb040f19c754707d28747f9e4cdbc018d98d173e87035ee57179604072","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-15T10:37:38Z","title_canon_sha256":"d29ac2276d2c25aa0e8c9bfc3cc90ca477eee79c36af2f79c223a763418bdb60"},"schema_version":"1.0","source":{"id":"2104.07361","kind":"arxiv","version":2}},"canonical_sha256":"cce6f92d376acac89dd58105f00c72e66622109acfa8b20ce09f62404f241334","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cce6f92d376acac89dd58105f00c72e66622109acfa8b20ce09f62404f241334","first_computed_at":"2026-07-05T04:27:05.322710Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:27:05.322710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FNmKkM93Tab+8WLhmKmfib3BT2rYSUEyUOmMDFkI8iA+iB0o7paeqYMTJGVoPS+tGjxbEi8LHVfjsHmss/waBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:27:05.323115Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.07361","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f59ecc290ecf05e6318a542e6d57e085bbfc6f8585c06a6047ff7627637836c","sha256:5643695f4227c2427b48f83501ad7f9db6933461ce63dd212ea708f2492b747e"],"state_sha256":"3d7c26dee94e95fb2e3f5c7af3d873eff707e0110ae0312a6f36fc62a1ccab6d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"urmdck8LJDSu//Lh4dKG3vKINkdnJEvw7cLsp8635otJUBj71sFS2reakOPwlPeGPsR+Rve+Rxd+3Zhy6VZdCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:08:26.192887Z","bundle_sha256":"ec36f68458fae6462dbc9bd9f83c6c02f996257657b1fe3338995f833accd70e"}}