{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:VFZBUFXXAJR72E3RYZITDDXM4Y","short_pith_number":"pith:VFZBUFXX","canonical_record":{"source":{"id":"1903.03252","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-08T02:29:22Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d9900037dc3ddd2b4afb70667fba1a0c6766232537e83ea881d92d87d7b6485e","abstract_canon_sha256":"19b71aba55e35e001cba556b02d3d73d28e66adb181ac66a435ebe5ffb670da7"},"schema_version":"1.0"},"canonical_sha256":"a9721a16f70263fd1371c651318eece60d268b297aac6fb1f8d03efb1962e792","source":{"kind":"arxiv","id":"1903.03252","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.03252","created_at":"2026-05-17T23:51:46Z"},{"alias_kind":"arxiv_version","alias_value":"1903.03252v1","created_at":"2026-05-17T23:51:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.03252","created_at":"2026-05-17T23:51:46Z"},{"alias_kind":"pith_short_12","alias_value":"VFZBUFXXAJR7","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"VFZBUFXXAJR72E3R","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"VFZBUFXX","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:VFZBUFXXAJR72E3RYZITDDXM4Y","target":"record","payload":{"canonical_record":{"source":{"id":"1903.03252","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-08T02:29:22Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d9900037dc3ddd2b4afb70667fba1a0c6766232537e83ea881d92d87d7b6485e","abstract_canon_sha256":"19b71aba55e35e001cba556b02d3d73d28e66adb181ac66a435ebe5ffb670da7"},"schema_version":"1.0"},"canonical_sha256":"a9721a16f70263fd1371c651318eece60d268b297aac6fb1f8d03efb1962e792","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:46.071063Z","signature_b64":"n/5723NdnCVBADiKjkmgnwFa8JtaBzEYBFLNb/+xuoo4dDUHkJBTFIIxlcxKCunynDK7klPo/LrqHTCBjTztCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9721a16f70263fd1371c651318eece60d268b297aac6fb1f8d03efb1962e792","last_reissued_at":"2026-05-17T23:51:46.070394Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:46.070394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.03252","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8GFmwA3ttxhwhofDvEDHCMGa1uw37g51Y7cN5c1bRY/c5b4nkB5SS/r/GolHBOuza55bvAndIuKDsIu8FtxJAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T19:25:44.690538Z"},"content_sha256":"c2c4b706d35e9643a9a36313467d27414fbd8f392e99214d11153766de905708","schema_version":"1.0","event_id":"sha256:c2c4b706d35e9643a9a36313467d27414fbd8f392e99214d11153766de905708"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:VFZBUFXXAJR72E3RYZITDDXM4Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Feature Relevance Through Step Size Adaptation in Temporal-Difference Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Kearney, Jaden Travnik, Patrick M. Pilarski, Richard S. Sutton, Vivek Veeriah","submitted_at":"2019-03-08T02:29:22Z","abstract_excerpt":"There is a long history of using meta learning as representation learning, specifically for determining the relevance of inputs. In this paper, we examine an instance of meta-learning in which feature relevance is learned by adapting step size parameters of stochastic gradient descent---building on a variety of prior work in stochastic approximation, machine learning, and artificial neural networks. In particular, we focus on stochastic meta-descent introduced in the Incremental Delta-Bar-Delta (IDBD) algorithm for setting individual step sizes for each feature of a linear function approximato"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.03252","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":""},"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":"2026-05-17T23:51:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dRjqKwEMv8+pu5/LMK8xo8yBtF4ETczlC8u3qVCTCzgRM64i09YYNiRg9ArnsU5eqkOh3k9zazwaRKEwFLWqCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T19:25:44.691418Z"},"content_sha256":"77eb39e9835f5b9c69b8ff2114fdd0114ec22e24a649227693dbb07f8cc81fd3","schema_version":"1.0","event_id":"sha256:77eb39e9835f5b9c69b8ff2114fdd0114ec22e24a649227693dbb07f8cc81fd3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VFZBUFXXAJR72E3RYZITDDXM4Y/bundle.json","state_url":"https://pith.science/pith/VFZBUFXXAJR72E3RYZITDDXM4Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VFZBUFXXAJR72E3RYZITDDXM4Y/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":"2026-05-31T19:25:44Z","links":{"resolver":"https://pith.science/pith/VFZBUFXXAJR72E3RYZITDDXM4Y","bundle":"https://pith.science/pith/VFZBUFXXAJR72E3RYZITDDXM4Y/bundle.json","state":"https://pith.science/pith/VFZBUFXXAJR72E3RYZITDDXM4Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VFZBUFXXAJR72E3RYZITDDXM4Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:VFZBUFXXAJR72E3RYZITDDXM4Y","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":"19b71aba55e35e001cba556b02d3d73d28e66adb181ac66a435ebe5ffb670da7","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-08T02:29:22Z","title_canon_sha256":"d9900037dc3ddd2b4afb70667fba1a0c6766232537e83ea881d92d87d7b6485e"},"schema_version":"1.0","source":{"id":"1903.03252","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.03252","created_at":"2026-05-17T23:51:46Z"},{"alias_kind":"arxiv_version","alias_value":"1903.03252v1","created_at":"2026-05-17T23:51:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.03252","created_at":"2026-05-17T23:51:46Z"},{"alias_kind":"pith_short_12","alias_value":"VFZBUFXXAJR7","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"VFZBUFXXAJR72E3R","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"VFZBUFXX","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:77eb39e9835f5b9c69b8ff2114fdd0114ec22e24a649227693dbb07f8cc81fd3","target":"graph","created_at":"2026-05-17T23:51:46Z","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"},"paper":{"abstract_excerpt":"There is a long history of using meta learning as representation learning, specifically for determining the relevance of inputs. In this paper, we examine an instance of meta-learning in which feature relevance is learned by adapting step size parameters of stochastic gradient descent---building on a variety of prior work in stochastic approximation, machine learning, and artificial neural networks. In particular, we focus on stochastic meta-descent introduced in the Incremental Delta-Bar-Delta (IDBD) algorithm for setting individual step sizes for each feature of a linear function approximato","authors_text":"Alex Kearney, Jaden Travnik, Patrick M. Pilarski, Richard S. Sutton, Vivek Veeriah","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-08T02:29:22Z","title":"Learning Feature Relevance Through Step Size Adaptation in Temporal-Difference Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.03252","kind":"arxiv","version":1},"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:c2c4b706d35e9643a9a36313467d27414fbd8f392e99214d11153766de905708","target":"record","created_at":"2026-05-17T23:51:46Z","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":"19b71aba55e35e001cba556b02d3d73d28e66adb181ac66a435ebe5ffb670da7","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-08T02:29:22Z","title_canon_sha256":"d9900037dc3ddd2b4afb70667fba1a0c6766232537e83ea881d92d87d7b6485e"},"schema_version":"1.0","source":{"id":"1903.03252","kind":"arxiv","version":1}},"canonical_sha256":"a9721a16f70263fd1371c651318eece60d268b297aac6fb1f8d03efb1962e792","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9721a16f70263fd1371c651318eece60d268b297aac6fb1f8d03efb1962e792","first_computed_at":"2026-05-17T23:51:46.070394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:46.070394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n/5723NdnCVBADiKjkmgnwFa8JtaBzEYBFLNb/+xuoo4dDUHkJBTFIIxlcxKCunynDK7klPo/LrqHTCBjTztCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:46.071063Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.03252","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2c4b706d35e9643a9a36313467d27414fbd8f392e99214d11153766de905708","sha256:77eb39e9835f5b9c69b8ff2114fdd0114ec22e24a649227693dbb07f8cc81fd3"],"state_sha256":"690564117731fb00b8adce2056b3a8adaade1305c15376ec004ef1b4286c5c5b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NNAAJ4W/X51g8YZ8bmRm9l7ytE6OcXoJzZP8TyNOYCtLUqkFNP4xW7wtubN2GPqFMN3sao6F8VdSj8Vb9Q9/AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T19:25:44.696712Z","bundle_sha256":"9454888f7e92fa1291db6b96225486c802ff1e21262270e73d08bb6112268fc5"}}