{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:URPWUHZVOFF6RSUAANAZHPWBSE","short_pith_number":"pith:URPWUHZV","canonical_record":{"source":{"id":"2112.11622","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-22T02:01:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"debdb9a957ba1b07d4cb70ddc14cfc384afbfd79d2e67918cf9a89b2492410e4","abstract_canon_sha256":"df817db19319e48b1ca85f77e6c09a189eec9adf10820e85576ea8f14a075f2b"},"schema_version":"1.0"},"canonical_sha256":"a45f6a1f35714be8ca80034193bec1910efef2b0d1a9ebc85a741fad99959791","source":{"kind":"arxiv","id":"2112.11622","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.11622","created_at":"2026-07-05T03:59:43Z"},{"alias_kind":"arxiv_version","alias_value":"2112.11622v2","created_at":"2026-07-05T03:59:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.11622","created_at":"2026-07-05T03:59:43Z"},{"alias_kind":"pith_short_12","alias_value":"URPWUHZVOFF6","created_at":"2026-07-05T03:59:43Z"},{"alias_kind":"pith_short_16","alias_value":"URPWUHZVOFF6RSUA","created_at":"2026-07-05T03:59:43Z"},{"alias_kind":"pith_short_8","alias_value":"URPWUHZV","created_at":"2026-07-05T03:59:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:URPWUHZVOFF6RSUAANAZHPWBSE","target":"record","payload":{"canonical_record":{"source":{"id":"2112.11622","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-22T02:01:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"debdb9a957ba1b07d4cb70ddc14cfc384afbfd79d2e67918cf9a89b2492410e4","abstract_canon_sha256":"df817db19319e48b1ca85f77e6c09a189eec9adf10820e85576ea8f14a075f2b"},"schema_version":"1.0"},"canonical_sha256":"a45f6a1f35714be8ca80034193bec1910efef2b0d1a9ebc85a741fad99959791","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:59:43.402141Z","signature_b64":"gTANUZ1RPzqnUjYf+n5JLT4zeuuOMfnZCtvCKpIf5BZyHddffb8TecujS+wJNrjBLqwL5QJsAZ8fU7reMqfJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a45f6a1f35714be8ca80034193bec1910efef2b0d1a9ebc85a741fad99959791","last_reissued_at":"2026-07-05T03:59:43.401673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:59:43.401673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.11622","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":"2026-07-05T03:59:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NG7Io4pMfY3nKrkD+gPKdkBdrhY0S69Vj3tgMIjeu01A31kIwC9JE36dAwqr0F1hX8kEhdCARb7txbUxfYMqBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T10:13:29.268457Z"},"content_sha256":"a977c64537b1015d6a88533225f9322cb4205fd326ca64970d465c722eaa2ac4","schema_version":"1.0","event_id":"sha256:a977c64537b1015d6a88533225f9322cb4205fd326ca64970d465c722eaa2ac4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:URPWUHZVOFF6RSUAANAZHPWBSE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Alternate Policy Gradient Estimator for Softmax Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"A. Rupam Mahmood, Martha White, Samuele Tosatto, Shivam Garg, Yangchen Pan","submitted_at":"2021-12-22T02:01:19Z","abstract_excerpt":"Policy gradient (PG) estimators are ineffective in dealing with softmax policies that are sub-optimally saturated, which refers to the situation when the policy concentrates its probability mass on sub-optimal actions. Sub-optimal policy saturation may arise from bad policy initialization or sudden changes in the environment that occur after the policy has already converged. Current softmax PG estimators require a large number of updates to overcome policy saturation, which causes low sample efficiency and poor adaptability to new situations. To mitigate this problem, we propose a novel PG est"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.11622","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/2112.11622/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":"2026-07-05T03:59:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fxYd8B4PRsL/sOdGxIDnabLcHHngiAiNKDisOPT9ovxvhIybc2/+0bKN0DQdwG6afmANdSqqZYZpKuPDE+QYDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T10:13:29.268940Z"},"content_sha256":"ac101bdfce80812cd2eef1c6eb5cc6ea7ae820e39dd662366b34efa61d1aecc9","schema_version":"1.0","event_id":"sha256:ac101bdfce80812cd2eef1c6eb5cc6ea7ae820e39dd662366b34efa61d1aecc9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/URPWUHZVOFF6RSUAANAZHPWBSE/bundle.json","state_url":"https://pith.science/pith/URPWUHZVOFF6RSUAANAZHPWBSE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/URPWUHZVOFF6RSUAANAZHPWBSE/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":"2026-08-20T10:13:29Z","links":{"resolver":"https://pith.science/pith/URPWUHZVOFF6RSUAANAZHPWBSE","bundle":"https://pith.science/pith/URPWUHZVOFF6RSUAANAZHPWBSE/bundle.json","state":"https://pith.science/pith/URPWUHZVOFF6RSUAANAZHPWBSE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/URPWUHZVOFF6RSUAANAZHPWBSE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:URPWUHZVOFF6RSUAANAZHPWBSE","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":"df817db19319e48b1ca85f77e6c09a189eec9adf10820e85576ea8f14a075f2b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-22T02:01:19Z","title_canon_sha256":"debdb9a957ba1b07d4cb70ddc14cfc384afbfd79d2e67918cf9a89b2492410e4"},"schema_version":"1.0","source":{"id":"2112.11622","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.11622","created_at":"2026-07-05T03:59:43Z"},{"alias_kind":"arxiv_version","alias_value":"2112.11622v2","created_at":"2026-07-05T03:59:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.11622","created_at":"2026-07-05T03:59:43Z"},{"alias_kind":"pith_short_12","alias_value":"URPWUHZVOFF6","created_at":"2026-07-05T03:59:43Z"},{"alias_kind":"pith_short_16","alias_value":"URPWUHZVOFF6RSUA","created_at":"2026-07-05T03:59:43Z"},{"alias_kind":"pith_short_8","alias_value":"URPWUHZV","created_at":"2026-07-05T03:59:43Z"}],"graph_snapshots":[{"event_id":"sha256:ac101bdfce80812cd2eef1c6eb5cc6ea7ae820e39dd662366b34efa61d1aecc9","target":"graph","created_at":"2026-07-05T03:59:43Z","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/2112.11622/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy gradient (PG) estimators are ineffective in dealing with softmax policies that are sub-optimally saturated, which refers to the situation when the policy concentrates its probability mass on sub-optimal actions. Sub-optimal policy saturation may arise from bad policy initialization or sudden changes in the environment that occur after the policy has already converged. Current softmax PG estimators require a large number of updates to overcome policy saturation, which causes low sample efficiency and poor adaptability to new situations. To mitigate this problem, we propose a novel PG est","authors_text":"A. Rupam Mahmood, Martha White, Samuele Tosatto, Shivam Garg, Yangchen Pan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-22T02:01:19Z","title":"An Alternate Policy Gradient Estimator for Softmax Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.11622","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:a977c64537b1015d6a88533225f9322cb4205fd326ca64970d465c722eaa2ac4","target":"record","created_at":"2026-07-05T03:59:43Z","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":"df817db19319e48b1ca85f77e6c09a189eec9adf10820e85576ea8f14a075f2b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-22T02:01:19Z","title_canon_sha256":"debdb9a957ba1b07d4cb70ddc14cfc384afbfd79d2e67918cf9a89b2492410e4"},"schema_version":"1.0","source":{"id":"2112.11622","kind":"arxiv","version":2}},"canonical_sha256":"a45f6a1f35714be8ca80034193bec1910efef2b0d1a9ebc85a741fad99959791","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a45f6a1f35714be8ca80034193bec1910efef2b0d1a9ebc85a741fad99959791","first_computed_at":"2026-07-05T03:59:43.401673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:59:43.401673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gTANUZ1RPzqnUjYf+n5JLT4zeuuOMfnZCtvCKpIf5BZyHddffb8TecujS+wJNrjBLqwL5QJsAZ8fU7reMqfJBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:59:43.402141Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.11622","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a977c64537b1015d6a88533225f9322cb4205fd326ca64970d465c722eaa2ac4","sha256:ac101bdfce80812cd2eef1c6eb5cc6ea7ae820e39dd662366b34efa61d1aecc9"],"state_sha256":"d70c14ec3dfac771781f6d696b7ebefc8946a43a9998c921183cd0944fd77da6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jlk3NbwxDlAgaaAr0PQKVJ7YUnJTp8mrSjEKq3jGrfjA1mNRXruotDVWnp3kLCut2M8jGUMEcf4nG8xzwYnlBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T10:13:29.272548Z","bundle_sha256":"da01a677ba34e154f2916f361490592f271868022568bfd47a9f0e411b2c799a"}}