{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EAFKGNHPQLGK4LH4U27TG6X2YN","short_pith_number":"pith:EAFKGNHP","canonical_record":{"source":{"id":"2306.17833","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-30T17:53:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"871e4ee19413dbd3276990b75cb13010e0abc99e617857a8fd9b6878e1153920","abstract_canon_sha256":"c09bf6d3dc60eea87875d17570901ec783f948eeaabddd8dc119e8c5d6166b1d"},"schema_version":"1.0"},"canonical_sha256":"200aa334ef82ccae2cfca6bf337afac34c6b281507b7bfb748d1a3cf8b5fca40","source":{"kind":"arxiv","id":"2306.17833","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.17833","created_at":"2026-07-05T07:12:51Z"},{"alias_kind":"arxiv_version","alias_value":"2306.17833v2","created_at":"2026-07-05T07:12:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17833","created_at":"2026-07-05T07:12:51Z"},{"alias_kind":"pith_short_12","alias_value":"EAFKGNHPQLGK","created_at":"2026-07-05T07:12:51Z"},{"alias_kind":"pith_short_16","alias_value":"EAFKGNHPQLGK4LH4","created_at":"2026-07-05T07:12:51Z"},{"alias_kind":"pith_short_8","alias_value":"EAFKGNHP","created_at":"2026-07-05T07:12:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EAFKGNHPQLGK4LH4U27TG6X2YN","target":"record","payload":{"canonical_record":{"source":{"id":"2306.17833","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-30T17:53:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"871e4ee19413dbd3276990b75cb13010e0abc99e617857a8fd9b6878e1153920","abstract_canon_sha256":"c09bf6d3dc60eea87875d17570901ec783f948eeaabddd8dc119e8c5d6166b1d"},"schema_version":"1.0"},"canonical_sha256":"200aa334ef82ccae2cfca6bf337afac34c6b281507b7bfb748d1a3cf8b5fca40","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:51.189549Z","signature_b64":"ZXqiNV4WSX5O8EUHSTRpZAJDSSRpYobLpmISxeijEMful/90L8Sw0ntFm3rBZvMKoa92KbihkM6yIJ8eHyN9Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"200aa334ef82ccae2cfca6bf337afac34c6b281507b7bfb748d1a3cf8b5fca40","last_reissued_at":"2026-07-05T07:12:51.189079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:51.189079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.17833","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":"2026-07-05T07:12:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CWzuOyyyh9LV69SjY+pUeQ+Dd/QkR1weudPLxK10UyYpFxmI+w4pW28VCIrELDmQdPhf+dj1WOQjV4zLNrrBCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T21:47:04.541027Z"},"content_sha256":"c09892fb7775084d4c0f67c51c1d66c412074d15cb66f53c219631f821079351","schema_version":"1.0","event_id":"sha256:c09892fb7775084d4c0f67c51c1d66c412074d15cb66f53c219631f821079351"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EAFKGNHPQLGK4LH4U27TG6X2YN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Resetting the Optimizer in Deep RL: An Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kavosh Asadi, Rasool Fakoor, Shoham Sabach","submitted_at":"2023-06-30T17:53:50Z","abstract_excerpt":"We focus on the task of approximating the optimal value function in deep reinforcement learning. This iterative process is comprised of solving a sequence of optimization problems where the loss function changes per iteration. The common approach to solving this sequence of problems is to employ modern variants of the stochastic gradient descent algorithm such as Adam. These optimizers maintain their own internal parameters such as estimates of the first-order and the second-order moments of the gradient, and update them over time. Therefore, information obtained in previous iterations is used"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17833","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/2306.17833/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":"2026-07-05T07:12:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VRFjcuXTWLb2mdq8J7OXUZmzaa//nECWaH1S+8laczXdWUlcrMtoUeD0HSyasy3rG89tph8ngaVfpCz+dT2VBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T21:47:04.541553Z"},"content_sha256":"316fd8982336661ccd20d474362934d48e0c2cd100ee9537a37dd9fb783c7a3d","schema_version":"1.0","event_id":"sha256:316fd8982336661ccd20d474362934d48e0c2cd100ee9537a37dd9fb783c7a3d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EAFKGNHPQLGK4LH4U27TG6X2YN/bundle.json","state_url":"https://pith.science/pith/EAFKGNHPQLGK4LH4U27TG6X2YN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EAFKGNHPQLGK4LH4U27TG6X2YN/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":"2026-08-05T21:47:04Z","links":{"resolver":"https://pith.science/pith/EAFKGNHPQLGK4LH4U27TG6X2YN","bundle":"https://pith.science/pith/EAFKGNHPQLGK4LH4U27TG6X2YN/bundle.json","state":"https://pith.science/pith/EAFKGNHPQLGK4LH4U27TG6X2YN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EAFKGNHPQLGK4LH4U27TG6X2YN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EAFKGNHPQLGK4LH4U27TG6X2YN","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":"c09bf6d3dc60eea87875d17570901ec783f948eeaabddd8dc119e8c5d6166b1d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-30T17:53:50Z","title_canon_sha256":"871e4ee19413dbd3276990b75cb13010e0abc99e617857a8fd9b6878e1153920"},"schema_version":"1.0","source":{"id":"2306.17833","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.17833","created_at":"2026-07-05T07:12:51Z"},{"alias_kind":"arxiv_version","alias_value":"2306.17833v2","created_at":"2026-07-05T07:12:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17833","created_at":"2026-07-05T07:12:51Z"},{"alias_kind":"pith_short_12","alias_value":"EAFKGNHPQLGK","created_at":"2026-07-05T07:12:51Z"},{"alias_kind":"pith_short_16","alias_value":"EAFKGNHPQLGK4LH4","created_at":"2026-07-05T07:12:51Z"},{"alias_kind":"pith_short_8","alias_value":"EAFKGNHP","created_at":"2026-07-05T07:12:51Z"}],"graph_snapshots":[{"event_id":"sha256:316fd8982336661ccd20d474362934d48e0c2cd100ee9537a37dd9fb783c7a3d","target":"graph","created_at":"2026-07-05T07:12:51Z","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/2306.17833/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We focus on the task of approximating the optimal value function in deep reinforcement learning. This iterative process is comprised of solving a sequence of optimization problems where the loss function changes per iteration. The common approach to solving this sequence of problems is to employ modern variants of the stochastic gradient descent algorithm such as Adam. These optimizers maintain their own internal parameters such as estimates of the first-order and the second-order moments of the gradient, and update them over time. Therefore, information obtained in previous iterations is used","authors_text":"Kavosh Asadi, Rasool Fakoor, Shoham Sabach","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-30T17:53:50Z","title":"Resetting the Optimizer in Deep RL: An Empirical Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17833","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:c09892fb7775084d4c0f67c51c1d66c412074d15cb66f53c219631f821079351","target":"record","created_at":"2026-07-05T07:12:51Z","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":"c09bf6d3dc60eea87875d17570901ec783f948eeaabddd8dc119e8c5d6166b1d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-30T17:53:50Z","title_canon_sha256":"871e4ee19413dbd3276990b75cb13010e0abc99e617857a8fd9b6878e1153920"},"schema_version":"1.0","source":{"id":"2306.17833","kind":"arxiv","version":2}},"canonical_sha256":"200aa334ef82ccae2cfca6bf337afac34c6b281507b7bfb748d1a3cf8b5fca40","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"200aa334ef82ccae2cfca6bf337afac34c6b281507b7bfb748d1a3cf8b5fca40","first_computed_at":"2026-07-05T07:12:51.189079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:12:51.189079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZXqiNV4WSX5O8EUHSTRpZAJDSSRpYobLpmISxeijEMful/90L8Sw0ntFm3rBZvMKoa92KbihkM6yIJ8eHyN9Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:12:51.189549Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.17833","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c09892fb7775084d4c0f67c51c1d66c412074d15cb66f53c219631f821079351","sha256:316fd8982336661ccd20d474362934d48e0c2cd100ee9537a37dd9fb783c7a3d"],"state_sha256":"5568e3736ad89bdb1ae373a02b61ebf8d47f2f2201aa9096d7821c9fa091fabe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9m7domrpxOvLRUTceYNlWxFQS1lI6wyS2XMZo2NknLBJ3b4BCXJ0LSxXtvwP8fU7WmKwa8tZKFY3Vcwf7mh5CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T21:47:04.546411Z","bundle_sha256":"30b6a610e5aa4bff0f072f4516d52ddc31b4d976540665ff01e85a635968fbfa"}}