{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:MKOVA43USPUPO3YFZ6RWIYTOCS","short_pith_number":"pith:MKOVA43U","canonical_record":{"source":{"id":"1906.09781","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-24T08:40:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6d396786a65a860d74ed74a87ecf17eba2ef8def4ea7851b37d822deffe9dfa1","abstract_canon_sha256":"168462a653e5a68379e3de9888ff39a812644bbf8a2c4c7a79eab4bed0b5a4f7"},"schema_version":"1.0"},"canonical_sha256":"629d50737493e8f76f05cfa364626e14b570f9d9bf39fdb2932b044396f71515","source":{"kind":"arxiv","id":"1906.09781","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.09781","created_at":"2026-05-17T23:42:36Z"},{"alias_kind":"arxiv_version","alias_value":"1906.09781v1","created_at":"2026-05-17T23:42:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09781","created_at":"2026-05-17T23:42:36Z"},{"alias_kind":"pith_short_12","alias_value":"MKOVA43USPUP","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"MKOVA43USPUPO3YF","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"MKOVA43U","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:MKOVA43USPUPO3YFZ6RWIYTOCS","target":"record","payload":{"canonical_record":{"source":{"id":"1906.09781","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-24T08:40:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6d396786a65a860d74ed74a87ecf17eba2ef8def4ea7851b37d822deffe9dfa1","abstract_canon_sha256":"168462a653e5a68379e3de9888ff39a812644bbf8a2c4c7a79eab4bed0b5a4f7"},"schema_version":"1.0"},"canonical_sha256":"629d50737493e8f76f05cfa364626e14b570f9d9bf39fdb2932b044396f71515","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:36.746517Z","signature_b64":"xhPbi9jBN/uX54VIJe7zJQH6zjzRVBCGzPZNr4TtUG48zaD1zWmP1ZZ2k3SradgogXuwxkZM6fzMokmHB8gxAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"629d50737493e8f76f05cfa364626e14b570f9d9bf39fdb2932b044396f71515","last_reissued_at":"2026-05-17T23:42:36.745914Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:36.745914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.09781","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":"2026-05-17T23:42:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SjAS41DGTSAh0u7JUK7qpdr4K07IbvYuAZiOHuAsPQcRI5qID6pmNMOXa5anIaEt81IX9y99ZsBquMrzqT1hCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:49:29.027815Z"},"content_sha256":"705702e966a0a3fdd786a7734c7b36d0bd6a84f3cb1635a87b6033c2718f01f5","schema_version":"1.0","event_id":"sha256:705702e966a0a3fdd786a7734c7b36d0bd6a84f3cb1635a87b6033c2718f01f5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:MKOVA43USPUPO3YFZ6RWIYTOCS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"In Hindsight: A Smooth Reward for Steady Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hadi S. Jomaa, Josif Grabocka, Lars Schmidt-Thieme","submitted_at":"2019-06-24T08:40:58Z","abstract_excerpt":"In classical Q-learning, the objective is to maximize the sum of discounted rewards through iteratively using the Bellman equation as an update, in an attempt to estimate the action value function of the optimal policy. Conventionally, the loss function is defined as the temporal difference between the action value and the expected (discounted) reward, however it focuses solely on the future, leading to overestimation errors. We extend the well-established Q-learning techniques by introducing the hindsight factor, an additional loss term that takes into account how the model progresses, by int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09781","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":"2026-05-17T23:42:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o683UvSXannWsZWfLkxp0emZWyyt0mt48tEraMrVH81VCOaa6JxSltkNkFSaYYnPtlm0EaXOiOVm7yJliwpSDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:49:29.028205Z"},"content_sha256":"a2d590f2ce71786c202b0c88fe2d839fba8e9389b87c02658418e12b3da68354","schema_version":"1.0","event_id":"sha256:a2d590f2ce71786c202b0c88fe2d839fba8e9389b87c02658418e12b3da68354"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MKOVA43USPUPO3YFZ6RWIYTOCS/bundle.json","state_url":"https://pith.science/pith/MKOVA43USPUPO3YFZ6RWIYTOCS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MKOVA43USPUPO3YFZ6RWIYTOCS/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":"2026-05-26T11:49:29Z","links":{"resolver":"https://pith.science/pith/MKOVA43USPUPO3YFZ6RWIYTOCS","bundle":"https://pith.science/pith/MKOVA43USPUPO3YFZ6RWIYTOCS/bundle.json","state":"https://pith.science/pith/MKOVA43USPUPO3YFZ6RWIYTOCS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MKOVA43USPUPO3YFZ6RWIYTOCS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:MKOVA43USPUPO3YFZ6RWIYTOCS","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":"168462a653e5a68379e3de9888ff39a812644bbf8a2c4c7a79eab4bed0b5a4f7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-24T08:40:58Z","title_canon_sha256":"6d396786a65a860d74ed74a87ecf17eba2ef8def4ea7851b37d822deffe9dfa1"},"schema_version":"1.0","source":{"id":"1906.09781","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.09781","created_at":"2026-05-17T23:42:36Z"},{"alias_kind":"arxiv_version","alias_value":"1906.09781v1","created_at":"2026-05-17T23:42:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09781","created_at":"2026-05-17T23:42:36Z"},{"alias_kind":"pith_short_12","alias_value":"MKOVA43USPUP","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"MKOVA43USPUPO3YF","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"MKOVA43U","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:a2d590f2ce71786c202b0c88fe2d839fba8e9389b87c02658418e12b3da68354","target":"graph","created_at":"2026-05-17T23:42:36Z","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":"In classical Q-learning, the objective is to maximize the sum of discounted rewards through iteratively using the Bellman equation as an update, in an attempt to estimate the action value function of the optimal policy. Conventionally, the loss function is defined as the temporal difference between the action value and the expected (discounted) reward, however it focuses solely on the future, leading to overestimation errors. We extend the well-established Q-learning techniques by introducing the hindsight factor, an additional loss term that takes into account how the model progresses, by int","authors_text":"Hadi S. Jomaa, Josif Grabocka, Lars Schmidt-Thieme","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-24T08:40:58Z","title":"In Hindsight: A Smooth Reward for Steady Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09781","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":"sha256:705702e966a0a3fdd786a7734c7b36d0bd6a84f3cb1635a87b6033c2718f01f5","target":"record","created_at":"2026-05-17T23:42:36Z","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":"168462a653e5a68379e3de9888ff39a812644bbf8a2c4c7a79eab4bed0b5a4f7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-24T08:40:58Z","title_canon_sha256":"6d396786a65a860d74ed74a87ecf17eba2ef8def4ea7851b37d822deffe9dfa1"},"schema_version":"1.0","source":{"id":"1906.09781","kind":"arxiv","version":1}},"canonical_sha256":"629d50737493e8f76f05cfa364626e14b570f9d9bf39fdb2932b044396f71515","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"629d50737493e8f76f05cfa364626e14b570f9d9bf39fdb2932b044396f71515","first_computed_at":"2026-05-17T23:42:36.745914Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:36.745914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xhPbi9jBN/uX54VIJe7zJQH6zjzRVBCGzPZNr4TtUG48zaD1zWmP1ZZ2k3SradgogXuwxkZM6fzMokmHB8gxAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:36.746517Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.09781","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:705702e966a0a3fdd786a7734c7b36d0bd6a84f3cb1635a87b6033c2718f01f5","sha256:a2d590f2ce71786c202b0c88fe2d839fba8e9389b87c02658418e12b3da68354"],"state_sha256":"2014ba35097394a749d64148c4253844bf646397e204f587f5741afd7e73a52b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZuyQLqrw7dVRJ9f5924KatUYyO2ceu04NyikvDYQwGyZJBapQKAfeKZGiCn1lWS0nHR+W3aYEj0UvjMQjxP1Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T11:49:29.030624Z","bundle_sha256":"6e2ac3196e09a837a7b1a6342811e1dfc624ccd9022329907b948dc9d12d0028"}}