{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:66O2HSY5ANSHHPJDM4HDXPPZLN","short_pith_number":"pith:66O2HSY5","schema_version":"1.0","canonical_sha256":"f79da3cb1d036473bd23670e3bbdf95b51dc71fdfd9ac3f53331248cc36c19bd","source":{"kind":"arxiv","id":"2307.11897","version":2},"attestation_state":"computed","paper":{"title":"Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Akash Velu, Dilip Arumugam, Skanda Vaidyanath","submitted_at":"2023-07-21T20:54:52Z","abstract_excerpt":"Oftentimes, environments for sequential decision-making problems can be quite sparse in the provision of evaluative feedback to guide reinforcement-learning agents. In the extreme case, long trajectories of behavior are merely punctuated with a single terminal feedback signal, leading to a significant temporal delay between the observation of a non-trivial reward and the individual steps of behavior culpable for achieving said reward. Coping with such a credit assignment challenge is one of the hallmark characteristics of reinforcement learning. While prior work has introduced the concept of h"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2307.11897","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-21T20:54:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8c9581831fb876f31f0cb5d045a05cdfb23c32640629aad36616b311f068c209","abstract_canon_sha256":"8cb277e0d92994cdbb25c9cb423a139db821117e21a51c01843f25084d0848d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:44.537425Z","signature_b64":"R0cuN8BsQ97HJYV15CoqGDSpIpBj8gEZ6BlaColraVyba1s6dIWnQnwc320fCNDp9F6E1aFnxRanT/SvT+cJDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f79da3cb1d036473bd23670e3bbdf95b51dc71fdfd9ac3f53331248cc36c19bd","last_reissued_at":"2026-07-05T06:42:44.536985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:44.536985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Akash Velu, Dilip Arumugam, Skanda Vaidyanath","submitted_at":"2023-07-21T20:54:52Z","abstract_excerpt":"Oftentimes, environments for sequential decision-making problems can be quite sparse in the provision of evaluative feedback to guide reinforcement-learning agents. In the extreme case, long trajectories of behavior are merely punctuated with a single terminal feedback signal, leading to a significant temporal delay between the observation of a non-trivial reward and the individual steps of behavior culpable for achieving said reward. Coping with such a credit assignment challenge is one of the hallmark characteristics of reinforcement learning. While prior work has introduced the concept of h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.11897","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/2307.11897/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2307.11897","created_at":"2026-07-05T06:42:44.537046+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.11897v2","created_at":"2026-07-05T06:42:44.537046+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.11897","created_at":"2026-07-05T06:42:44.537046+00:00"},{"alias_kind":"pith_short_12","alias_value":"66O2HSY5ANSH","created_at":"2026-07-05T06:42:44.537046+00:00"},{"alias_kind":"pith_short_16","alias_value":"66O2HSY5ANSHHPJD","created_at":"2026-07-05T06:42:44.537046+00:00"},{"alias_kind":"pith_short_8","alias_value":"66O2HSY5","created_at":"2026-07-05T06:42:44.537046+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/66O2HSY5ANSHHPJDM4HDXPPZLN","json":"https://pith.science/pith/66O2HSY5ANSHHPJDM4HDXPPZLN.json","graph_json":"https://pith.science/api/pith-number/66O2HSY5ANSHHPJDM4HDXPPZLN/graph.json","events_json":"https://pith.science/api/pith-number/66O2HSY5ANSHHPJDM4HDXPPZLN/events.json","paper":"https://pith.science/paper/66O2HSY5"},"agent_actions":{"view_html":"https://pith.science/pith/66O2HSY5ANSHHPJDM4HDXPPZLN","download_json":"https://pith.science/pith/66O2HSY5ANSHHPJDM4HDXPPZLN.json","view_paper":"https://pith.science/paper/66O2HSY5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.11897&json=true","fetch_graph":"https://pith.science/api/pith-number/66O2HSY5ANSHHPJDM4HDXPPZLN/graph.json","fetch_events":"https://pith.science/api/pith-number/66O2HSY5ANSHHPJDM4HDXPPZLN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/66O2HSY5ANSHHPJDM4HDXPPZLN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/66O2HSY5ANSHHPJDM4HDXPPZLN/action/storage_attestation","attest_author":"https://pith.science/pith/66O2HSY5ANSHHPJDM4HDXPPZLN/action/author_attestation","sign_citation":"https://pith.science/pith/66O2HSY5ANSHHPJDM4HDXPPZLN/action/citation_signature","submit_replication":"https://pith.science/pith/66O2HSY5ANSHHPJDM4HDXPPZLN/action/replication_record"}},"created_at":"2026-07-05T06:42:44.537046+00:00","updated_at":"2026-07-05T06:42:44.537046+00:00"}