{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:66O2HSY5ANSHHPJDM4HDXPPZLN","short_pith_number":"pith:66O2HSY5","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"},"canonical_sha256":"f79da3cb1d036473bd23670e3bbdf95b51dc71fdfd9ac3f53331248cc36c19bd","source":{"kind":"arxiv","id":"2307.11897","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.11897","created_at":"2026-07-05T06:42:44Z"},{"alias_kind":"arxiv_version","alias_value":"2307.11897v2","created_at":"2026-07-05T06:42:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.11897","created_at":"2026-07-05T06:42:44Z"},{"alias_kind":"pith_short_12","alias_value":"66O2HSY5ANSH","created_at":"2026-07-05T06:42:44Z"},{"alias_kind":"pith_short_16","alias_value":"66O2HSY5ANSHHPJD","created_at":"2026-07-05T06:42:44Z"},{"alias_kind":"pith_short_8","alias_value":"66O2HSY5","created_at":"2026-07-05T06:42:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:66O2HSY5ANSHHPJDM4HDXPPZLN","target":"record","payload":{"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"},"canonical_sha256":"f79da3cb1d036473bd23670e3bbdf95b51dc71fdfd9ac3f53331248cc36c19bd","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"},"source_kind":"arxiv","source_id":"2307.11897","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":"2026-07-05T06:42:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rnk4cTAM4/cit22BBVgIxR6d93KTLVeMI+IYh0eBqoqWRuSveiO/lZBcTD3Q3n1PEqJmIaHGCZe5g9yi+M15Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:21:13.135980Z"},"content_sha256":"5247bf54a03c893b1bb53d85457a99dbe5f2fe7d8ed139fdd6442f87a15edfcb","schema_version":"1.0","event_id":"sha256:5247bf54a03c893b1bb53d85457a99dbe5f2fe7d8ed139fdd6442f87a15edfcb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:66O2HSY5ANSHHPJDM4HDXPPZLN","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:42:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Te0tS970ajdiE8m0K+vKG+1yPk0tXtFwrc4HwqDjxRqLHCH24O1rrqmVKUSabdHHsv0VE5bpj/ocMNPTSeVgCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:21:13.136360Z"},"content_sha256":"efddb7ceb20ec5db4023334d3d21a45803a6bdac45ca69fc35ecf0e0e399a6ea","schema_version":"1.0","event_id":"sha256:efddb7ceb20ec5db4023334d3d21a45803a6bdac45ca69fc35ecf0e0e399a6ea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/66O2HSY5ANSHHPJDM4HDXPPZLN/bundle.json","state_url":"https://pith.science/pith/66O2HSY5ANSHHPJDM4HDXPPZLN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/66O2HSY5ANSHHPJDM4HDXPPZLN/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":"2026-07-07T13:21:13Z","links":{"resolver":"https://pith.science/pith/66O2HSY5ANSHHPJDM4HDXPPZLN","bundle":"https://pith.science/pith/66O2HSY5ANSHHPJDM4HDXPPZLN/bundle.json","state":"https://pith.science/pith/66O2HSY5ANSHHPJDM4HDXPPZLN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/66O2HSY5ANSHHPJDM4HDXPPZLN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:66O2HSY5ANSHHPJDM4HDXPPZLN","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":"8cb277e0d92994cdbb25c9cb423a139db821117e21a51c01843f25084d0848d9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-21T20:54:52Z","title_canon_sha256":"8c9581831fb876f31f0cb5d045a05cdfb23c32640629aad36616b311f068c209"},"schema_version":"1.0","source":{"id":"2307.11897","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.11897","created_at":"2026-07-05T06:42:44Z"},{"alias_kind":"arxiv_version","alias_value":"2307.11897v2","created_at":"2026-07-05T06:42:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.11897","created_at":"2026-07-05T06:42:44Z"},{"alias_kind":"pith_short_12","alias_value":"66O2HSY5ANSH","created_at":"2026-07-05T06:42:44Z"},{"alias_kind":"pith_short_16","alias_value":"66O2HSY5ANSHHPJD","created_at":"2026-07-05T06:42:44Z"},{"alias_kind":"pith_short_8","alias_value":"66O2HSY5","created_at":"2026-07-05T06:42:44Z"}],"graph_snapshots":[{"event_id":"sha256:efddb7ceb20ec5db4023334d3d21a45803a6bdac45ca69fc35ecf0e0e399a6ea","target":"graph","created_at":"2026-07-05T06:42:44Z","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/2307.11897/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Akash Velu, Dilip Arumugam, Skanda Vaidyanath","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-21T20:54:52Z","title":"Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.11897","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":"sha256:5247bf54a03c893b1bb53d85457a99dbe5f2fe7d8ed139fdd6442f87a15edfcb","target":"record","created_at":"2026-07-05T06:42:44Z","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":"8cb277e0d92994cdbb25c9cb423a139db821117e21a51c01843f25084d0848d9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-21T20:54:52Z","title_canon_sha256":"8c9581831fb876f31f0cb5d045a05cdfb23c32640629aad36616b311f068c209"},"schema_version":"1.0","source":{"id":"2307.11897","kind":"arxiv","version":2}},"canonical_sha256":"f79da3cb1d036473bd23670e3bbdf95b51dc71fdfd9ac3f53331248cc36c19bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f79da3cb1d036473bd23670e3bbdf95b51dc71fdfd9ac3f53331248cc36c19bd","first_computed_at":"2026-07-05T06:42:44.536985Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:42:44.536985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R0cuN8BsQ97HJYV15CoqGDSpIpBj8gEZ6BlaColraVyba1s6dIWnQnwc320fCNDp9F6E1aFnxRanT/SvT+cJDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:42:44.537425Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.11897","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5247bf54a03c893b1bb53d85457a99dbe5f2fe7d8ed139fdd6442f87a15edfcb","sha256:efddb7ceb20ec5db4023334d3d21a45803a6bdac45ca69fc35ecf0e0e399a6ea"],"state_sha256":"43e2addffdb9f8060242df8a1a3d4451072cd801f492278d1aa63d4bc0dee3a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MEnzhIuWbYfnJVL6eytqeqsNuktCbiEc2cgapSkQKqiwvM0//znZfUXTwQ2jL9UOLOPu9ZPg9KssYsuuaFVmDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:21:13.138572Z","bundle_sha256":"04a876a313679b91ed59f7414c83131af22b2a27cf7a5c50907cfaa62a579b7e"}}