{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:AZS6CKZHL3QGAJNA6PLQV2WPRJ","short_pith_number":"pith:AZS6CKZH","canonical_record":{"source":{"id":"2111.04850","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-08T22:17:36Z","cross_cats_sorted":[],"title_canon_sha256":"dbe419cdf3a0f6e65760e15abf3b62a5eae7be276ee0e4da5f48574b45e67282","abstract_canon_sha256":"e60ebd6cb9ef0a4abcce9ef23e96b50030b555c907b2ffdbe794a19673e3c708"},"schema_version":"1.0"},"canonical_sha256":"0665e12b275ee06025a0f3d70aeacf8a401527175e044ae49f3b2c042a66b54b","source":{"kind":"arxiv","id":"2111.04850","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.04850","created_at":"2026-07-05T05:39:00Z"},{"alias_kind":"arxiv_version","alias_value":"2111.04850v3","created_at":"2026-07-05T05:39:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.04850","created_at":"2026-07-05T05:39:00Z"},{"alias_kind":"pith_short_12","alias_value":"AZS6CKZHL3QG","created_at":"2026-07-05T05:39:00Z"},{"alias_kind":"pith_short_16","alias_value":"AZS6CKZHL3QGAJNA","created_at":"2026-07-05T05:39:00Z"},{"alias_kind":"pith_short_8","alias_value":"AZS6CKZH","created_at":"2026-07-05T05:39:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:AZS6CKZHL3QGAJNA6PLQV2WPRJ","target":"record","payload":{"canonical_record":{"source":{"id":"2111.04850","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-08T22:17:36Z","cross_cats_sorted":[],"title_canon_sha256":"dbe419cdf3a0f6e65760e15abf3b62a5eae7be276ee0e4da5f48574b45e67282","abstract_canon_sha256":"e60ebd6cb9ef0a4abcce9ef23e96b50030b555c907b2ffdbe794a19673e3c708"},"schema_version":"1.0"},"canonical_sha256":"0665e12b275ee06025a0f3d70aeacf8a401527175e044ae49f3b2c042a66b54b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:39:00.550796Z","signature_b64":"/RuVRTTF6sGFVuNjqz3u8TxhQI6GRXCvn5lorNd8ylz4MP810A0tlHS4ETW24K2N5Wgo/sz3muAx4O8crsioDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0665e12b275ee06025a0f3d70aeacf8a401527175e044ae49f3b2c042a66b54b","last_reissued_at":"2026-07-05T05:39:00.550402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:39:00.550402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.04850","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:39:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"volfJ2ZnKhc7c40rWFajwd+XodSlxL6L53PIReZNOlr/9yPssgvLW+hYO5FFkYk5C226jKi5C2/6jBcHWkBiDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:25:03.826686Z"},"content_sha256":"8c83a8a08a446322b238d119de602ad51dc745112cb4515f08b409805fbaf30a","schema_version":"1.0","event_id":"sha256:8c83a8a08a446322b238d119de602ad51dc745112cb4515f08b409805fbaf30a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:AZS6CKZHL3QGAJNA6PLQV2WPRJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dueling RL: Reinforcement Learning with Trajectory Preferences","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aadirupa Saha, Aldo Pacchiano, Jonathan Lee","submitted_at":"2021-11-08T22:17:36Z","abstract_excerpt":"We consider the problem of preference based reinforcement learning (PbRL), where, unlike traditional reinforcement learning, an agent receives feedback only in terms of a 1 bit (0/1) preference over a trajectory pair instead of absolute rewards for them. The success of the traditional RL framework crucially relies on the underlying agent-reward model, which, however, depends on how accurately a system designer can express an appropriate reward function and often a non-trivial task. The main novelty of our framework is the ability to learn from preference-based trajectory feedback that eliminat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.04850","kind":"arxiv","version":3},"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/2111.04850/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":"2026-07-05T05:39:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jtMKc3Z3ZCYRz/t48SmDXOkyIxd/g6M1s1C/XKNPkPJfUuFwZnRN9FXKgZEZ/4iYcvMKxsQ+5ySXwmgv5qpHCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:25:03.827312Z"},"content_sha256":"af31fc1bb001b8c340db030bff68770505db60e0f91d317eb642540d4f0e6fb5","schema_version":"1.0","event_id":"sha256:af31fc1bb001b8c340db030bff68770505db60e0f91d317eb642540d4f0e6fb5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AZS6CKZHL3QGAJNA6PLQV2WPRJ/bundle.json","state_url":"https://pith.science/pith/AZS6CKZHL3QGAJNA6PLQV2WPRJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AZS6CKZHL3QGAJNA6PLQV2WPRJ/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":"2026-08-08T16:25:03Z","links":{"resolver":"https://pith.science/pith/AZS6CKZHL3QGAJNA6PLQV2WPRJ","bundle":"https://pith.science/pith/AZS6CKZHL3QGAJNA6PLQV2WPRJ/bundle.json","state":"https://pith.science/pith/AZS6CKZHL3QGAJNA6PLQV2WPRJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AZS6CKZHL3QGAJNA6PLQV2WPRJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:AZS6CKZHL3QGAJNA6PLQV2WPRJ","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":"e60ebd6cb9ef0a4abcce9ef23e96b50030b555c907b2ffdbe794a19673e3c708","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-08T22:17:36Z","title_canon_sha256":"dbe419cdf3a0f6e65760e15abf3b62a5eae7be276ee0e4da5f48574b45e67282"},"schema_version":"1.0","source":{"id":"2111.04850","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.04850","created_at":"2026-07-05T05:39:00Z"},{"alias_kind":"arxiv_version","alias_value":"2111.04850v3","created_at":"2026-07-05T05:39:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.04850","created_at":"2026-07-05T05:39:00Z"},{"alias_kind":"pith_short_12","alias_value":"AZS6CKZHL3QG","created_at":"2026-07-05T05:39:00Z"},{"alias_kind":"pith_short_16","alias_value":"AZS6CKZHL3QGAJNA","created_at":"2026-07-05T05:39:00Z"},{"alias_kind":"pith_short_8","alias_value":"AZS6CKZH","created_at":"2026-07-05T05:39:00Z"}],"graph_snapshots":[{"event_id":"sha256:af31fc1bb001b8c340db030bff68770505db60e0f91d317eb642540d4f0e6fb5","target":"graph","created_at":"2026-07-05T05:39:00Z","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/2111.04850/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the problem of preference based reinforcement learning (PbRL), where, unlike traditional reinforcement learning, an agent receives feedback only in terms of a 1 bit (0/1) preference over a trajectory pair instead of absolute rewards for them. The success of the traditional RL framework crucially relies on the underlying agent-reward model, which, however, depends on how accurately a system designer can express an appropriate reward function and often a non-trivial task. The main novelty of our framework is the ability to learn from preference-based trajectory feedback that eliminat","authors_text":"Aadirupa Saha, Aldo Pacchiano, Jonathan Lee","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-08T22:17:36Z","title":"Dueling RL: Reinforcement Learning with Trajectory Preferences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.04850","kind":"arxiv","version":3},"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":"sha256:8c83a8a08a446322b238d119de602ad51dc745112cb4515f08b409805fbaf30a","target":"record","created_at":"2026-07-05T05:39:00Z","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":"e60ebd6cb9ef0a4abcce9ef23e96b50030b555c907b2ffdbe794a19673e3c708","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-08T22:17:36Z","title_canon_sha256":"dbe419cdf3a0f6e65760e15abf3b62a5eae7be276ee0e4da5f48574b45e67282"},"schema_version":"1.0","source":{"id":"2111.04850","kind":"arxiv","version":3}},"canonical_sha256":"0665e12b275ee06025a0f3d70aeacf8a401527175e044ae49f3b2c042a66b54b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0665e12b275ee06025a0f3d70aeacf8a401527175e044ae49f3b2c042a66b54b","first_computed_at":"2026-07-05T05:39:00.550402Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:39:00.550402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/RuVRTTF6sGFVuNjqz3u8TxhQI6GRXCvn5lorNd8ylz4MP810A0tlHS4ETW24K2N5Wgo/sz3muAx4O8crsioDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:39:00.550796Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.04850","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c83a8a08a446322b238d119de602ad51dc745112cb4515f08b409805fbaf30a","sha256:af31fc1bb001b8c340db030bff68770505db60e0f91d317eb642540d4f0e6fb5"],"state_sha256":"83603e8c691b5937a658b5832ff0ed0af142b8111c825824db3abaed7c2aef16"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mIXQOc9JzELe0xnrH06j04NghBYuBu9unEfvobLLW39bOQDa5TG9v63eaQlvN2D4cnMYRpKJ8/IOUS6cAS+aBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:25:03.831754Z","bundle_sha256":"74d9bca10dca00cc57d8f0e5ec9ca200dce136918574efb0ef502b0d9c84c40e"}}