{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3DUPXATBTF3IPE2XI7S2FDDT4Q","short_pith_number":"pith:3DUPXATB","canonical_record":{"source":{"id":"2412.16878","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-22T06:15:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d5d345f5861896cf85fb44d2f29f6e9b3667ebd353f9804d4d00f0c540d15c52","abstract_canon_sha256":"dab6593acaf491cce2c1748bf6a8161908f87d072e9d8af98afd35dc890efe8a"},"schema_version":"1.0"},"canonical_sha256":"d8e8fb8261997687935747e5a28c73e435b708779c83d11efb88b5f5a7e897f3","source":{"kind":"arxiv","id":"2412.16878","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16878","created_at":"2026-07-05T09:53:14Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16878v1","created_at":"2026-07-05T09:53:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16878","created_at":"2026-07-05T09:53:14Z"},{"alias_kind":"pith_short_12","alias_value":"3DUPXATBTF3I","created_at":"2026-07-05T09:53:14Z"},{"alias_kind":"pith_short_16","alias_value":"3DUPXATBTF3IPE2X","created_at":"2026-07-05T09:53:14Z"},{"alias_kind":"pith_short_8","alias_value":"3DUPXATB","created_at":"2026-07-05T09:53:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3DUPXATBTF3IPE2XI7S2FDDT4Q","target":"record","payload":{"canonical_record":{"source":{"id":"2412.16878","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-22T06:15:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d5d345f5861896cf85fb44d2f29f6e9b3667ebd353f9804d4d00f0c540d15c52","abstract_canon_sha256":"dab6593acaf491cce2c1748bf6a8161908f87d072e9d8af98afd35dc890efe8a"},"schema_version":"1.0"},"canonical_sha256":"d8e8fb8261997687935747e5a28c73e435b708779c83d11efb88b5f5a7e897f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:14.082492Z","signature_b64":"YzOY0SU4FK4e8oxfvE5OKpn6cxCjVmaqp/gJxOxDJbHpG4Emts69wb7qr6PPi7RQE5A1VkcGjaFJTZ64P29jDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8e8fb8261997687935747e5a28c73e435b708779c83d11efb88b5f5a7e897f3","last_reissued_at":"2026-07-05T09:53:14.081948Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:14.081948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.16878","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":"2026-07-05T09:53:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZdqJVNYBibmDP9WBjNnntWNuBrMzowSiLnVrlW3pFKK90c5gE0dUeX729qignz71pj49KfvtNORiR6xzR/dMBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:01:28.282474Z"},"content_sha256":"a7ce1292146211d8a775ff72a7768f824c11f05f62a119b1ba196370aed03c8d","schema_version":"1.0","event_id":"sha256:a7ce1292146211d8a775ff72a7768f824c11f05f62a119b1ba196370aed03c8d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3DUPXATBTF3IPE2XI7S2FDDT4Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Online Preference-based Reinforcement Learning with Self-augmented Feedback from Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dongbin Zhao, Jingbo Sun, Qichao Zhang, Songjun Tu, Xiangyuan Lan","submitted_at":"2024-12-22T06:15:25Z","abstract_excerpt":"Preference-based reinforcement learning (PbRL) provides a powerful paradigm to avoid meticulous reward engineering by learning rewards based on human preferences. However, real-time human feedback is hard to obtain in online tasks. Most work suppose there is a \"scripted teacher\" that utilizes privileged predefined reward to provide preference feedback. In this paper, we propose a RL Self-augmented Large Language Model Feedback (RL-SaLLM-F) technique that does not rely on privileged information for online PbRL. RL-SaLLM-F leverages the reflective and discriminative capabilities of LLM to genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16878","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.16878/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":"2026-07-05T09:53:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T6hNZEXbMuLcRtm9+iE7UXdQWfhiiBFfwkgS6uIHhmjLCvbnzkY840dMBN8hnNnGKcLl1LtIDfHXcdJtUOsJAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:01:28.282845Z"},"content_sha256":"2ef1f9746e53b7bd0c250154ec9b365747630ce5a0e6d21bc77b29a64a5e3f0c","schema_version":"1.0","event_id":"sha256:2ef1f9746e53b7bd0c250154ec9b365747630ce5a0e6d21bc77b29a64a5e3f0c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3DUPXATBTF3IPE2XI7S2FDDT4Q/bundle.json","state_url":"https://pith.science/pith/3DUPXATBTF3IPE2XI7S2FDDT4Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3DUPXATBTF3IPE2XI7S2FDDT4Q/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":"2026-07-07T09:01:28Z","links":{"resolver":"https://pith.science/pith/3DUPXATBTF3IPE2XI7S2FDDT4Q","bundle":"https://pith.science/pith/3DUPXATBTF3IPE2XI7S2FDDT4Q/bundle.json","state":"https://pith.science/pith/3DUPXATBTF3IPE2XI7S2FDDT4Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3DUPXATBTF3IPE2XI7S2FDDT4Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3DUPXATBTF3IPE2XI7S2FDDT4Q","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":"dab6593acaf491cce2c1748bf6a8161908f87d072e9d8af98afd35dc890efe8a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-22T06:15:25Z","title_canon_sha256":"d5d345f5861896cf85fb44d2f29f6e9b3667ebd353f9804d4d00f0c540d15c52"},"schema_version":"1.0","source":{"id":"2412.16878","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16878","created_at":"2026-07-05T09:53:14Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16878v1","created_at":"2026-07-05T09:53:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16878","created_at":"2026-07-05T09:53:14Z"},{"alias_kind":"pith_short_12","alias_value":"3DUPXATBTF3I","created_at":"2026-07-05T09:53:14Z"},{"alias_kind":"pith_short_16","alias_value":"3DUPXATBTF3IPE2X","created_at":"2026-07-05T09:53:14Z"},{"alias_kind":"pith_short_8","alias_value":"3DUPXATB","created_at":"2026-07-05T09:53:14Z"}],"graph_snapshots":[{"event_id":"sha256:2ef1f9746e53b7bd0c250154ec9b365747630ce5a0e6d21bc77b29a64a5e3f0c","target":"graph","created_at":"2026-07-05T09:53:14Z","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/2412.16878/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference-based reinforcement learning (PbRL) provides a powerful paradigm to avoid meticulous reward engineering by learning rewards based on human preferences. However, real-time human feedback is hard to obtain in online tasks. Most work suppose there is a \"scripted teacher\" that utilizes privileged predefined reward to provide preference feedback. In this paper, we propose a RL Self-augmented Large Language Model Feedback (RL-SaLLM-F) technique that does not rely on privileged information for online PbRL. RL-SaLLM-F leverages the reflective and discriminative capabilities of LLM to genera","authors_text":"Dongbin Zhao, Jingbo Sun, Qichao Zhang, Songjun Tu, Xiangyuan Lan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-22T06:15:25Z","title":"Online Preference-based Reinforcement Learning with Self-augmented Feedback from Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16878","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:a7ce1292146211d8a775ff72a7768f824c11f05f62a119b1ba196370aed03c8d","target":"record","created_at":"2026-07-05T09:53:14Z","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":"dab6593acaf491cce2c1748bf6a8161908f87d072e9d8af98afd35dc890efe8a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-22T06:15:25Z","title_canon_sha256":"d5d345f5861896cf85fb44d2f29f6e9b3667ebd353f9804d4d00f0c540d15c52"},"schema_version":"1.0","source":{"id":"2412.16878","kind":"arxiv","version":1}},"canonical_sha256":"d8e8fb8261997687935747e5a28c73e435b708779c83d11efb88b5f5a7e897f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8e8fb8261997687935747e5a28c73e435b708779c83d11efb88b5f5a7e897f3","first_computed_at":"2026-07-05T09:53:14.081948Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:14.081948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YzOY0SU4FK4e8oxfvE5OKpn6cxCjVmaqp/gJxOxDJbHpG4Emts69wb7qr6PPi7RQE5A1VkcGjaFJTZ64P29jDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:14.082492Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.16878","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7ce1292146211d8a775ff72a7768f824c11f05f62a119b1ba196370aed03c8d","sha256:2ef1f9746e53b7bd0c250154ec9b365747630ce5a0e6d21bc77b29a64a5e3f0c"],"state_sha256":"231ab7dce29938634d4f6add31672a78a0d3de143fecf9472e5036b71d86d0d7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"21FNfL4xQof24BjqaO5s0h36MgxWoMTux0/ATAGWlc2F9xczvJEXRzmif+BZ2uruY2ph3d1xpvxiuayApO/yAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:01:28.284818Z","bundle_sha256":"761b9c96eea51b40a7a17eaa812beea8ce1a59714dc47cf2cb8d7c21fad30251"}}