{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:B7DNFNPW4EWOA4V4AQJOXDODD4","short_pith_number":"pith:B7DNFNPW","canonical_record":{"source":{"id":"2106.07704","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-14T18:48:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f62df1813fbf37a391017abc83e0be6ab415779210963da92485d688a1f85ee6","abstract_canon_sha256":"15992c1f436eeb8bbcb259d424da0817f1b635fc68990351d3203eb6236ad28b"},"schema_version":"1.0"},"canonical_sha256":"0fc6d2b5f6e12ce072bc0412eb8dc31f12fc63de727d3b6b0bae843ad21c4712","source":{"kind":"arxiv","id":"2106.07704","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.07704","created_at":"2026-07-05T05:09:12Z"},{"alias_kind":"arxiv_version","alias_value":"2106.07704v4","created_at":"2026-07-05T05:09:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.07704","created_at":"2026-07-05T05:09:12Z"},{"alias_kind":"pith_short_12","alias_value":"B7DNFNPW4EWO","created_at":"2026-07-05T05:09:12Z"},{"alias_kind":"pith_short_16","alias_value":"B7DNFNPW4EWOA4V4","created_at":"2026-07-05T05:09:12Z"},{"alias_kind":"pith_short_8","alias_value":"B7DNFNPW","created_at":"2026-07-05T05:09:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:B7DNFNPW4EWOA4V4AQJOXDODD4","target":"record","payload":{"canonical_record":{"source":{"id":"2106.07704","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-14T18:48:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f62df1813fbf37a391017abc83e0be6ab415779210963da92485d688a1f85ee6","abstract_canon_sha256":"15992c1f436eeb8bbcb259d424da0817f1b635fc68990351d3203eb6236ad28b"},"schema_version":"1.0"},"canonical_sha256":"0fc6d2b5f6e12ce072bc0412eb8dc31f12fc63de727d3b6b0bae843ad21c4712","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:12.235101Z","signature_b64":"bm9aR6hJKwgB/NJlFPwqGs/WLc+wSNA9bV3qZqqFTvOuvwPfQyILp23OhY8FLf5AzArzkAyIxEesXSvKEBTPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fc6d2b5f6e12ce072bc0412eb8dc31f12fc63de727d3b6b0bae843ad21c4712","last_reissued_at":"2026-07-05T05:09:12.234622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:12.234622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.07704","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:09:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O4ZqWWHUGa+MAF081cMvLGoub6URRutksscLt4Ln7kRZA24BevK9Vbadzt6SRfNWzk5d9gRcAPEX5ffkeVgDCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:32:33.722862Z"},"content_sha256":"e7bd424f956f870feed5e450d48202d947db436d87df1934a4e0caf534c5615a","schema_version":"1.0","event_id":"sha256:e7bd424f956f870feed5e450d48202d947db436d87df1934a4e0caf534c5615a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:B7DNFNPW4EWOA4V4AQJOXDODD4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient (Soft) Q-Learning for Text Generation with Limited Good Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bowen Tan, Eric P. Xing, Han Guo, Zhengzhong Liu, Zhiting Hu","submitted_at":"2021-06-14T18:48:40Z","abstract_excerpt":"Maximum likelihood estimation (MLE) is the predominant algorithm for training text generation models. This paradigm relies on direct supervision examples, which is not applicable to many emerging applications, such as generating adversarial attacks or generating prompts to control language models. Reinforcement learning (RL) on the other hand offers a more flexible solution by allowing users to plug in arbitrary task metrics as reward. Yet previous RL algorithms for text generation, such as policy gradient (on-policy RL) and Q-learning (off-policy RL), are often notoriously inefficient or unst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.07704","kind":"arxiv","version":4},"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/2106.07704/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":"2026-07-05T05:09:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zlz7sR4toLcwQ4sgZPzA0Jyhd8q75HfyKjV7bR5ggqd08dEZV02a3L56ghO+Uee+eaQVT4o14kmPa8A3ySz7Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:32:33.723443Z"},"content_sha256":"c95adf8d6945128e03c7973e33991c52d24ce8f6b713644ed093da6972ff5c95","schema_version":"1.0","event_id":"sha256:c95adf8d6945128e03c7973e33991c52d24ce8f6b713644ed093da6972ff5c95"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B7DNFNPW4EWOA4V4AQJOXDODD4/bundle.json","state_url":"https://pith.science/pith/B7DNFNPW4EWOA4V4AQJOXDODD4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B7DNFNPW4EWOA4V4AQJOXDODD4/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":"2026-08-10T12:32:33Z","links":{"resolver":"https://pith.science/pith/B7DNFNPW4EWOA4V4AQJOXDODD4","bundle":"https://pith.science/pith/B7DNFNPW4EWOA4V4AQJOXDODD4/bundle.json","state":"https://pith.science/pith/B7DNFNPW4EWOA4V4AQJOXDODD4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B7DNFNPW4EWOA4V4AQJOXDODD4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:B7DNFNPW4EWOA4V4AQJOXDODD4","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":"15992c1f436eeb8bbcb259d424da0817f1b635fc68990351d3203eb6236ad28b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-14T18:48:40Z","title_canon_sha256":"f62df1813fbf37a391017abc83e0be6ab415779210963da92485d688a1f85ee6"},"schema_version":"1.0","source":{"id":"2106.07704","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.07704","created_at":"2026-07-05T05:09:12Z"},{"alias_kind":"arxiv_version","alias_value":"2106.07704v4","created_at":"2026-07-05T05:09:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.07704","created_at":"2026-07-05T05:09:12Z"},{"alias_kind":"pith_short_12","alias_value":"B7DNFNPW4EWO","created_at":"2026-07-05T05:09:12Z"},{"alias_kind":"pith_short_16","alias_value":"B7DNFNPW4EWOA4V4","created_at":"2026-07-05T05:09:12Z"},{"alias_kind":"pith_short_8","alias_value":"B7DNFNPW","created_at":"2026-07-05T05:09:12Z"}],"graph_snapshots":[{"event_id":"sha256:c95adf8d6945128e03c7973e33991c52d24ce8f6b713644ed093da6972ff5c95","target":"graph","created_at":"2026-07-05T05:09:12Z","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/2106.07704/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Maximum likelihood estimation (MLE) is the predominant algorithm for training text generation models. This paradigm relies on direct supervision examples, which is not applicable to many emerging applications, such as generating adversarial attacks or generating prompts to control language models. Reinforcement learning (RL) on the other hand offers a more flexible solution by allowing users to plug in arbitrary task metrics as reward. Yet previous RL algorithms for text generation, such as policy gradient (on-policy RL) and Q-learning (off-policy RL), are often notoriously inefficient or unst","authors_text":"Bowen Tan, Eric P. Xing, Han Guo, Zhengzhong Liu, Zhiting Hu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-14T18:48:40Z","title":"Efficient (Soft) Q-Learning for Text Generation with Limited Good Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.07704","kind":"arxiv","version":4},"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:e7bd424f956f870feed5e450d48202d947db436d87df1934a4e0caf534c5615a","target":"record","created_at":"2026-07-05T05:09:12Z","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":"15992c1f436eeb8bbcb259d424da0817f1b635fc68990351d3203eb6236ad28b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-14T18:48:40Z","title_canon_sha256":"f62df1813fbf37a391017abc83e0be6ab415779210963da92485d688a1f85ee6"},"schema_version":"1.0","source":{"id":"2106.07704","kind":"arxiv","version":4}},"canonical_sha256":"0fc6d2b5f6e12ce072bc0412eb8dc31f12fc63de727d3b6b0bae843ad21c4712","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0fc6d2b5f6e12ce072bc0412eb8dc31f12fc63de727d3b6b0bae843ad21c4712","first_computed_at":"2026-07-05T05:09:12.234622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:09:12.234622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bm9aR6hJKwgB/NJlFPwqGs/WLc+wSNA9bV3qZqqFTvOuvwPfQyILp23OhY8FLf5AzArzkAyIxEesXSvKEBTPCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:09:12.235101Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.07704","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7bd424f956f870feed5e450d48202d947db436d87df1934a4e0caf534c5615a","sha256:c95adf8d6945128e03c7973e33991c52d24ce8f6b713644ed093da6972ff5c95"],"state_sha256":"ea8258993c77e656d1e5385c2ddf82ef8d3f3ab9abf795b9f122d83efc422fc6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O08JgAbpdW6G2AeI5lXuUkf6gESnM3SJUsaJc3AHKr0T62IWMY411uMsHcO/v5bTHNagIvcSL7ytrH16BmZUDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T12:32:33.727091Z","bundle_sha256":"71f7b8dbea5ac660d735ed3d9317330c713b62bb6f6b00e358a19c498785deac"}}