{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:SU5NGVQIF6FEEQYHM7VW6XXQUN","short_pith_number":"pith:SU5NGVQI","canonical_record":{"source":{"id":"1810.01371","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-10-02T17:01:28Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"0a6a9ee0278a41bef98f6b42c52fcc11735ab5600b5490577b59a3248f5254dd","abstract_canon_sha256":"e740cb842eb08c9251644d56d271a22416feb948aac71c8ebe41c11e07b518d9"},"schema_version":"1.0"},"canonical_sha256":"953ad356082f8a42430767eb6f5ef0a36424dcaafe0fec7fbfceab12bd16740e","source":{"kind":"arxiv","id":"1810.01371","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.01371","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"1810.01371v3","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.01371","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"SU5NGVQIF6FE","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"pith_short_16","alias_value":"SU5NGVQIF6FEEQYH","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"pith_short_8","alias_value":"SU5NGVQI","created_at":"2026-07-05T01:05:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:SU5NGVQIF6FEEQYHM7VW6XXQUN","target":"record","payload":{"canonical_record":{"source":{"id":"1810.01371","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-10-02T17:01:28Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"0a6a9ee0278a41bef98f6b42c52fcc11735ab5600b5490577b59a3248f5254dd","abstract_canon_sha256":"e740cb842eb08c9251644d56d271a22416feb948aac71c8ebe41c11e07b518d9"},"schema_version":"1.0"},"canonical_sha256":"953ad356082f8a42430767eb6f5ef0a36424dcaafe0fec7fbfceab12bd16740e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:05:08.474921Z","signature_b64":"gN0SHhStKOIXrJqBJmAM2BPtuQ+v64RAtso27sVz2Lhcu+P/IcbWE3K8NMcJbSgk0SeaYgKS+vNRNAnbfAWfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"953ad356082f8a42430767eb6f5ef0a36424dcaafe0fec7fbfceab12bd16740e","last_reissued_at":"2026-07-05T01:05:08.474519Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:05:08.474519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.01371","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":"2026-07-05T01:05:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wwFn8o4lUBvYgEmJGgoQSRcETtSj7XO8XyydSKzSXX/Uc3ABxkDgznj/5RQCeeKpQWB4UoqIv5xXWBHpbv8UCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T11:09:34.980958Z"},"content_sha256":"193f016f826ec2ac4c1633bda75d842f5d327a487921267efd04635b4b817039","schema_version":"1.0","event_id":"sha256:193f016f826ec2ac4c1633bda75d842f5d327a487921267efd04635b4b817039"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:SU5NGVQIF6FEEQYHM7VW6XXQUN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Dialog Policy Learning via Positive Memory Retention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Rui Zhao, Volker Tresp","submitted_at":"2018-10-02T17:01:28Z","abstract_excerpt":"This paper is concerned with the training of recurrent neural networks as goal-oriented dialog agents using reinforcement learning. Training such agents with policy gradients typically requires a large amount of samples. However, the collection of the required data in form of conversations between chat-bots and human agents is time-consuming and expensive. To mitigate this problem, we describe an efficient policy gradient method using positive memory retention, which significantly increases the sample-efficiency. We show that our method is 10 times more sample-efficient than policy gradients i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.01371","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/1810.01371/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":"2026-07-05T01:05:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8v9vG5S/BWWVi7Mct/yW1y5kOaUCZcsLexFTgyuSJW/OxwjJSFJBaj5MVEmbQdEujLAKYI8P1cOCdZtFGiUiAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T11:09:34.981486Z"},"content_sha256":"5d5f5fd4f9ec351d5190922c9f6a86ea2f5734aaebf5c5673da2c32b7c0b18db","schema_version":"1.0","event_id":"sha256:5d5f5fd4f9ec351d5190922c9f6a86ea2f5734aaebf5c5673da2c32b7c0b18db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SU5NGVQIF6FEEQYHM7VW6XXQUN/bundle.json","state_url":"https://pith.science/pith/SU5NGVQIF6FEEQYHM7VW6XXQUN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SU5NGVQIF6FEEQYHM7VW6XXQUN/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":"2026-08-21T11:09:34Z","links":{"resolver":"https://pith.science/pith/SU5NGVQIF6FEEQYHM7VW6XXQUN","bundle":"https://pith.science/pith/SU5NGVQIF6FEEQYHM7VW6XXQUN/bundle.json","state":"https://pith.science/pith/SU5NGVQIF6FEEQYHM7VW6XXQUN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SU5NGVQIF6FEEQYHM7VW6XXQUN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:SU5NGVQIF6FEEQYHM7VW6XXQUN","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":"e740cb842eb08c9251644d56d271a22416feb948aac71c8ebe41c11e07b518d9","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-10-02T17:01:28Z","title_canon_sha256":"0a6a9ee0278a41bef98f6b42c52fcc11735ab5600b5490577b59a3248f5254dd"},"schema_version":"1.0","source":{"id":"1810.01371","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.01371","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"1810.01371v3","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.01371","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"SU5NGVQIF6FE","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"pith_short_16","alias_value":"SU5NGVQIF6FEEQYH","created_at":"2026-07-05T01:05:08Z"},{"alias_kind":"pith_short_8","alias_value":"SU5NGVQI","created_at":"2026-07-05T01:05:08Z"}],"graph_snapshots":[{"event_id":"sha256:5d5f5fd4f9ec351d5190922c9f6a86ea2f5734aaebf5c5673da2c32b7c0b18db","target":"graph","created_at":"2026-07-05T01:05:08Z","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/1810.01371/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper is concerned with the training of recurrent neural networks as goal-oriented dialog agents using reinforcement learning. Training such agents with policy gradients typically requires a large amount of samples. However, the collection of the required data in form of conversations between chat-bots and human agents is time-consuming and expensive. To mitigate this problem, we describe an efficient policy gradient method using positive memory retention, which significantly increases the sample-efficiency. We show that our method is 10 times more sample-efficient than policy gradients i","authors_text":"Rui Zhao, Volker Tresp","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-10-02T17:01:28Z","title":"Efficient Dialog Policy Learning via Positive Memory Retention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.01371","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":"sha256:193f016f826ec2ac4c1633bda75d842f5d327a487921267efd04635b4b817039","target":"record","created_at":"2026-07-05T01:05:08Z","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":"e740cb842eb08c9251644d56d271a22416feb948aac71c8ebe41c11e07b518d9","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-10-02T17:01:28Z","title_canon_sha256":"0a6a9ee0278a41bef98f6b42c52fcc11735ab5600b5490577b59a3248f5254dd"},"schema_version":"1.0","source":{"id":"1810.01371","kind":"arxiv","version":3}},"canonical_sha256":"953ad356082f8a42430767eb6f5ef0a36424dcaafe0fec7fbfceab12bd16740e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"953ad356082f8a42430767eb6f5ef0a36424dcaafe0fec7fbfceab12bd16740e","first_computed_at":"2026-07-05T01:05:08.474519Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:05:08.474519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gN0SHhStKOIXrJqBJmAM2BPtuQ+v64RAtso27sVz2Lhcu+P/IcbWE3K8NMcJbSgk0SeaYgKS+vNRNAnbfAWfAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:05:08.474921Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.01371","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:193f016f826ec2ac4c1633bda75d842f5d327a487921267efd04635b4b817039","sha256:5d5f5fd4f9ec351d5190922c9f6a86ea2f5734aaebf5c5673da2c32b7c0b18db"],"state_sha256":"d3484d8bb8b611ea712caaec6ccdaff64552e279495ca3d2ba865e8a269a6734"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nVCDj0XAwAm35RDckjumVox6kU4E+25DMz55fWSD1WM7jvbiuAouQzx8hSPmUGWAK0imYGKFDKJxejtHSv9GDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T11:09:34.986972Z","bundle_sha256":"fb6cd88677a1313bb6e3413ae5edf4e7277612a7cd8c76b8e7922c041e214614"}}