{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:K3T6DH6JUDIUSZ5OPX3VLPEBB5","short_pith_number":"pith:K3T6DH6J","canonical_record":{"source":{"id":"2011.02248","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-11-04T12:12:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"141506d26ac1c6dee69ee17a16801d1410d0a818107863c05e23195323f80119","abstract_canon_sha256":"fa0b4e35e8bbf31b1c4e55190a18bb0114a27f67148803c4c746377f208a16cd"},"schema_version":"1.0"},"canonical_sha256":"56e7e19fc9a0d14967ae7df755bc810f4ab6de298449f4e6f2894830c34448cf","source":{"kind":"arxiv","id":"2011.02248","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.02248","created_at":"2026-07-05T01:49:10Z"},{"alias_kind":"arxiv_version","alias_value":"2011.02248v1","created_at":"2026-07-05T01:49:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.02248","created_at":"2026-07-05T01:49:10Z"},{"alias_kind":"pith_short_12","alias_value":"K3T6DH6JUDIU","created_at":"2026-07-05T01:49:10Z"},{"alias_kind":"pith_short_16","alias_value":"K3T6DH6JUDIUSZ5O","created_at":"2026-07-05T01:49:10Z"},{"alias_kind":"pith_short_8","alias_value":"K3T6DH6J","created_at":"2026-07-05T01:49:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:K3T6DH6JUDIUSZ5OPX3VLPEBB5","target":"record","payload":{"canonical_record":{"source":{"id":"2011.02248","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-11-04T12:12:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"141506d26ac1c6dee69ee17a16801d1410d0a818107863c05e23195323f80119","abstract_canon_sha256":"fa0b4e35e8bbf31b1c4e55190a18bb0114a27f67148803c4c746377f208a16cd"},"schema_version":"1.0"},"canonical_sha256":"56e7e19fc9a0d14967ae7df755bc810f4ab6de298449f4e6f2894830c34448cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:10.848599Z","signature_b64":"xHHy59/FOFIIeWrUwFjSOVs97BGGrG+0+vMGnQ4u1XhjJEDmhs6zQ++5QtrwvMyeulCrbHkrbqljlZyVmiidDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56e7e19fc9a0d14967ae7df755bc810f4ab6de298449f4e6f2894830c34448cf","last_reissued_at":"2026-07-05T01:49:10.848210Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:10.848210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.02248","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":"2026-07-05T01:49:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fs5gxEMbu6rxVKj/+iaHQ1koQ3d6T3X57OKgSwrlY30aWWrZWVexYF+AasxpHq2XpbnmpQ29LPJGVXYB8O5zBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:54:55.860288Z"},"content_sha256":"641949a79e5d9c38504910098e09cb23c91c5429ce5872164c69a765a73fc578","schema_version":"1.0","event_id":"sha256:641949a79e5d9c38504910098e09cb23c91c5429ce5872164c69a765a73fc578"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:K3T6DH6JUDIUSZ5OPX3VLPEBB5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generative Inverse Deep Reinforcement Learning for Online Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Aixin Sun, Liming Zhu, Lina Yao, Xianzhi Wang, Xiaocong Chen, Xiwei Xu","submitted_at":"2020-11-04T12:12:25Z","abstract_excerpt":"Deep reinforcement learning enables an agent to capture user's interest through interactions with the environment dynamically. It has attracted great interest in the recommendation research. Deep reinforcement learning uses a reward function to learn user's interest and to control the learning process. However, most reward functions are manually designed; they are either unrealistic or imprecise to reflect the high variety, dimensionality, and non-linearity properties of the recommendation problem. That makes it difficult for the agent to learn an optimal policy to generate the most satisfacto"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.02248","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/2011.02248/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":"2026-07-05T01:49:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2/W2OBTErZE0Xo4NUi8jX9CeM1Lgel1IP/gM9V8RfCPPqf8dZMdLdroEX7me0ogWkYIEHlzF058Z6RkbswUgAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:54:55.860671Z"},"content_sha256":"ff91fa48f2712ee590f27bb93c1c106517a8775c03f4a39f40e2f7d307324f08","schema_version":"1.0","event_id":"sha256:ff91fa48f2712ee590f27bb93c1c106517a8775c03f4a39f40e2f7d307324f08"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K3T6DH6JUDIUSZ5OPX3VLPEBB5/bundle.json","state_url":"https://pith.science/pith/K3T6DH6JUDIUSZ5OPX3VLPEBB5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K3T6DH6JUDIUSZ5OPX3VLPEBB5/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":"2026-07-07T03:54:55Z","links":{"resolver":"https://pith.science/pith/K3T6DH6JUDIUSZ5OPX3VLPEBB5","bundle":"https://pith.science/pith/K3T6DH6JUDIUSZ5OPX3VLPEBB5/bundle.json","state":"https://pith.science/pith/K3T6DH6JUDIUSZ5OPX3VLPEBB5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K3T6DH6JUDIUSZ5OPX3VLPEBB5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:K3T6DH6JUDIUSZ5OPX3VLPEBB5","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":"fa0b4e35e8bbf31b1c4e55190a18bb0114a27f67148803c4c746377f208a16cd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-11-04T12:12:25Z","title_canon_sha256":"141506d26ac1c6dee69ee17a16801d1410d0a818107863c05e23195323f80119"},"schema_version":"1.0","source":{"id":"2011.02248","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.02248","created_at":"2026-07-05T01:49:10Z"},{"alias_kind":"arxiv_version","alias_value":"2011.02248v1","created_at":"2026-07-05T01:49:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.02248","created_at":"2026-07-05T01:49:10Z"},{"alias_kind":"pith_short_12","alias_value":"K3T6DH6JUDIU","created_at":"2026-07-05T01:49:10Z"},{"alias_kind":"pith_short_16","alias_value":"K3T6DH6JUDIUSZ5O","created_at":"2026-07-05T01:49:10Z"},{"alias_kind":"pith_short_8","alias_value":"K3T6DH6J","created_at":"2026-07-05T01:49:10Z"}],"graph_snapshots":[{"event_id":"sha256:ff91fa48f2712ee590f27bb93c1c106517a8775c03f4a39f40e2f7d307324f08","target":"graph","created_at":"2026-07-05T01:49:10Z","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/2011.02248/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning enables an agent to capture user's interest through interactions with the environment dynamically. It has attracted great interest in the recommendation research. Deep reinforcement learning uses a reward function to learn user's interest and to control the learning process. However, most reward functions are manually designed; they are either unrealistic or imprecise to reflect the high variety, dimensionality, and non-linearity properties of the recommendation problem. That makes it difficult for the agent to learn an optimal policy to generate the most satisfacto","authors_text":"Aixin Sun, Liming Zhu, Lina Yao, Xianzhi Wang, Xiaocong Chen, Xiwei Xu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-11-04T12:12:25Z","title":"Generative Inverse Deep Reinforcement Learning for Online Recommendation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.02248","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":"sha256:641949a79e5d9c38504910098e09cb23c91c5429ce5872164c69a765a73fc578","target":"record","created_at":"2026-07-05T01:49:10Z","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":"fa0b4e35e8bbf31b1c4e55190a18bb0114a27f67148803c4c746377f208a16cd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-11-04T12:12:25Z","title_canon_sha256":"141506d26ac1c6dee69ee17a16801d1410d0a818107863c05e23195323f80119"},"schema_version":"1.0","source":{"id":"2011.02248","kind":"arxiv","version":1}},"canonical_sha256":"56e7e19fc9a0d14967ae7df755bc810f4ab6de298449f4e6f2894830c34448cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56e7e19fc9a0d14967ae7df755bc810f4ab6de298449f4e6f2894830c34448cf","first_computed_at":"2026-07-05T01:49:10.848210Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:49:10.848210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xHHy59/FOFIIeWrUwFjSOVs97BGGrG+0+vMGnQ4u1XhjJEDmhs6zQ++5QtrwvMyeulCrbHkrbqljlZyVmiidDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:49:10.848599Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.02248","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:641949a79e5d9c38504910098e09cb23c91c5429ce5872164c69a765a73fc578","sha256:ff91fa48f2712ee590f27bb93c1c106517a8775c03f4a39f40e2f7d307324f08"],"state_sha256":"c8005c50732d6eb547997b355299e94309ba3411027550fcae57e42be2368315"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q35v2SYxjZx2S+RFvrAgqb1BPql7+maVHayGoNhs8NrW+R1JOtH9nX73p+WU/9kroOIu0ClGgC/ZPvP+yq4ZDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T03:54:55.863679Z","bundle_sha256":"0cb304dc41c04d22e7425eceaa9ce6f4477d656d352ac4090da9cb0371d6329b"}}