{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GPOZVVZUUH2FI54KPC3S6ZKI6T","short_pith_number":"pith:GPOZVVZU","canonical_record":{"source":{"id":"2304.09087","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-04-17T07:25:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ff6090ace557b24026b3a615d47af0709c65b03d69292abe1eff365c4e758d99","abstract_canon_sha256":"f2546bba2f61fd4cc03bb1771b78b01060e1aa4e8957da4830f2623c2c4a840b"},"schema_version":"1.0"},"canonical_sha256":"33dd9ad734a1f454778a78b72f6548f4df354bf4324a22740f7c85aed060aa9b","source":{"kind":"arxiv","id":"2304.09087","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.09087","created_at":"2026-07-05T06:02:16Z"},{"alias_kind":"arxiv_version","alias_value":"2304.09087v1","created_at":"2026-07-05T06:02:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.09087","created_at":"2026-07-05T06:02:16Z"},{"alias_kind":"pith_short_12","alias_value":"GPOZVVZUUH2F","created_at":"2026-07-05T06:02:16Z"},{"alias_kind":"pith_short_16","alias_value":"GPOZVVZUUH2FI54K","created_at":"2026-07-05T06:02:16Z"},{"alias_kind":"pith_short_8","alias_value":"GPOZVVZU","created_at":"2026-07-05T06:02:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GPOZVVZUUH2FI54KPC3S6ZKI6T","target":"record","payload":{"canonical_record":{"source":{"id":"2304.09087","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-04-17T07:25:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ff6090ace557b24026b3a615d47af0709c65b03d69292abe1eff365c4e758d99","abstract_canon_sha256":"f2546bba2f61fd4cc03bb1771b78b01060e1aa4e8957da4830f2623c2c4a840b"},"schema_version":"1.0"},"canonical_sha256":"33dd9ad734a1f454778a78b72f6548f4df354bf4324a22740f7c85aed060aa9b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:02:16.668932Z","signature_b64":"UphDXjN4DGRIY5NLtWPNR89a/B97A33tNnUVqn5h41IlzzcJogpmirWVLgjg9/lzncip0ErltVip5MFTVedqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33dd9ad734a1f454778a78b72f6548f4df354bf4324a22740f7c85aed060aa9b","last_reissued_at":"2026-07-05T06:02:16.668469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:02:16.668469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.09087","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":"2026-07-05T06:02:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4dD0TwKmBO5fOTah2eX8X/M9asP++vI+DA+U9hW+L1VM3i1UBk5cuSNWqx2N6LEUn6cp5Vc8MRlffPPioT26Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T14:40:44.527182Z"},"content_sha256":"7a049753c52905230cf544d04c844363985692e707ce9122a2c5868ffbb4992b","schema_version":"1.0","event_id":"sha256:7a049753c52905230cf544d04c844363985692e707ce9122a2c5868ffbb4992b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GPOZVVZUUH2FI54KPC3S6ZKI6T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MDDL: A Framework for Reinforcement Learning-based Position Allocation in Multi-Channel Feed","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Dong Wang, Fan Yang, Guogang Liao, Xiaowen Shi, Xiaoxu Wu, Xingxing Wang, Yongkang Wang, Yuanying Cai, Ze Wang","submitted_at":"2023-04-17T07:25:58Z","abstract_excerpt":"Nowadays, the mainstream approach in position allocation system is to utilize a reinforcement learning model to allocate appropriate locations for items in various channels and then mix them into the feed. There are two types of data employed to train reinforcement learning (RL) model for position allocation, named strategy data and random data. Strategy data is collected from the current online model, it suffers from an imbalanced distribution of state-action pairs, resulting in severe overestimation problems during training. On the other hand, random data offers a more uniform distribution o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.09087","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/2304.09087/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":"2026-07-05T06:02:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EczVOUURi5d18DUi8TKmTvhBNKMOrfXVF8DwTRiWlLUb4qy+ywoKHa0B/0//p5LAXdp9x4tZAmJvUDF+HYh5Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T14:40:44.529644Z"},"content_sha256":"0ee2230d9b50a6e6321d70e099902e44649e28b4580f26436fdf38ce5cccfc6d","schema_version":"1.0","event_id":"sha256:0ee2230d9b50a6e6321d70e099902e44649e28b4580f26436fdf38ce5cccfc6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GPOZVVZUUH2FI54KPC3S6ZKI6T/bundle.json","state_url":"https://pith.science/pith/GPOZVVZUUH2FI54KPC3S6ZKI6T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GPOZVVZUUH2FI54KPC3S6ZKI6T/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":"2026-08-18T14:40:44Z","links":{"resolver":"https://pith.science/pith/GPOZVVZUUH2FI54KPC3S6ZKI6T","bundle":"https://pith.science/pith/GPOZVVZUUH2FI54KPC3S6ZKI6T/bundle.json","state":"https://pith.science/pith/GPOZVVZUUH2FI54KPC3S6ZKI6T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GPOZVVZUUH2FI54KPC3S6ZKI6T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GPOZVVZUUH2FI54KPC3S6ZKI6T","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":"f2546bba2f61fd4cc03bb1771b78b01060e1aa4e8957da4830f2623c2c4a840b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-04-17T07:25:58Z","title_canon_sha256":"ff6090ace557b24026b3a615d47af0709c65b03d69292abe1eff365c4e758d99"},"schema_version":"1.0","source":{"id":"2304.09087","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.09087","created_at":"2026-07-05T06:02:16Z"},{"alias_kind":"arxiv_version","alias_value":"2304.09087v1","created_at":"2026-07-05T06:02:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.09087","created_at":"2026-07-05T06:02:16Z"},{"alias_kind":"pith_short_12","alias_value":"GPOZVVZUUH2F","created_at":"2026-07-05T06:02:16Z"},{"alias_kind":"pith_short_16","alias_value":"GPOZVVZUUH2FI54K","created_at":"2026-07-05T06:02:16Z"},{"alias_kind":"pith_short_8","alias_value":"GPOZVVZU","created_at":"2026-07-05T06:02:16Z"}],"graph_snapshots":[{"event_id":"sha256:0ee2230d9b50a6e6321d70e099902e44649e28b4580f26436fdf38ce5cccfc6d","target":"graph","created_at":"2026-07-05T06:02:16Z","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/2304.09087/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Nowadays, the mainstream approach in position allocation system is to utilize a reinforcement learning model to allocate appropriate locations for items in various channels and then mix them into the feed. There are two types of data employed to train reinforcement learning (RL) model for position allocation, named strategy data and random data. Strategy data is collected from the current online model, it suffers from an imbalanced distribution of state-action pairs, resulting in severe overestimation problems during training. On the other hand, random data offers a more uniform distribution o","authors_text":"Dong Wang, Fan Yang, Guogang Liao, Xiaowen Shi, Xiaoxu Wu, Xingxing Wang, Yongkang Wang, Yuanying Cai, Ze Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-04-17T07:25:58Z","title":"MDDL: A Framework for Reinforcement Learning-based Position Allocation in Multi-Channel Feed"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.09087","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":"sha256:7a049753c52905230cf544d04c844363985692e707ce9122a2c5868ffbb4992b","target":"record","created_at":"2026-07-05T06:02:16Z","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":"f2546bba2f61fd4cc03bb1771b78b01060e1aa4e8957da4830f2623c2c4a840b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-04-17T07:25:58Z","title_canon_sha256":"ff6090ace557b24026b3a615d47af0709c65b03d69292abe1eff365c4e758d99"},"schema_version":"1.0","source":{"id":"2304.09087","kind":"arxiv","version":1}},"canonical_sha256":"33dd9ad734a1f454778a78b72f6548f4df354bf4324a22740f7c85aed060aa9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33dd9ad734a1f454778a78b72f6548f4df354bf4324a22740f7c85aed060aa9b","first_computed_at":"2026-07-05T06:02:16.668469Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:02:16.668469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UphDXjN4DGRIY5NLtWPNR89a/B97A33tNnUVqn5h41IlzzcJogpmirWVLgjg9/lzncip0ErltVip5MFTVedqDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:02:16.668932Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.09087","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a049753c52905230cf544d04c844363985692e707ce9122a2c5868ffbb4992b","sha256:0ee2230d9b50a6e6321d70e099902e44649e28b4580f26436fdf38ce5cccfc6d"],"state_sha256":"4c4d8dcd56c3feee9d856d2441028c0f4235a48945c1432d327ea30dae3ecf03"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YuxCJGWkyc5hj5bK3YhWoSKZ9jCGug+AoVxUGZ2XdAQ3/U0HvfwZ+4r2yFIMI2QNRClt7op/quzKQPoQoXkwAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T14:40:44.537212Z","bundle_sha256":"a8dd93df25e154a651426952138e97f9003d0887864437ea320ff74d94f51bde"}}