{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:6U7M2QBX3WYVGCBQ35Q77AX73N","short_pith_number":"pith:6U7M2QBX","canonical_record":{"source":{"id":"1512.01124","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-03T15:51:30Z","cross_cats_sorted":["cs.HC","cs.LG"],"title_canon_sha256":"d1d5e977d92bfe509a7b9ceb33f9e119be059eaa292650bf652b974df5a69999","abstract_canon_sha256":"5bd4e9e1e299ecc7a383815c4f55b9050c5b5d0211a8f8c91845c526d2da64b4"},"schema_version":"1.0"},"canonical_sha256":"f53ecd4037ddb1530830df61ff82ffdb7bcf444f1c4b90bee829ff7816b01692","source":{"kind":"arxiv","id":"1512.01124","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.01124","created_at":"2026-05-18T01:24:14Z"},{"alias_kind":"arxiv_version","alias_value":"1512.01124v2","created_at":"2026-05-18T01:24:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.01124","created_at":"2026-05-18T01:24:14Z"},{"alias_kind":"pith_short_12","alias_value":"6U7M2QBX3WYV","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"6U7M2QBX3WYVGCBQ","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"6U7M2QBX","created_at":"2026-05-18T12:29:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:6U7M2QBX3WYVGCBQ35Q77AX73N","target":"record","payload":{"canonical_record":{"source":{"id":"1512.01124","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-03T15:51:30Z","cross_cats_sorted":["cs.HC","cs.LG"],"title_canon_sha256":"d1d5e977d92bfe509a7b9ceb33f9e119be059eaa292650bf652b974df5a69999","abstract_canon_sha256":"5bd4e9e1e299ecc7a383815c4f55b9050c5b5d0211a8f8c91845c526d2da64b4"},"schema_version":"1.0"},"canonical_sha256":"f53ecd4037ddb1530830df61ff82ffdb7bcf444f1c4b90bee829ff7816b01692","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:24:14.061303Z","signature_b64":"qdABkhr8wlvZBCm9U5pysVyThAnnItvA6Uf2yu0C14EqkDEtzktqe+FdgGNfGNWH9Sf8MInG2ZTh/LJeAF4hCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f53ecd4037ddb1530830df61ff82ffdb7bcf444f1c4b90bee829ff7816b01692","last_reissued_at":"2026-05-18T01:24:14.060663Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:24:14.060663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1512.01124","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:24:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/i6BWIlPbZewy9KE3IQkpFCnemVfpTHn5FB10pjSExWXxxsnBHOIylweA8kiJEjJiQF7s4udnhxs798C+vmXCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T01:09:35.040846Z"},"content_sha256":"2af1103b7edc4741cf8e72ec91b2ce168e44a333899ce6475ce15888aa23d1b9","schema_version":"1.0","event_id":"sha256:2af1103b7edc4741cf8e72ec91b2ce168e44a333899ce6475ce15888aa23d1b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:6U7M2QBX3WYVGCBQ35Q77AX73N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning with Attention for Slate Markov Decision Processes with High-Dimensional States and Actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.LG"],"primary_cat":"cs.AI","authors_text":"Ben Coppin, Daniel Visentin, Gabriel Dulac-Arnold, Peter Sunehag, Richard Evans, Yori Zwols","submitted_at":"2015-12-03T15:51:30Z","abstract_excerpt":"Many real-world problems come with action spaces represented as feature vectors. Although high-dimensional control is a largely unsolved problem, there has recently been progress for modest dimensionalities. Here we report on a successful attempt at addressing problems of dimensionality as high as $2000$, of a particular form. Motivated by important applications such as recommendation systems that do not fit the standard reinforcement learning frameworks, we introduce Slate Markov Decision Processes (slate-MDPs). A Slate-MDP is an MDP with a combinatorial action space consisting of slates (tup"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.01124","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T01:24:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MlWtEl1ieA5V6tsNeKRBkyI4RyM5mSKaR4wmzVt+uCEKL6oStN1H8fM+InhSTexDwi6S+jVeoY1N7NYU4UFpDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T01:09:35.041494Z"},"content_sha256":"486d682bea8d59c99b2fda16d91d9f69e2975000082ca88aaa8e6ee600c65f40","schema_version":"1.0","event_id":"sha256:486d682bea8d59c99b2fda16d91d9f69e2975000082ca88aaa8e6ee600c65f40"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6U7M2QBX3WYVGCBQ35Q77AX73N/bundle.json","state_url":"https://pith.science/pith/6U7M2QBX3WYVGCBQ35Q77AX73N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6U7M2QBX3WYVGCBQ35Q77AX73N/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":"2026-05-26T01:09:35Z","links":{"resolver":"https://pith.science/pith/6U7M2QBX3WYVGCBQ35Q77AX73N","bundle":"https://pith.science/pith/6U7M2QBX3WYVGCBQ35Q77AX73N/bundle.json","state":"https://pith.science/pith/6U7M2QBX3WYVGCBQ35Q77AX73N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6U7M2QBX3WYVGCBQ35Q77AX73N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:6U7M2QBX3WYVGCBQ35Q77AX73N","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":"5bd4e9e1e299ecc7a383815c4f55b9050c5b5d0211a8f8c91845c526d2da64b4","cross_cats_sorted":["cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-03T15:51:30Z","title_canon_sha256":"d1d5e977d92bfe509a7b9ceb33f9e119be059eaa292650bf652b974df5a69999"},"schema_version":"1.0","source":{"id":"1512.01124","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.01124","created_at":"2026-05-18T01:24:14Z"},{"alias_kind":"arxiv_version","alias_value":"1512.01124v2","created_at":"2026-05-18T01:24:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.01124","created_at":"2026-05-18T01:24:14Z"},{"alias_kind":"pith_short_12","alias_value":"6U7M2QBX3WYV","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"6U7M2QBX3WYVGCBQ","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"6U7M2QBX","created_at":"2026-05-18T12:29:07Z"}],"graph_snapshots":[{"event_id":"sha256:486d682bea8d59c99b2fda16d91d9f69e2975000082ca88aaa8e6ee600c65f40","target":"graph","created_at":"2026-05-18T01:24:14Z","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"},"paper":{"abstract_excerpt":"Many real-world problems come with action spaces represented as feature vectors. Although high-dimensional control is a largely unsolved problem, there has recently been progress for modest dimensionalities. Here we report on a successful attempt at addressing problems of dimensionality as high as $2000$, of a particular form. Motivated by important applications such as recommendation systems that do not fit the standard reinforcement learning frameworks, we introduce Slate Markov Decision Processes (slate-MDPs). A Slate-MDP is an MDP with a combinatorial action space consisting of slates (tup","authors_text":"Ben Coppin, Daniel Visentin, Gabriel Dulac-Arnold, Peter Sunehag, Richard Evans, Yori Zwols","cross_cats":["cs.HC","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-03T15:51:30Z","title":"Deep Reinforcement Learning with Attention for Slate Markov Decision Processes with High-Dimensional States and Actions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.01124","kind":"arxiv","version":2},"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":"sha256:2af1103b7edc4741cf8e72ec91b2ce168e44a333899ce6475ce15888aa23d1b9","target":"record","created_at":"2026-05-18T01:24:14Z","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":"5bd4e9e1e299ecc7a383815c4f55b9050c5b5d0211a8f8c91845c526d2da64b4","cross_cats_sorted":["cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-03T15:51:30Z","title_canon_sha256":"d1d5e977d92bfe509a7b9ceb33f9e119be059eaa292650bf652b974df5a69999"},"schema_version":"1.0","source":{"id":"1512.01124","kind":"arxiv","version":2}},"canonical_sha256":"f53ecd4037ddb1530830df61ff82ffdb7bcf444f1c4b90bee829ff7816b01692","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f53ecd4037ddb1530830df61ff82ffdb7bcf444f1c4b90bee829ff7816b01692","first_computed_at":"2026-05-18T01:24:14.060663Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:24:14.060663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qdABkhr8wlvZBCm9U5pysVyThAnnItvA6Uf2yu0C14EqkDEtzktqe+FdgGNfGNWH9Sf8MInG2ZTh/LJeAF4hCA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:24:14.061303Z","signed_message":"canonical_sha256_bytes"},"source_id":"1512.01124","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2af1103b7edc4741cf8e72ec91b2ce168e44a333899ce6475ce15888aa23d1b9","sha256:486d682bea8d59c99b2fda16d91d9f69e2975000082ca88aaa8e6ee600c65f40"],"state_sha256":"98207903bc1956fef8d845c3d3faaf49c992fe63f63e3d95647b7d45fa7deebf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ek4tvcTKEHhVyuUtCtIU2dQ3IKGGCU3WyOBt4Uf46lHAmTuRoLV1MhiFfhxOP2SBTO39ptyFVxOCLMZExE2/BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T01:09:35.044965Z","bundle_sha256":"eb8db01ca7109a844d226bba698b9b98a85bf93977ac20af47026d7d85fbb125"}}