{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ZM6TFJ3IU5JWD4UH6DXFZMTTX3","short_pith_number":"pith:ZM6TFJ3I","canonical_record":{"source":{"id":"1802.06958","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NI","submitted_at":"2018-02-20T04:06:08Z","cross_cats_sorted":[],"title_canon_sha256":"a01e0ef7fccfc959f5773b464e49885ae88b0ae6d1a00b8a22fb256b0e4329cc","abstract_canon_sha256":"cf7e37f54533305b8205d27a75d0e2afa5eb5c37539e419c4dd2ef65c038413f"},"schema_version":"1.0"},"canonical_sha256":"cb3d32a768a75361f287f0ee5cb273bed40938cb02b3aedd3e01394c79c510fc","source":{"kind":"arxiv","id":"1802.06958","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06958","created_at":"2026-05-18T00:22:53Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06958v1","created_at":"2026-05-18T00:22:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06958","created_at":"2026-05-18T00:22:53Z"},{"alias_kind":"pith_short_12","alias_value":"ZM6TFJ3IU5JW","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZM6TFJ3IU5JWD4UH","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZM6TFJ3I","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ZM6TFJ3IU5JWD4UH6DXFZMTTX3","target":"record","payload":{"canonical_record":{"source":{"id":"1802.06958","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NI","submitted_at":"2018-02-20T04:06:08Z","cross_cats_sorted":[],"title_canon_sha256":"a01e0ef7fccfc959f5773b464e49885ae88b0ae6d1a00b8a22fb256b0e4329cc","abstract_canon_sha256":"cf7e37f54533305b8205d27a75d0e2afa5eb5c37539e419c4dd2ef65c038413f"},"schema_version":"1.0"},"canonical_sha256":"cb3d32a768a75361f287f0ee5cb273bed40938cb02b3aedd3e01394c79c510fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:53.879899Z","signature_b64":"ee27c4DxNOVFRbcTVvUD1T3iIzegSHEpyEBbvSsZ+1Qm9OmJd5RGQYa0PmiY9aeGPSG2BkSoPFWZydtTjspZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb3d32a768a75361f287f0ee5cb273bed40938cb02b3aedd3e01394c79c510fc","last_reissued_at":"2026-05-18T00:22:53.879411Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:53.879411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.06958","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":"2026-05-18T00:22:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WDgmFzKMByO4jgnG0Co49TPC9DFeEXv2v0HqlqNuGSxd3g9jSkgS8XulgAsK5r+mAUzB7C04vtF8YaT5+yKHDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T08:59:21.271484Z"},"content_sha256":"bcbd9db1e603a0d1655f40b30d75d564ce0d1d22779b0b711ffbfe6d8709ccaa","schema_version":"1.0","event_id":"sha256:bcbd9db1e603a0d1655f40b30d75d564ce0d1d22779b0b711ffbfe6d8709ccaa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ZM6TFJ3IU5JWD4UH6DXFZMTTX3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning for Dynamic Multichannel Access in Wireless Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NI","authors_text":"Bhaskar Krishnamachari, Hanpeng Liu, Pedro Henrique Gomes, Shangxing Wang","submitted_at":"2018-02-20T04:06:08Z","abstract_excerpt":"We consider a dynamic multichannel access problem, where multiple correlated channels follow an unknown joint Markov model. A user at each time slot selects a channel to transmit data and receives a reward based on the success or failure of the transmission. The objective is to find a policy that maximizes the expected long-term reward. The problem is formulated as a partially observable Markov decision process (POMDP) with unknown system dynamics. To overcome the challenges of unknown system dynamics as well as prohibitive computation, we apply the concept of reinforcement learning and implem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06958","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":""},"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":"2026-05-18T00:22:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BFAQfuUGpU1L4Sz+3UayOc8ReXU6VoRs0kBqIi8KF9579t+4eUUKavyCXXzOnZSQPVjW/GN1Q3ItYIz3aHEXAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T08:59:21.271828Z"},"content_sha256":"0ca0165f7f5ba4af8da492c5dbc7a641a7cf413a7a7c02d93baaf3edcdba6f53","schema_version":"1.0","event_id":"sha256:0ca0165f7f5ba4af8da492c5dbc7a641a7cf413a7a7c02d93baaf3edcdba6f53"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZM6TFJ3IU5JWD4UH6DXFZMTTX3/bundle.json","state_url":"https://pith.science/pith/ZM6TFJ3IU5JWD4UH6DXFZMTTX3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZM6TFJ3IU5JWD4UH6DXFZMTTX3/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":"2026-06-03T08:59:21Z","links":{"resolver":"https://pith.science/pith/ZM6TFJ3IU5JWD4UH6DXFZMTTX3","bundle":"https://pith.science/pith/ZM6TFJ3IU5JWD4UH6DXFZMTTX3/bundle.json","state":"https://pith.science/pith/ZM6TFJ3IU5JWD4UH6DXFZMTTX3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZM6TFJ3IU5JWD4UH6DXFZMTTX3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZM6TFJ3IU5JWD4UH6DXFZMTTX3","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":"cf7e37f54533305b8205d27a75d0e2afa5eb5c37539e419c4dd2ef65c038413f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NI","submitted_at":"2018-02-20T04:06:08Z","title_canon_sha256":"a01e0ef7fccfc959f5773b464e49885ae88b0ae6d1a00b8a22fb256b0e4329cc"},"schema_version":"1.0","source":{"id":"1802.06958","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06958","created_at":"2026-05-18T00:22:53Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06958v1","created_at":"2026-05-18T00:22:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06958","created_at":"2026-05-18T00:22:53Z"},{"alias_kind":"pith_short_12","alias_value":"ZM6TFJ3IU5JW","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZM6TFJ3IU5JWD4UH","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZM6TFJ3I","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:0ca0165f7f5ba4af8da492c5dbc7a641a7cf413a7a7c02d93baaf3edcdba6f53","target":"graph","created_at":"2026-05-18T00:22:53Z","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":"We consider a dynamic multichannel access problem, where multiple correlated channels follow an unknown joint Markov model. A user at each time slot selects a channel to transmit data and receives a reward based on the success or failure of the transmission. The objective is to find a policy that maximizes the expected long-term reward. The problem is formulated as a partially observable Markov decision process (POMDP) with unknown system dynamics. To overcome the challenges of unknown system dynamics as well as prohibitive computation, we apply the concept of reinforcement learning and implem","authors_text":"Bhaskar Krishnamachari, Hanpeng Liu, Pedro Henrique Gomes, Shangxing Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NI","submitted_at":"2018-02-20T04:06:08Z","title":"Deep Reinforcement Learning for Dynamic Multichannel Access in Wireless Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06958","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:bcbd9db1e603a0d1655f40b30d75d564ce0d1d22779b0b711ffbfe6d8709ccaa","target":"record","created_at":"2026-05-18T00:22:53Z","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":"cf7e37f54533305b8205d27a75d0e2afa5eb5c37539e419c4dd2ef65c038413f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NI","submitted_at":"2018-02-20T04:06:08Z","title_canon_sha256":"a01e0ef7fccfc959f5773b464e49885ae88b0ae6d1a00b8a22fb256b0e4329cc"},"schema_version":"1.0","source":{"id":"1802.06958","kind":"arxiv","version":1}},"canonical_sha256":"cb3d32a768a75361f287f0ee5cb273bed40938cb02b3aedd3e01394c79c510fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb3d32a768a75361f287f0ee5cb273bed40938cb02b3aedd3e01394c79c510fc","first_computed_at":"2026-05-18T00:22:53.879411Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:53.879411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ee27c4DxNOVFRbcTVvUD1T3iIzegSHEpyEBbvSsZ+1Qm9OmJd5RGQYa0PmiY9aeGPSG2BkSoPFWZydtTjspZCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:53.879899Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.06958","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bcbd9db1e603a0d1655f40b30d75d564ce0d1d22779b0b711ffbfe6d8709ccaa","sha256:0ca0165f7f5ba4af8da492c5dbc7a641a7cf413a7a7c02d93baaf3edcdba6f53"],"state_sha256":"dbd9f212247f00c62ae6b571e2f0556e3ab650e053af04373b268111bb346996"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Rm3ks4E2J4MYUJebYm+DcfpJ0CmEqzZC9L6boprxcIKi2t1tYp7+HxIJjZY8K/6lGsV80X/7tzWR1HB0wCOAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T08:59:21.273801Z","bundle_sha256":"e21e621e37402b83ce1b6ab1917dc5aadadfe88ea76911a5db63c272c72059f7"}}