{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZNTGZ7IRJI6NMT4I56P7TVZD7F","short_pith_number":"pith:ZNTGZ7IR","canonical_record":{"source":{"id":"2607.19397","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-04T05:45:32Z","cross_cats_sorted":[],"title_canon_sha256":"a711cf2e8b6e18b7d8b2fe851c538e3f37d69c8578aa8700dc392b202cc63ea9","abstract_canon_sha256":"bf264191bf41c5233630903db9609e0f2be4962081a7c94e901ef85a28d772ac"},"schema_version":"1.0"},"canonical_sha256":"cb666cfd114a3cd64f88ef9ff9d723f963c0cc09ab0dd70f5bc169e1dae7f0ed","source":{"kind":"arxiv","id":"2607.19397","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.19397","created_at":"2026-07-23T00:23:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.19397v1","created_at":"2026-07-23T00:23:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19397","created_at":"2026-07-23T00:23:47Z"},{"alias_kind":"pith_short_12","alias_value":"ZNTGZ7IRJI6N","created_at":"2026-07-23T00:23:47Z"},{"alias_kind":"pith_short_16","alias_value":"ZNTGZ7IRJI6NMT4I","created_at":"2026-07-23T00:23:47Z"},{"alias_kind":"pith_short_8","alias_value":"ZNTGZ7IR","created_at":"2026-07-23T00:23:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZNTGZ7IRJI6NMT4I56P7TVZD7F","target":"record","payload":{"canonical_record":{"source":{"id":"2607.19397","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-04T05:45:32Z","cross_cats_sorted":[],"title_canon_sha256":"a711cf2e8b6e18b7d8b2fe851c538e3f37d69c8578aa8700dc392b202cc63ea9","abstract_canon_sha256":"bf264191bf41c5233630903db9609e0f2be4962081a7c94e901ef85a28d772ac"},"schema_version":"1.0"},"canonical_sha256":"cb666cfd114a3cd64f88ef9ff9d723f963c0cc09ab0dd70f5bc169e1dae7f0ed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T00:23:47.974149Z","signature_b64":"A1vihQOzCcR7PAeH+WdS6ZslasIOLR2gvd4OFOu/xtGcezcbyE7Doe8MbyTXV4kYeN+EhpYKL0cBbtdLXr9CDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb666cfd114a3cd64f88ef9ff9d723f963c0cc09ab0dd70f5bc169e1dae7f0ed","last_reissued_at":"2026-07-23T00:23:47.973324Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T00:23:47.973324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.19397","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":"2026-07-23T00:23:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZydnAu9F/sA4mb9nsrnJNMxuGaxuS/ZkmuxX+5S1TtWxptgO7TDyHwuKX3XFII8L34SY3lfk2NDCpvHTxUNUCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:51:53.601495Z"},"content_sha256":"9e5198a62e7ecb27d2ce5a2d29f84ab56b92e6444038daa2b75828e33b4c0628","schema_version":"1.0","event_id":"sha256:9e5198a62e7ecb27d2ce5a2d29f84ab56b92e6444038daa2b75828e33b4c0628"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZNTGZ7IRJI6NMT4I56P7TVZD7F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Memory Merge DQN: Sensitivity Weighted Target Updates for Stable Value Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adrian Ly, Francisco Cruz, Peter Vamplew, Richard Dazeley, Sunil Aryal","submitted_at":"2026-07-04T05:45:32Z","abstract_excerpt":"Deep Q-networks use target networks to stabilise bootstrapped value learning, but the standard hard copy update also introduces a tradeoff. Holding the target network fixed, improves short term stability, yet each hard update abruptly replaces the target parameters with the newest online network and discards recent parameter history. This can produce sudden changes in the bootstrap target and may remove value function structure that remains useful later in training. This paper introduces Memory Merge DQN, a target network update mechanism that maintains a short memory of recent historical onli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19397","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/2607.19397/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":"2026-07-23T00:23:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KMI3s/cO+c9bmbzsUd1N9V5T8i2j/pIfhGPecThoxtM7Dy/fPaDOKoyG/ppCIr4jO0p8/ET2JXuWR9ATuX7oBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:51:53.602082Z"},"content_sha256":"b2f25ed71d443e7ac55239c50e973aa57d3b461b256043e08f9a7d6139170a73","schema_version":"1.0","event_id":"sha256:b2f25ed71d443e7ac55239c50e973aa57d3b461b256043e08f9a7d6139170a73"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZNTGZ7IRJI6NMT4I56P7TVZD7F/bundle.json","state_url":"https://pith.science/pith/ZNTGZ7IRJI6NMT4I56P7TVZD7F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZNTGZ7IRJI6NMT4I56P7TVZD7F/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":"2026-08-09T19:51:53Z","links":{"resolver":"https://pith.science/pith/ZNTGZ7IRJI6NMT4I56P7TVZD7F","bundle":"https://pith.science/pith/ZNTGZ7IRJI6NMT4I56P7TVZD7F/bundle.json","state":"https://pith.science/pith/ZNTGZ7IRJI6NMT4I56P7TVZD7F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZNTGZ7IRJI6NMT4I56P7TVZD7F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZNTGZ7IRJI6NMT4I56P7TVZD7F","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":"bf264191bf41c5233630903db9609e0f2be4962081a7c94e901ef85a28d772ac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-04T05:45:32Z","title_canon_sha256":"a711cf2e8b6e18b7d8b2fe851c538e3f37d69c8578aa8700dc392b202cc63ea9"},"schema_version":"1.0","source":{"id":"2607.19397","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.19397","created_at":"2026-07-23T00:23:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.19397v1","created_at":"2026-07-23T00:23:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19397","created_at":"2026-07-23T00:23:47Z"},{"alias_kind":"pith_short_12","alias_value":"ZNTGZ7IRJI6N","created_at":"2026-07-23T00:23:47Z"},{"alias_kind":"pith_short_16","alias_value":"ZNTGZ7IRJI6NMT4I","created_at":"2026-07-23T00:23:47Z"},{"alias_kind":"pith_short_8","alias_value":"ZNTGZ7IR","created_at":"2026-07-23T00:23:47Z"}],"graph_snapshots":[{"event_id":"sha256:b2f25ed71d443e7ac55239c50e973aa57d3b461b256043e08f9a7d6139170a73","target":"graph","created_at":"2026-07-23T00:23:47Z","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/2607.19397/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Q-networks use target networks to stabilise bootstrapped value learning, but the standard hard copy update also introduces a tradeoff. Holding the target network fixed, improves short term stability, yet each hard update abruptly replaces the target parameters with the newest online network and discards recent parameter history. This can produce sudden changes in the bootstrap target and may remove value function structure that remains useful later in training. This paper introduces Memory Merge DQN, a target network update mechanism that maintains a short memory of recent historical onli","authors_text":"Adrian Ly, Francisco Cruz, Peter Vamplew, Richard Dazeley, Sunil Aryal","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-04T05:45:32Z","title":"Memory Merge DQN: Sensitivity Weighted Target Updates for Stable Value Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19397","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":"sha256:9e5198a62e7ecb27d2ce5a2d29f84ab56b92e6444038daa2b75828e33b4c0628","target":"record","created_at":"2026-07-23T00:23:47Z","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":"bf264191bf41c5233630903db9609e0f2be4962081a7c94e901ef85a28d772ac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-04T05:45:32Z","title_canon_sha256":"a711cf2e8b6e18b7d8b2fe851c538e3f37d69c8578aa8700dc392b202cc63ea9"},"schema_version":"1.0","source":{"id":"2607.19397","kind":"arxiv","version":1}},"canonical_sha256":"cb666cfd114a3cd64f88ef9ff9d723f963c0cc09ab0dd70f5bc169e1dae7f0ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb666cfd114a3cd64f88ef9ff9d723f963c0cc09ab0dd70f5bc169e1dae7f0ed","first_computed_at":"2026-07-23T00:23:47.973324Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-23T00:23:47.973324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A1vihQOzCcR7PAeH+WdS6ZslasIOLR2gvd4OFOu/xtGcezcbyE7Doe8MbyTXV4kYeN+EhpYKL0cBbtdLXr9CDQ==","signature_status":"signed_v1","signed_at":"2026-07-23T00:23:47.974149Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.19397","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e5198a62e7ecb27d2ce5a2d29f84ab56b92e6444038daa2b75828e33b4c0628","sha256:b2f25ed71d443e7ac55239c50e973aa57d3b461b256043e08f9a7d6139170a73"],"state_sha256":"c28b47900341b9a55f03f7118d9eee71cd033f2c0ebf447fd00a037447ee11c4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+p5R1SJIZzmFE/CA3oFGSy+vjOgHLZdiF5v9qLCW/84Ask7GTjJD1r4iA6FvpCTpubOow0liLTqL7BtJHefHCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T19:51:53.606169Z","bundle_sha256":"64745a0a62f59d697152a0c739fe2aa628aceb64e3a0d55d3866cf1949c800e3"}}