{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZQT6IKMBN24K3G5YJY7755XTBK","short_pith_number":"pith:ZQT6IKMB","canonical_record":{"source":{"id":"2406.01838","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T23:10:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"50d53d6992d628939f47757873cb0e10e5157debc5249b6ada4f4eb27d3f79f0","abstract_canon_sha256":"77dbf3f22f0e26cd66a1e8f0eb842299b09fab438ca104baf09228b72e70a5d0"},"schema_version":"1.0"},"canonical_sha256":"cc27e429816eb8ad9bb84e3ffef6f30abea872921f83c59c2827242bd86bee6f","source":{"kind":"arxiv","id":"2406.01838","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01838","created_at":"2026-07-05T09:10:00Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01838v2","created_at":"2026-07-05T09:10:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01838","created_at":"2026-07-05T09:10:00Z"},{"alias_kind":"pith_short_12","alias_value":"ZQT6IKMBN24K","created_at":"2026-07-05T09:10:00Z"},{"alias_kind":"pith_short_16","alias_value":"ZQT6IKMBN24K3G5Y","created_at":"2026-07-05T09:10:00Z"},{"alias_kind":"pith_short_8","alias_value":"ZQT6IKMB","created_at":"2026-07-05T09:10:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZQT6IKMBN24K3G5YJY7755XTBK","target":"record","payload":{"canonical_record":{"source":{"id":"2406.01838","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T23:10:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"50d53d6992d628939f47757873cb0e10e5157debc5249b6ada4f4eb27d3f79f0","abstract_canon_sha256":"77dbf3f22f0e26cd66a1e8f0eb842299b09fab438ca104baf09228b72e70a5d0"},"schema_version":"1.0"},"canonical_sha256":"cc27e429816eb8ad9bb84e3ffef6f30abea872921f83c59c2827242bd86bee6f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:00.209445Z","signature_b64":"R+zaSlDPUWvHLQEIIdPp8BNCkY1H5FT7C+KhWbVgjXAIP01i706LkJSUxsOIrRkaovHfgw8bRK4hT2O/sHhhBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc27e429816eb8ad9bb84e3ffef6f30abea872921f83c59c2827242bd86bee6f","last_reissued_at":"2026-07-05T09:10:00.208921Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:00.208921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.01838","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":"2026-07-05T09:10:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k6BGrBzKM0ltm/uEvDfqh72tF4h+ZUCeenrIYAnt9qXPlB6SeidEtEqAqgvSlK5k2xWdhVsz7Zd2gb/7eU6/Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T03:39:43.746295Z"},"content_sha256":"af54bb01e798eeae99393cba82d635b704c1d942dcca82a055ce976e221c390e","schema_version":"1.0","event_id":"sha256:af54bb01e798eeae99393cba82d635b704c1d942dcca82a055ce976e221c390e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZQT6IKMBN24K3G5YJY7755XTBK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning the Target Network in Function Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kavosh Asadi, Ming Yin, Rasool Fakoor, Shoham Sabach, Yao Liu","submitted_at":"2024-06-03T23:10:35Z","abstract_excerpt":"We focus on the task of learning the value function in the reinforcement learning (RL) setting. This task is often solved by updating a pair of online and target networks while ensuring that the parameters of these two networks are equivalent. We propose Lookahead-Replicate (LR), a new value-function approximation algorithm that is agnostic to this parameter-space equivalence. Instead, the LR algorithm is designed to maintain an equivalence between the two networks in the function space. This value-based equivalence is obtained by employing a new target-network update. We show that LR leads to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01838","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.01838/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":"2026-07-05T09:10:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fMRTqrMJx7OxR03WWpBUcOuNw4RlB7y7aERs3/CKhi3KiFtaaD82rNotTf8jmouGO1+3UrzhSyA9tvZNiGDNDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T03:39:43.746680Z"},"content_sha256":"50996d796db077200ea85336e6802f71c10183c0c5bdaa2ee8a1aaaf935d3633","schema_version":"1.0","event_id":"sha256:50996d796db077200ea85336e6802f71c10183c0c5bdaa2ee8a1aaaf935d3633"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZQT6IKMBN24K3G5YJY7755XTBK/bundle.json","state_url":"https://pith.science/pith/ZQT6IKMBN24K3G5YJY7755XTBK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZQT6IKMBN24K3G5YJY7755XTBK/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":"2026-08-21T03:39:43Z","links":{"resolver":"https://pith.science/pith/ZQT6IKMBN24K3G5YJY7755XTBK","bundle":"https://pith.science/pith/ZQT6IKMBN24K3G5YJY7755XTBK/bundle.json","state":"https://pith.science/pith/ZQT6IKMBN24K3G5YJY7755XTBK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZQT6IKMBN24K3G5YJY7755XTBK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZQT6IKMBN24K3G5YJY7755XTBK","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":"77dbf3f22f0e26cd66a1e8f0eb842299b09fab438ca104baf09228b72e70a5d0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T23:10:35Z","title_canon_sha256":"50d53d6992d628939f47757873cb0e10e5157debc5249b6ada4f4eb27d3f79f0"},"schema_version":"1.0","source":{"id":"2406.01838","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01838","created_at":"2026-07-05T09:10:00Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01838v2","created_at":"2026-07-05T09:10:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01838","created_at":"2026-07-05T09:10:00Z"},{"alias_kind":"pith_short_12","alias_value":"ZQT6IKMBN24K","created_at":"2026-07-05T09:10:00Z"},{"alias_kind":"pith_short_16","alias_value":"ZQT6IKMBN24K3G5Y","created_at":"2026-07-05T09:10:00Z"},{"alias_kind":"pith_short_8","alias_value":"ZQT6IKMB","created_at":"2026-07-05T09:10:00Z"}],"graph_snapshots":[{"event_id":"sha256:50996d796db077200ea85336e6802f71c10183c0c5bdaa2ee8a1aaaf935d3633","target":"graph","created_at":"2026-07-05T09:10:00Z","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/2406.01838/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We focus on the task of learning the value function in the reinforcement learning (RL) setting. This task is often solved by updating a pair of online and target networks while ensuring that the parameters of these two networks are equivalent. We propose Lookahead-Replicate (LR), a new value-function approximation algorithm that is agnostic to this parameter-space equivalence. Instead, the LR algorithm is designed to maintain an equivalence between the two networks in the function space. This value-based equivalence is obtained by employing a new target-network update. We show that LR leads to","authors_text":"Kavosh Asadi, Ming Yin, Rasool Fakoor, Shoham Sabach, Yao Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T23:10:35Z","title":"Learning the Target Network in Function Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01838","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:af54bb01e798eeae99393cba82d635b704c1d942dcca82a055ce976e221c390e","target":"record","created_at":"2026-07-05T09:10:00Z","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":"77dbf3f22f0e26cd66a1e8f0eb842299b09fab438ca104baf09228b72e70a5d0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T23:10:35Z","title_canon_sha256":"50d53d6992d628939f47757873cb0e10e5157debc5249b6ada4f4eb27d3f79f0"},"schema_version":"1.0","source":{"id":"2406.01838","kind":"arxiv","version":2}},"canonical_sha256":"cc27e429816eb8ad9bb84e3ffef6f30abea872921f83c59c2827242bd86bee6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc27e429816eb8ad9bb84e3ffef6f30abea872921f83c59c2827242bd86bee6f","first_computed_at":"2026-07-05T09:10:00.208921Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:00.208921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R+zaSlDPUWvHLQEIIdPp8BNCkY1H5FT7C+KhWbVgjXAIP01i706LkJSUxsOIrRkaovHfgw8bRK4hT2O/sHhhBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:00.209445Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01838","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af54bb01e798eeae99393cba82d635b704c1d942dcca82a055ce976e221c390e","sha256:50996d796db077200ea85336e6802f71c10183c0c5bdaa2ee8a1aaaf935d3633"],"state_sha256":"2247f70dbdb355efb2ad855471c1e6e86277af3c805c03b4aa16b9e8658fecb1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/xiWIRvg6CwesFtISQTeuks3YLs+WhZs3pM1eAUUEFlMN213SVcCu5q57ZjgF1Uk4Dv/Yy5mAhaN+akv3RE9CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T03:39:43.749063Z","bundle_sha256":"7ec929f284c9ae6fb323fc2f2ccc1a31890feec7d22c5226c721c9ebce06c24c"}}