{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PNWDVA2AOQ6ZGTOP3HHNQ5ZFNS","short_pith_number":"pith:PNWDVA2A","canonical_record":{"source":{"id":"2411.14783","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T07:52:28Z","cross_cats_sorted":[],"title_canon_sha256":"0f90c6b8be8d4f83683227a3e9e0e1740b6ce0d45de639bc253bc588247b2200","abstract_canon_sha256":"d25ce8066db4de2ce0935d8722322c75f44098e986d7716f92fb2ff27571cab5"},"schema_version":"1.0"},"canonical_sha256":"7b6c3a8340743d934dcfd9ced877256ca1ade598d005624ffef736b8a57bfc41","source":{"kind":"arxiv","id":"2411.14783","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14783","created_at":"2026-07-05T12:04:29Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14783v4","created_at":"2026-07-05T12:04:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14783","created_at":"2026-07-05T12:04:29Z"},{"alias_kind":"pith_short_12","alias_value":"PNWDVA2AOQ6Z","created_at":"2026-07-05T12:04:29Z"},{"alias_kind":"pith_short_16","alias_value":"PNWDVA2AOQ6ZGTOP","created_at":"2026-07-05T12:04:29Z"},{"alias_kind":"pith_short_8","alias_value":"PNWDVA2A","created_at":"2026-07-05T12:04:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PNWDVA2AOQ6ZGTOP3HHNQ5ZFNS","target":"record","payload":{"canonical_record":{"source":{"id":"2411.14783","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T07:52:28Z","cross_cats_sorted":[],"title_canon_sha256":"0f90c6b8be8d4f83683227a3e9e0e1740b6ce0d45de639bc253bc588247b2200","abstract_canon_sha256":"d25ce8066db4de2ce0935d8722322c75f44098e986d7716f92fb2ff27571cab5"},"schema_version":"1.0"},"canonical_sha256":"7b6c3a8340743d934dcfd9ced877256ca1ade598d005624ffef736b8a57bfc41","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:29.322257Z","signature_b64":"OS3kJAQSOY62xJU2TJ3ou/Pkf1QY0zSloHFWnODBwDHNhIM2EjVVUqrmFaPTMeBhZAyB8+QhPCxDAeFu7KuiAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b6c3a8340743d934dcfd9ced877256ca1ade598d005624ffef736b8a57bfc41","last_reissued_at":"2026-07-05T12:04:29.321642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:29.321642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.14783","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:04:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ksvmzI3JHLQYNEHsNJFS5hSN9VcXqy9lNSB1vtC18zDA7LAE1eIgZre5mFqGU+3wfOstqLFiFhLn5Bj9Q69uAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T19:45:27.743756Z"},"content_sha256":"0623b08f3c68f78b6f8a52de6b3bb8a996b0d10a7f76be108fc3cbd94d7a3d2e","schema_version":"1.0","event_id":"sha256:0623b08f3c68f78b6f8a52de6b3bb8a996b0d10a7f76be108fc3cbd94d7a3d2e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PNWDVA2AOQ6ZGTOP3HHNQ5ZFNS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Segmenting Action-Value Functions Over Time-Scales in SARSA via TD($\\Delta$)","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mahammad Humayoo","submitted_at":"2024-11-22T07:52:28Z","abstract_excerpt":"In numerous episodic reinforcement learning (RL) environments, SARSA-based methodologies are employed to enhance policies aimed at maximizing returns over long horizons. Traditional SARSA algorithms face challenges in achieving an optimal balance between bias and variation, primarily due to their dependence on a single, constant discount factor ($\\eta$). This investigation enhances the temporal difference decomposition method, TD($\\Delta$), by applying it to the SARSA algorithm, now designated as SARSA($\\Delta$). SARSA is a widely used on-policy RL method that enhances action-value functions v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14783","kind":"arxiv","version":4},"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/2411.14783/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":"2026-07-05T12:04:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G6JZLMu/R57IDrO8nMF+4PD9frg09Ena5tmhfhEfWxko6mWRIW2K0mFuj0y9AUmpWqsojZcpVS2xDHJ90oCWBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T19:45:27.744778Z"},"content_sha256":"215b253d5681133ee87596e7437b159d3ea6b8494f459695d9f3069c3f030a81","schema_version":"1.0","event_id":"sha256:215b253d5681133ee87596e7437b159d3ea6b8494f459695d9f3069c3f030a81"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PNWDVA2AOQ6ZGTOP3HHNQ5ZFNS/bundle.json","state_url":"https://pith.science/pith/PNWDVA2AOQ6ZGTOP3HHNQ5ZFNS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PNWDVA2AOQ6ZGTOP3HHNQ5ZFNS/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":"2026-08-16T19:45:27Z","links":{"resolver":"https://pith.science/pith/PNWDVA2AOQ6ZGTOP3HHNQ5ZFNS","bundle":"https://pith.science/pith/PNWDVA2AOQ6ZGTOP3HHNQ5ZFNS/bundle.json","state":"https://pith.science/pith/PNWDVA2AOQ6ZGTOP3HHNQ5ZFNS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PNWDVA2AOQ6ZGTOP3HHNQ5ZFNS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PNWDVA2AOQ6ZGTOP3HHNQ5ZFNS","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":"d25ce8066db4de2ce0935d8722322c75f44098e986d7716f92fb2ff27571cab5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T07:52:28Z","title_canon_sha256":"0f90c6b8be8d4f83683227a3e9e0e1740b6ce0d45de639bc253bc588247b2200"},"schema_version":"1.0","source":{"id":"2411.14783","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14783","created_at":"2026-07-05T12:04:29Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14783v4","created_at":"2026-07-05T12:04:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14783","created_at":"2026-07-05T12:04:29Z"},{"alias_kind":"pith_short_12","alias_value":"PNWDVA2AOQ6Z","created_at":"2026-07-05T12:04:29Z"},{"alias_kind":"pith_short_16","alias_value":"PNWDVA2AOQ6ZGTOP","created_at":"2026-07-05T12:04:29Z"},{"alias_kind":"pith_short_8","alias_value":"PNWDVA2A","created_at":"2026-07-05T12:04:29Z"}],"graph_snapshots":[{"event_id":"sha256:215b253d5681133ee87596e7437b159d3ea6b8494f459695d9f3069c3f030a81","target":"graph","created_at":"2026-07-05T12:04:29Z","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/2411.14783/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In numerous episodic reinforcement learning (RL) environments, SARSA-based methodologies are employed to enhance policies aimed at maximizing returns over long horizons. Traditional SARSA algorithms face challenges in achieving an optimal balance between bias and variation, primarily due to their dependence on a single, constant discount factor ($\\eta$). This investigation enhances the temporal difference decomposition method, TD($\\Delta$), by applying it to the SARSA algorithm, now designated as SARSA($\\Delta$). SARSA is a widely used on-policy RL method that enhances action-value functions v","authors_text":"Mahammad Humayoo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T07:52:28Z","title":"Segmenting Action-Value Functions Over Time-Scales in SARSA via TD($\\Delta$)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14783","kind":"arxiv","version":4},"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":"sha256:0623b08f3c68f78b6f8a52de6b3bb8a996b0d10a7f76be108fc3cbd94d7a3d2e","target":"record","created_at":"2026-07-05T12:04:29Z","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":"d25ce8066db4de2ce0935d8722322c75f44098e986d7716f92fb2ff27571cab5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T07:52:28Z","title_canon_sha256":"0f90c6b8be8d4f83683227a3e9e0e1740b6ce0d45de639bc253bc588247b2200"},"schema_version":"1.0","source":{"id":"2411.14783","kind":"arxiv","version":4}},"canonical_sha256":"7b6c3a8340743d934dcfd9ced877256ca1ade598d005624ffef736b8a57bfc41","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b6c3a8340743d934dcfd9ced877256ca1ade598d005624ffef736b8a57bfc41","first_computed_at":"2026-07-05T12:04:29.321642Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:04:29.321642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OS3kJAQSOY62xJU2TJ3ou/Pkf1QY0zSloHFWnODBwDHNhIM2EjVVUqrmFaPTMeBhZAyB8+QhPCxDAeFu7KuiAA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:04:29.322257Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14783","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0623b08f3c68f78b6f8a52de6b3bb8a996b0d10a7f76be108fc3cbd94d7a3d2e","sha256:215b253d5681133ee87596e7437b159d3ea6b8494f459695d9f3069c3f030a81"],"state_sha256":"94a0cf1679b7766ea28362ee0be29a6a4543c745412f520e2b149de51e790bfd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dEM/eWn5i00LdRmRsAN3D69nyIV6nBuUDlYMEJcNJGZABvoB5WHw81eqOsTzgRpOEJVCcTCIhyn2vNbvEGFgAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T19:45:27.837083Z","bundle_sha256":"dc77c48e30febddbfb8f3635a1cfa89115779f4d3464f1234d8c6aa449c4fe27"}}