{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5OI54RGS5LEAWK74PE5SAV7P67","short_pith_number":"pith:5OI54RGS","canonical_record":{"source":{"id":"2407.18913","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-26T17:59:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ed93a3298a922f2ba46cba5e0be3316493d503c8844c8d1ad46e963008274624","abstract_canon_sha256":"99552c720ffa12b6cbc0f5d8078d176484c14a5bcc0f38bcb9ca80b07342bae0"},"schema_version":"1.0"},"canonical_sha256":"eb91de44d2eac80b2bfc793b2057eff7e2323fe5efd77a046aafa24626d3d082","source":{"kind":"arxiv","id":"2407.18913","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.18913","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"arxiv_version","alias_value":"2407.18913v2","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18913","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"pith_short_12","alias_value":"5OI54RGS5LEA","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"pith_short_16","alias_value":"5OI54RGS5LEAWK74","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"pith_short_8","alias_value":"5OI54RGS","created_at":"2026-07-05T09:19:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5OI54RGS5LEAWK74PE5SAV7P67","target":"record","payload":{"canonical_record":{"source":{"id":"2407.18913","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-26T17:59:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ed93a3298a922f2ba46cba5e0be3316493d503c8844c8d1ad46e963008274624","abstract_canon_sha256":"99552c720ffa12b6cbc0f5d8078d176484c14a5bcc0f38bcb9ca80b07342bae0"},"schema_version":"1.0"},"canonical_sha256":"eb91de44d2eac80b2bfc793b2057eff7e2323fe5efd77a046aafa24626d3d082","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:11.557752Z","signature_b64":"+Lwdkzg+HNwsJnqwU6Y0wvY0f6o7Ip0RasDtc1AOjlcxQ/mFam2tx0Ey7aItka9S2BpSlG5IiE7HyEfQIv3tCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb91de44d2eac80b2bfc793b2057eff7e2323fe5efd77a046aafa24626d3d082","last_reissued_at":"2026-07-05T09:19:11.557262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:11.557262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.18913","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":"2026-07-05T09:19:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M/rkRHnYQaJmJ/fbd2KWUmhD1l1sawnvf3f22yIsNJwgy7KQEAEbH4XyX2+i3H/NP7ekQ2XYYKQYFRQ4QjsXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T21:51:14.558368Z"},"content_sha256":"44e34423ab5302f82f482342f5f5a295112d5e2138980b239b5ad61a0b95da22","schema_version":"1.0","event_id":"sha256:44e34423ab5302f82f482342f5f5a295112d5e2138980b239b5ad61a0b95da22"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5OI54RGS5LEAWK74PE5SAV7P67","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SOAP-RL: Sequential Option Advantage Propagation for Reinforcement Learning in POMDP Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jo\\~ao F. Henriques, Shu Ishida","submitted_at":"2024-07-26T17:59:55Z","abstract_excerpt":"This work compares ways of extending Reinforcement Learning algorithms to Partially Observed Markov Decision Processes (POMDPs) with options. One view of options is as temporally extended action, which can be realized as a memory that allows the agent to retain historical information beyond the policy's context window. While option assignment could be handled using heuristics and hand-crafted objectives, learning temporally consistent options and associated sub-policies without explicit supervision is a challenge. Two algorithms, PPOEM and SOAP, are proposed and studied in depth to address thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18913","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/2407.18913/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":"2026-07-05T09:19:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f7iGIwFoQOdMAzR1iXqNpgJr6SnOgqM2kZFBqmRxJi6WpfGIJqyrQlvQVFxHOqo4EZCYHxBAZOSS2lJR2NX2BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T21:51:14.558765Z"},"content_sha256":"2d599daf4f7b0b06e60d1e274fa3367c352151adb3a653fc54337357a2bf0aa0","schema_version":"1.0","event_id":"sha256:2d599daf4f7b0b06e60d1e274fa3367c352151adb3a653fc54337357a2bf0aa0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5OI54RGS5LEAWK74PE5SAV7P67/bundle.json","state_url":"https://pith.science/pith/5OI54RGS5LEAWK74PE5SAV7P67/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5OI54RGS5LEAWK74PE5SAV7P67/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":"2026-07-11T21:51:14Z","links":{"resolver":"https://pith.science/pith/5OI54RGS5LEAWK74PE5SAV7P67","bundle":"https://pith.science/pith/5OI54RGS5LEAWK74PE5SAV7P67/bundle.json","state":"https://pith.science/pith/5OI54RGS5LEAWK74PE5SAV7P67/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5OI54RGS5LEAWK74PE5SAV7P67/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5OI54RGS5LEAWK74PE5SAV7P67","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":"99552c720ffa12b6cbc0f5d8078d176484c14a5bcc0f38bcb9ca80b07342bae0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-26T17:59:55Z","title_canon_sha256":"ed93a3298a922f2ba46cba5e0be3316493d503c8844c8d1ad46e963008274624"},"schema_version":"1.0","source":{"id":"2407.18913","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.18913","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"arxiv_version","alias_value":"2407.18913v2","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18913","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"pith_short_12","alias_value":"5OI54RGS5LEA","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"pith_short_16","alias_value":"5OI54RGS5LEAWK74","created_at":"2026-07-05T09:19:11Z"},{"alias_kind":"pith_short_8","alias_value":"5OI54RGS","created_at":"2026-07-05T09:19:11Z"}],"graph_snapshots":[{"event_id":"sha256:2d599daf4f7b0b06e60d1e274fa3367c352151adb3a653fc54337357a2bf0aa0","target":"graph","created_at":"2026-07-05T09:19:11Z","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/2407.18913/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work compares ways of extending Reinforcement Learning algorithms to Partially Observed Markov Decision Processes (POMDPs) with options. One view of options is as temporally extended action, which can be realized as a memory that allows the agent to retain historical information beyond the policy's context window. While option assignment could be handled using heuristics and hand-crafted objectives, learning temporally consistent options and associated sub-policies without explicit supervision is a challenge. Two algorithms, PPOEM and SOAP, are proposed and studied in depth to address thi","authors_text":"Jo\\~ao F. Henriques, Shu Ishida","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-26T17:59:55Z","title":"SOAP-RL: Sequential Option Advantage Propagation for Reinforcement Learning in POMDP Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18913","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":"sha256:44e34423ab5302f82f482342f5f5a295112d5e2138980b239b5ad61a0b95da22","target":"record","created_at":"2026-07-05T09:19:11Z","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":"99552c720ffa12b6cbc0f5d8078d176484c14a5bcc0f38bcb9ca80b07342bae0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-26T17:59:55Z","title_canon_sha256":"ed93a3298a922f2ba46cba5e0be3316493d503c8844c8d1ad46e963008274624"},"schema_version":"1.0","source":{"id":"2407.18913","kind":"arxiv","version":2}},"canonical_sha256":"eb91de44d2eac80b2bfc793b2057eff7e2323fe5efd77a046aafa24626d3d082","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb91de44d2eac80b2bfc793b2057eff7e2323fe5efd77a046aafa24626d3d082","first_computed_at":"2026-07-05T09:19:11.557262Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:11.557262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+Lwdkzg+HNwsJnqwU6Y0wvY0f6o7Ip0RasDtc1AOjlcxQ/mFam2tx0Ey7aItka9S2BpSlG5IiE7HyEfQIv3tCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:11.557752Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.18913","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44e34423ab5302f82f482342f5f5a295112d5e2138980b239b5ad61a0b95da22","sha256:2d599daf4f7b0b06e60d1e274fa3367c352151adb3a653fc54337357a2bf0aa0"],"state_sha256":"1ecfcddb8886c9e6cc1435e47f3e690942aec42d3cb6887ee77f2b87b6d4693f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4XJUg/12w0LqMQXj+qVj8HAnvj+9tHOU/K4kNght/cCgLxnmiYN6FXJtJJyLrlDFSUB08MErUE9lELfvv5rUDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T21:51:14.562484Z","bundle_sha256":"2f8c3aa24abe15c46e5324b2375de89311d31dd4e97ec6e18a230f6f2c8a0a62"}}