{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SPXRYCLC3SPV623PVVSCJFBAXQ","short_pith_number":"pith:SPXRYCLC","canonical_record":{"source":{"id":"2505.11153","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T11:54:48Z","cross_cats_sorted":[],"title_canon_sha256":"48ad034d2d9be585ce88d575871733ebabbeb16ad872e6b01d3894e3c71b193e","abstract_canon_sha256":"1f3cf23d80598405b63e039a0147d5a897c6f4c37c1bb440d47cc7f897698850"},"schema_version":"1.0"},"canonical_sha256":"93ef1c0962dc9f5f6b6fad64249420bc004c8430dff6901a66ed0c92b591ff90","source":{"kind":"arxiv","id":"2505.11153","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11153","created_at":"2026-07-05T11:04:11Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11153v1","created_at":"2026-07-05T11:04:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11153","created_at":"2026-07-05T11:04:11Z"},{"alias_kind":"pith_short_12","alias_value":"SPXRYCLC3SPV","created_at":"2026-07-05T11:04:11Z"},{"alias_kind":"pith_short_16","alias_value":"SPXRYCLC3SPV623P","created_at":"2026-07-05T11:04:11Z"},{"alias_kind":"pith_short_8","alias_value":"SPXRYCLC","created_at":"2026-07-05T11:04:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SPXRYCLC3SPV623PVVSCJFBAXQ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.11153","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T11:54:48Z","cross_cats_sorted":[],"title_canon_sha256":"48ad034d2d9be585ce88d575871733ebabbeb16ad872e6b01d3894e3c71b193e","abstract_canon_sha256":"1f3cf23d80598405b63e039a0147d5a897c6f4c37c1bb440d47cc7f897698850"},"schema_version":"1.0"},"canonical_sha256":"93ef1c0962dc9f5f6b6fad64249420bc004c8430dff6901a66ed0c92b591ff90","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:11.857877Z","signature_b64":"uAI0tuNg6P5yoGuq59s+qP5G7l+FDdjtBFZaEwAa/efidKC93d3x9GYG7iSrLH/ie4Ij8QN04lNgpF8SubcmAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93ef1c0962dc9f5f6b6fad64249420bc004c8430dff6901a66ed0c92b591ff90","last_reissued_at":"2026-07-05T11:04:11.857303Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:11.857303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.11153","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":"2026-07-05T11:04:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w+RRzryCVofu3/+ZQtDszgd2jI6alwGT7RJv+++RJbLgh3Vd4tUqVvZY3QBiS1VR9FBy7WzuSRFoJxdqL8ORCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:37:13.309214Z"},"content_sha256":"d5419fb9dac09bde1f0a586aaf942ce675b00710b02d1905ea07afeb4f671982","schema_version":"1.0","event_id":"sha256:d5419fb9dac09bde1f0a586aaf942ce675b00710b02d1905ea07afeb4f671982"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SPXRYCLC3SPV623PVVSCJFBAXQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bi-directional Recurrence Improves Transformer in Partially Observable Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ashok Arora, Neetesh Kumar","submitted_at":"2025-05-16T11:54:48Z","abstract_excerpt":"In real-world reinforcement learning (RL) scenarios, agents often encounter partial observability, where incomplete or noisy information obscures the true state of the environment. Partially Observable Markov Decision Processes (POMDPs) are commonly used to model these environments, but effective performance requires memory mechanisms to utilise past observations. While recurrence networks have traditionally addressed this need, transformer-based models have recently shown improved sample efficiency in RL tasks. However, their application to POMDPs remains underdeveloped, and their real-world "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11153","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/2505.11153/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":"2026-07-05T11:04:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HT1YW8HnPeL3W548wQL6DCH9UQ7MkK4jpdU9j3Wqh7PUx3KyAfV8G0wbc7EdTHknTWs64+8P4XyZVa9puyFoCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:37:13.309822Z"},"content_sha256":"83463288a1347e73931650ae9253b38e45319801022ef8c5db20486fca18d225","schema_version":"1.0","event_id":"sha256:83463288a1347e73931650ae9253b38e45319801022ef8c5db20486fca18d225"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SPXRYCLC3SPV623PVVSCJFBAXQ/bundle.json","state_url":"https://pith.science/pith/SPXRYCLC3SPV623PVVSCJFBAXQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SPXRYCLC3SPV623PVVSCJFBAXQ/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":"2026-08-17T20:37:13Z","links":{"resolver":"https://pith.science/pith/SPXRYCLC3SPV623PVVSCJFBAXQ","bundle":"https://pith.science/pith/SPXRYCLC3SPV623PVVSCJFBAXQ/bundle.json","state":"https://pith.science/pith/SPXRYCLC3SPV623PVVSCJFBAXQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SPXRYCLC3SPV623PVVSCJFBAXQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SPXRYCLC3SPV623PVVSCJFBAXQ","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":"1f3cf23d80598405b63e039a0147d5a897c6f4c37c1bb440d47cc7f897698850","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T11:54:48Z","title_canon_sha256":"48ad034d2d9be585ce88d575871733ebabbeb16ad872e6b01d3894e3c71b193e"},"schema_version":"1.0","source":{"id":"2505.11153","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11153","created_at":"2026-07-05T11:04:11Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11153v1","created_at":"2026-07-05T11:04:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11153","created_at":"2026-07-05T11:04:11Z"},{"alias_kind":"pith_short_12","alias_value":"SPXRYCLC3SPV","created_at":"2026-07-05T11:04:11Z"},{"alias_kind":"pith_short_16","alias_value":"SPXRYCLC3SPV623P","created_at":"2026-07-05T11:04:11Z"},{"alias_kind":"pith_short_8","alias_value":"SPXRYCLC","created_at":"2026-07-05T11:04:11Z"}],"graph_snapshots":[{"event_id":"sha256:83463288a1347e73931650ae9253b38e45319801022ef8c5db20486fca18d225","target":"graph","created_at":"2026-07-05T11:04:11Z","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/2505.11153/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In real-world reinforcement learning (RL) scenarios, agents often encounter partial observability, where incomplete or noisy information obscures the true state of the environment. Partially Observable Markov Decision Processes (POMDPs) are commonly used to model these environments, but effective performance requires memory mechanisms to utilise past observations. While recurrence networks have traditionally addressed this need, transformer-based models have recently shown improved sample efficiency in RL tasks. However, their application to POMDPs remains underdeveloped, and their real-world ","authors_text":"Ashok Arora, Neetesh Kumar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T11:54:48Z","title":"Bi-directional Recurrence Improves Transformer in Partially Observable Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11153","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:d5419fb9dac09bde1f0a586aaf942ce675b00710b02d1905ea07afeb4f671982","target":"record","created_at":"2026-07-05T11:04:11Z","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":"1f3cf23d80598405b63e039a0147d5a897c6f4c37c1bb440d47cc7f897698850","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T11:54:48Z","title_canon_sha256":"48ad034d2d9be585ce88d575871733ebabbeb16ad872e6b01d3894e3c71b193e"},"schema_version":"1.0","source":{"id":"2505.11153","kind":"arxiv","version":1}},"canonical_sha256":"93ef1c0962dc9f5f6b6fad64249420bc004c8430dff6901a66ed0c92b591ff90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93ef1c0962dc9f5f6b6fad64249420bc004c8430dff6901a66ed0c92b591ff90","first_computed_at":"2026-07-05T11:04:11.857303Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:11.857303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uAI0tuNg6P5yoGuq59s+qP5G7l+FDdjtBFZaEwAa/efidKC93d3x9GYG7iSrLH/ie4Ij8QN04lNgpF8SubcmAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:11.857877Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11153","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5419fb9dac09bde1f0a586aaf942ce675b00710b02d1905ea07afeb4f671982","sha256:83463288a1347e73931650ae9253b38e45319801022ef8c5db20486fca18d225"],"state_sha256":"bc113a778235306f596afc96755d3f65510f21ba5b91b42c506f50a66f1a1d84"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LUL37oocszqHY65n4IsxFlyyyjPVuMZIvyHGs4CXOrZg55299XaM/VQszyzGnXgGQRL8Z923GuoIEJ+zEXzIAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T20:37:13.313806Z","bundle_sha256":"7d5c2da05b88ab3ef11d125359704b0928a3d482a8681d03fe2f22052b41611c"}}