{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4WKIGLHLZWXE4QR3F6Y2BK7GI3","short_pith_number":"pith:4WKIGLHL","canonical_record":{"source":{"id":"2507.16864","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-21T21:59:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8dceebf633591ea50bdd3affef22315a5c259dbe551515806211b3cd050fc09b","abstract_canon_sha256":"13a2825f1f53212f13ce31787c6404f6dc58df05d6b0b89418b42585b7309813"},"schema_version":"1.0"},"canonical_sha256":"e594832cebcdae4e423b2fb1a0abe646cf6b60bf5264120bfc3e4fc55114ee93","source":{"kind":"arxiv","id":"2507.16864","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.16864","created_at":"2026-07-05T11:41:57Z"},{"alias_kind":"arxiv_version","alias_value":"2507.16864v1","created_at":"2026-07-05T11:41:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16864","created_at":"2026-07-05T11:41:57Z"},{"alias_kind":"pith_short_12","alias_value":"4WKIGLHLZWXE","created_at":"2026-07-05T11:41:57Z"},{"alias_kind":"pith_short_16","alias_value":"4WKIGLHLZWXE4QR3","created_at":"2026-07-05T11:41:57Z"},{"alias_kind":"pith_short_8","alias_value":"4WKIGLHL","created_at":"2026-07-05T11:41:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4WKIGLHLZWXE4QR3F6Y2BK7GI3","target":"record","payload":{"canonical_record":{"source":{"id":"2507.16864","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-21T21:59:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8dceebf633591ea50bdd3affef22315a5c259dbe551515806211b3cd050fc09b","abstract_canon_sha256":"13a2825f1f53212f13ce31787c6404f6dc58df05d6b0b89418b42585b7309813"},"schema_version":"1.0"},"canonical_sha256":"e594832cebcdae4e423b2fb1a0abe646cf6b60bf5264120bfc3e4fc55114ee93","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:57.374201Z","signature_b64":"zNKfijig8JVdfsy9FgtEs+ohHVmryNHvEjInvM/ZyJ5GNCsk5A3hJ7SmNoXIi4Ic9RRIflm3YjEz3tDepAoSAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e594832cebcdae4e423b2fb1a0abe646cf6b60bf5264120bfc3e4fc55114ee93","last_reissued_at":"2026-07-05T11:41:57.373712Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:57.373712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.16864","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":"2026-07-05T11:41:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bIAHhybD9WYQH/RcU0gRu4QdPdjESZxbzg5077mWMFNH2LAs+eMuvd9DGcVxlt49RkYdup9wF30mq/OtFUGLAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:28:27.465856Z"},"content_sha256":"a15d3af9fdf7d1bf664b7a5d38e292c25860450643679cdf5b9ef23fcde1d2a8","schema_version":"1.0","event_id":"sha256:a15d3af9fdf7d1bf664b7a5d38e292c25860450643679cdf5b9ef23fcde1d2a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4WKIGLHLZWXE4QR3F6Y2BK7GI3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning in hyperbolic space for multi-step reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dung-Yang Lee, Momiao Xiong, Tao Xu","submitted_at":"2025-07-21T21:59:05Z","abstract_excerpt":"Multi-step reasoning is a fundamental challenge in artificial intelligence, with applications ranging from mathematical problem-solving to decision-making in dynamic environments. Reinforcement Learning (RL) has shown promise in enabling agents to perform multi-step reasoning by optimizing long-term rewards. However, conventional RL methods struggle with complex reasoning tasks due to issues such as credit assignment, high-dimensional state representations, and stability concerns. Recent advancements in Transformer architectures and hyperbolic geometry have provided novel solutions to these ch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16864","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/2507.16864/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":"2026-07-05T11:41:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eSHSaoorauskeySUAs9C5w620jgTcj3xfDO8XYRqXQpFWerJbSaTwbSMKtjLCGZGq5HibYKOpKs3H5VinZZqCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:28:27.466428Z"},"content_sha256":"fbd401ab0655f4b47c6528bc072b5c94ddd3336902d85ae63d990d9724046d05","schema_version":"1.0","event_id":"sha256:fbd401ab0655f4b47c6528bc072b5c94ddd3336902d85ae63d990d9724046d05"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4WKIGLHLZWXE4QR3F6Y2BK7GI3/bundle.json","state_url":"https://pith.science/pith/4WKIGLHLZWXE4QR3F6Y2BK7GI3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4WKIGLHLZWXE4QR3F6Y2BK7GI3/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":"2026-08-09T20:28:27Z","links":{"resolver":"https://pith.science/pith/4WKIGLHLZWXE4QR3F6Y2BK7GI3","bundle":"https://pith.science/pith/4WKIGLHLZWXE4QR3F6Y2BK7GI3/bundle.json","state":"https://pith.science/pith/4WKIGLHLZWXE4QR3F6Y2BK7GI3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4WKIGLHLZWXE4QR3F6Y2BK7GI3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4WKIGLHLZWXE4QR3F6Y2BK7GI3","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":"13a2825f1f53212f13ce31787c6404f6dc58df05d6b0b89418b42585b7309813","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-21T21:59:05Z","title_canon_sha256":"8dceebf633591ea50bdd3affef22315a5c259dbe551515806211b3cd050fc09b"},"schema_version":"1.0","source":{"id":"2507.16864","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.16864","created_at":"2026-07-05T11:41:57Z"},{"alias_kind":"arxiv_version","alias_value":"2507.16864v1","created_at":"2026-07-05T11:41:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16864","created_at":"2026-07-05T11:41:57Z"},{"alias_kind":"pith_short_12","alias_value":"4WKIGLHLZWXE","created_at":"2026-07-05T11:41:57Z"},{"alias_kind":"pith_short_16","alias_value":"4WKIGLHLZWXE4QR3","created_at":"2026-07-05T11:41:57Z"},{"alias_kind":"pith_short_8","alias_value":"4WKIGLHL","created_at":"2026-07-05T11:41:57Z"}],"graph_snapshots":[{"event_id":"sha256:fbd401ab0655f4b47c6528bc072b5c94ddd3336902d85ae63d990d9724046d05","target":"graph","created_at":"2026-07-05T11:41:57Z","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/2507.16864/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-step reasoning is a fundamental challenge in artificial intelligence, with applications ranging from mathematical problem-solving to decision-making in dynamic environments. Reinforcement Learning (RL) has shown promise in enabling agents to perform multi-step reasoning by optimizing long-term rewards. However, conventional RL methods struggle with complex reasoning tasks due to issues such as credit assignment, high-dimensional state representations, and stability concerns. Recent advancements in Transformer architectures and hyperbolic geometry have provided novel solutions to these ch","authors_text":"Dung-Yang Lee, Momiao Xiong, Tao Xu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-21T21:59:05Z","title":"Reinforcement Learning in hyperbolic space for multi-step reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16864","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:a15d3af9fdf7d1bf664b7a5d38e292c25860450643679cdf5b9ef23fcde1d2a8","target":"record","created_at":"2026-07-05T11:41:57Z","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":"13a2825f1f53212f13ce31787c6404f6dc58df05d6b0b89418b42585b7309813","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-21T21:59:05Z","title_canon_sha256":"8dceebf633591ea50bdd3affef22315a5c259dbe551515806211b3cd050fc09b"},"schema_version":"1.0","source":{"id":"2507.16864","kind":"arxiv","version":1}},"canonical_sha256":"e594832cebcdae4e423b2fb1a0abe646cf6b60bf5264120bfc3e4fc55114ee93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e594832cebcdae4e423b2fb1a0abe646cf6b60bf5264120bfc3e4fc55114ee93","first_computed_at":"2026-07-05T11:41:57.373712Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:41:57.373712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zNKfijig8JVdfsy9FgtEs+ohHVmryNHvEjInvM/ZyJ5GNCsk5A3hJ7SmNoXIi4Ic9RRIflm3YjEz3tDepAoSAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:41:57.374201Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.16864","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a15d3af9fdf7d1bf664b7a5d38e292c25860450643679cdf5b9ef23fcde1d2a8","sha256:fbd401ab0655f4b47c6528bc072b5c94ddd3336902d85ae63d990d9724046d05"],"state_sha256":"0daabed24428a64555fab3671a212f6e6f984b3a372ac35e1be43f9325ce60cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Xoxu5HUuIiyJIf0Igr+aXG+W+CExsG7w8u08sa55gj6t59BJUzufJu/CASUVq778jME4ZaV9L6bY2CbR2S9Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T20:28:27.470665Z","bundle_sha256":"9b1e7e72c36606c44383f1cc1560610e8a5bd20b86d84fd96cdfcdd80de0aabd"}}