{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JUN5526DBXXIQIQL5Y7L753R4T","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":"1c4aa4e75f9db7569220059bb86c6448d0ee5f6757b34e2ca21db13b168aa8b9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-22T13:39:33Z","title_canon_sha256":"3c3916cfe8a8bcecc5f482b754e237bbef06559d301bded87761552354882486"},"schema_version":"1.0","source":{"id":"2405.13640","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.13640","created_at":"2026-07-05T10:49:44Z"},{"alias_kind":"arxiv_version","alias_value":"2405.13640v2","created_at":"2026-07-05T10:49:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13640","created_at":"2026-07-05T10:49:44Z"},{"alias_kind":"pith_short_12","alias_value":"JUN5526DBXXI","created_at":"2026-07-05T10:49:44Z"},{"alias_kind":"pith_short_16","alias_value":"JUN5526DBXXIQIQL","created_at":"2026-07-05T10:49:44Z"},{"alias_kind":"pith_short_8","alias_value":"JUN5526D","created_at":"2026-07-05T10:49:44Z"}],"graph_snapshots":[{"event_id":"sha256:2eb0c3211055477307b86102bf6ce51002092c530eb43e4437771e7e2288fd31","target":"graph","created_at":"2026-07-05T10:49:44Z","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/2405.13640/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) is an effective method of finding reasoning pathways in incomplete knowledge graphs (KGs). To overcome the challenges of a large action space, a self-supervised pre-training method is proposed to warm up the policy network before the RL training stage. To alleviate the distributional mismatch issue in general self-supervised RL (SSRL), in our supervised learning (SL) stage, the agent selects actions based on the policy network and learns from generated labels; this self-generation of labels is the intuition behind the name self-supervised. With this training framewo","authors_text":"Gang Li, Hagen Soltau, Izhak Shafran, Laurent El Shafey, Liqiang Wang, Mingqiu Wang, Nan Du, Owen Burns, Ying Ma","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-22T13:39:33Z","title":"Knowledge Graph Reasoning with Self-supervised Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13640","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":"sha256:3ae3618dee3d91879a0f168b091eb1e4cf37e79e29378a9f30f132e2f3bdfa94","target":"record","created_at":"2026-07-05T10:49:44Z","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":"1c4aa4e75f9db7569220059bb86c6448d0ee5f6757b34e2ca21db13b168aa8b9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-22T13:39:33Z","title_canon_sha256":"3c3916cfe8a8bcecc5f482b754e237bbef06559d301bded87761552354882486"},"schema_version":"1.0","source":{"id":"2405.13640","kind":"arxiv","version":2}},"canonical_sha256":"4d1bdeebc30dee88220bee3ebff771e4d5cf4d3ec656fb5d780af0032c36868a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d1bdeebc30dee88220bee3ebff771e4d5cf4d3ec656fb5d780af0032c36868a","first_computed_at":"2026-07-05T10:49:44.607872Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:44.607872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RMsFsa3vDtgOsh5hb4VqUO9BuVpjFmEMmRtBJz5UNXLdEmxxQ/OD37TRxtrIknReWAXWYH4rIFERQl1aVT52Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:44.608393Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.13640","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ae3618dee3d91879a0f168b091eb1e4cf37e79e29378a9f30f132e2f3bdfa94","sha256:2eb0c3211055477307b86102bf6ce51002092c530eb43e4437771e7e2288fd31"],"state_sha256":"ff85ba7758189ee7afa7f12df2bd7e2ece3d76dc4fdc66cd34e945a430c9ed30"}