{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CY7LJ5FRRJ3IFYD22HEPMDCTHV","short_pith_number":"pith:CY7LJ5FR","canonical_record":{"source":{"id":"2606.21975","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-20T10:06:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4f47b821dafd3b411e7eadc6a380f0788a1293b8467176aaff4b90901c26eaff","abstract_canon_sha256":"2dc9b0bea51499d7e2aa64532e690fab08315a81a06b7c9ee87e4b3e2d9ff6f5"},"schema_version":"1.0"},"canonical_sha256":"163eb4f4b18a7682e07ad1c8f60c533d5fb38d6cb570f64dee9ca9132e39a575","source":{"kind":"arxiv","id":"2606.21975","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21975","created_at":"2026-06-23T02:13:04Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21975v1","created_at":"2026-06-23T02:13:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21975","created_at":"2026-06-23T02:13:04Z"},{"alias_kind":"pith_short_12","alias_value":"CY7LJ5FRRJ3I","created_at":"2026-06-23T02:13:04Z"},{"alias_kind":"pith_short_16","alias_value":"CY7LJ5FRRJ3IFYD2","created_at":"2026-06-23T02:13:04Z"},{"alias_kind":"pith_short_8","alias_value":"CY7LJ5FR","created_at":"2026-06-23T02:13:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CY7LJ5FRRJ3IFYD22HEPMDCTHV","target":"record","payload":{"canonical_record":{"source":{"id":"2606.21975","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-20T10:06:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4f47b821dafd3b411e7eadc6a380f0788a1293b8467176aaff4b90901c26eaff","abstract_canon_sha256":"2dc9b0bea51499d7e2aa64532e690fab08315a81a06b7c9ee87e4b3e2d9ff6f5"},"schema_version":"1.0"},"canonical_sha256":"163eb4f4b18a7682e07ad1c8f60c533d5fb38d6cb570f64dee9ca9132e39a575","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:04.728046Z","signature_b64":"VtHh9jsD0v6CycOcS2XQ+qgL+vxQILpaeP7zkJiIJh++zj0gMzReoL+tZ94MYyXi4/E2mSmoEK5/rppWwukrCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"163eb4f4b18a7682e07ad1c8f60c533d5fb38d6cb570f64dee9ca9132e39a575","last_reissued_at":"2026-06-23T02:13:04.727650Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:04.727650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.21975","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":"2026-06-23T02:13:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"etmSvQ7hzniW/P9nb3NL1P7/u/dM14OEReYfxyKPJgy30eBh5nzkvt2CrzMcRj2qpBvVyztDGljD4XBA0ZC/Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T18:16:59.360189Z"},"content_sha256":"581b744b7ff65df0ce54c9612cdc23dfae0a253560e5208e6748ffd423de6e59","schema_version":"1.0","event_id":"sha256:581b744b7ff65df0ce54c9612cdc23dfae0a253560e5208e6748ffd423de6e59"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CY7LJ5FRRJ3IFYD22HEPMDCTHV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"IRumAI: Reinforcement Learning for Indian Rummy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Vignesh Mohan","submitted_at":"2026-06-20T10:06:57Z","abstract_excerpt":"Despite its massive player base and complex hidden-information dynamics, Indian Rummy has received no reinforcement learning attention. Existing agents rely on combinatorial search, which is tactically strong but slow at inference. We present IRumAI, the first RL agent for the domain. IRumAI integrates Proximal Policy Optimization (PPO), meld-aware observation encoding, deadwood-driven reward shaping, and a dual-branch convolutional architecture. IRumAI is RL-trained solely against weak heuristics, after a one-time behaviour-cloning warm-start on stronger demonstration data. It generalises to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21975","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/2606.21975/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":"2026-06-23T02:13:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rrl0xOs3i+KSPoPYFyANWRgJVMubwh+GyuU5ZQFYf2cP+5p6S9XJZQl7H4YrmBewaiu3c3UJlb20uRwnuy7cDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T18:16:59.360603Z"},"content_sha256":"4c9c0d2cf5556d14c02880d79354da38c9ef607942e5d3c69ecd8c353b3a4c40","schema_version":"1.0","event_id":"sha256:4c9c0d2cf5556d14c02880d79354da38c9ef607942e5d3c69ecd8c353b3a4c40"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CY7LJ5FRRJ3IFYD22HEPMDCTHV/bundle.json","state_url":"https://pith.science/pith/CY7LJ5FRRJ3IFYD22HEPMDCTHV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CY7LJ5FRRJ3IFYD22HEPMDCTHV/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":"2026-07-04T18:16:59Z","links":{"resolver":"https://pith.science/pith/CY7LJ5FRRJ3IFYD22HEPMDCTHV","bundle":"https://pith.science/pith/CY7LJ5FRRJ3IFYD22HEPMDCTHV/bundle.json","state":"https://pith.science/pith/CY7LJ5FRRJ3IFYD22HEPMDCTHV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CY7LJ5FRRJ3IFYD22HEPMDCTHV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CY7LJ5FRRJ3IFYD22HEPMDCTHV","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":"2dc9b0bea51499d7e2aa64532e690fab08315a81a06b7c9ee87e4b3e2d9ff6f5","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-20T10:06:57Z","title_canon_sha256":"4f47b821dafd3b411e7eadc6a380f0788a1293b8467176aaff4b90901c26eaff"},"schema_version":"1.0","source":{"id":"2606.21975","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21975","created_at":"2026-06-23T02:13:04Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21975v1","created_at":"2026-06-23T02:13:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21975","created_at":"2026-06-23T02:13:04Z"},{"alias_kind":"pith_short_12","alias_value":"CY7LJ5FRRJ3I","created_at":"2026-06-23T02:13:04Z"},{"alias_kind":"pith_short_16","alias_value":"CY7LJ5FRRJ3IFYD2","created_at":"2026-06-23T02:13:04Z"},{"alias_kind":"pith_short_8","alias_value":"CY7LJ5FR","created_at":"2026-06-23T02:13:04Z"}],"graph_snapshots":[{"event_id":"sha256:4c9c0d2cf5556d14c02880d79354da38c9ef607942e5d3c69ecd8c353b3a4c40","target":"graph","created_at":"2026-06-23T02:13:04Z","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/2606.21975/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite its massive player base and complex hidden-information dynamics, Indian Rummy has received no reinforcement learning attention. Existing agents rely on combinatorial search, which is tactically strong but slow at inference. We present IRumAI, the first RL agent for the domain. IRumAI integrates Proximal Policy Optimization (PPO), meld-aware observation encoding, deadwood-driven reward shaping, and a dual-branch convolutional architecture. IRumAI is RL-trained solely against weak heuristics, after a one-time behaviour-cloning warm-start on stronger demonstration data. It generalises to ","authors_text":"Vignesh Mohan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-20T10:06:57Z","title":"IRumAI: Reinforcement Learning for Indian Rummy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21975","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":"sha256:581b744b7ff65df0ce54c9612cdc23dfae0a253560e5208e6748ffd423de6e59","target":"record","created_at":"2026-06-23T02:13:04Z","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":"2dc9b0bea51499d7e2aa64532e690fab08315a81a06b7c9ee87e4b3e2d9ff6f5","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-20T10:06:57Z","title_canon_sha256":"4f47b821dafd3b411e7eadc6a380f0788a1293b8467176aaff4b90901c26eaff"},"schema_version":"1.0","source":{"id":"2606.21975","kind":"arxiv","version":1}},"canonical_sha256":"163eb4f4b18a7682e07ad1c8f60c533d5fb38d6cb570f64dee9ca9132e39a575","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"163eb4f4b18a7682e07ad1c8f60c533d5fb38d6cb570f64dee9ca9132e39a575","first_computed_at":"2026-06-23T02:13:04.727650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:04.727650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VtHh9jsD0v6CycOcS2XQ+qgL+vxQILpaeP7zkJiIJh++zj0gMzReoL+tZ94MYyXi4/E2mSmoEK5/rppWwukrCA==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:04.728046Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21975","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:581b744b7ff65df0ce54c9612cdc23dfae0a253560e5208e6748ffd423de6e59","sha256:4c9c0d2cf5556d14c02880d79354da38c9ef607942e5d3c69ecd8c353b3a4c40"],"state_sha256":"f379f9fb332e1cb78689087216b4c823401ecb8987196661f9d76595089e3f96"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eEadREPhtzkT8CF3oCsCJyBRkTr2jjrStOb9XI8pj0U/90SdJMmOpsj3UAjwlgTXPE3QiKYDj7XuVQWMJPrSCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T18:16:59.362671Z","bundle_sha256":"072ba16f1fbbe928af6efb2cd3b719b024d530a4579ed44a94e5a2e72390d6e5"}}