{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KDGLKJ2GIY4XDYWHEXO3B7K6CM","short_pith_number":"pith:KDGLKJ2G","canonical_record":{"source":{"id":"2607.16204","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-07T00:40:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"01d0cbe33866682f702886fe93bdca011ef22b0efd21557a633230f85ad389b4","abstract_canon_sha256":"d1226495241b2395499a728d7fda489aff618256fb013557c2315a9e6f72bc58"},"schema_version":"1.0"},"canonical_sha256":"50ccb52746463971e2c725ddb0fd5e1303509a77a914ee9c85a0185b4857db5d","source":{"kind":"arxiv","id":"2607.16204","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16204","created_at":"2026-07-21T00:20:05Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16204v1","created_at":"2026-07-21T00:20:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16204","created_at":"2026-07-21T00:20:05Z"},{"alias_kind":"pith_short_12","alias_value":"KDGLKJ2GIY4X","created_at":"2026-07-21T00:20:05Z"},{"alias_kind":"pith_short_16","alias_value":"KDGLKJ2GIY4XDYWH","created_at":"2026-07-21T00:20:05Z"},{"alias_kind":"pith_short_8","alias_value":"KDGLKJ2G","created_at":"2026-07-21T00:20:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KDGLKJ2GIY4XDYWHEXO3B7K6CM","target":"record","payload":{"canonical_record":{"source":{"id":"2607.16204","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-07T00:40:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"01d0cbe33866682f702886fe93bdca011ef22b0efd21557a633230f85ad389b4","abstract_canon_sha256":"d1226495241b2395499a728d7fda489aff618256fb013557c2315a9e6f72bc58"},"schema_version":"1.0"},"canonical_sha256":"50ccb52746463971e2c725ddb0fd5e1303509a77a914ee9c85a0185b4857db5d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T00:20:05.580969Z","signature_b64":"9fZcvmrtr1AORpnsrwxFUgckr5DlqngwM+nIym67TwdfZ/yNd8L+EehZR+X3fTcNc4ZKgQTAtZQUCy+YMmYnCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50ccb52746463971e2c725ddb0fd5e1303509a77a914ee9c85a0185b4857db5d","last_reissued_at":"2026-07-21T00:20:05.580037Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T00:20:05.580037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.16204","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":"2026-07-21T00:20:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wdijB4LFm5PJinUVeVOceesyd+uc+/0wJlcDje8vYtXnyOMJin5OYZVVhf4Px4tavPG0vwQVGCZRXiUE2eVOCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:36:18.500791Z"},"content_sha256":"81ca113911d69397e01cfef8a3f0b0304de9de76b2d8b0bc8620ba7cb23da474","schema_version":"1.0","event_id":"sha256:81ca113911d69397e01cfef8a3f0b0304de9de76b2d8b0bc8620ba7cb23da474"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KDGLKJ2GIY4XDYWHEXO3B7K6CM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Darshan Deshpande","submitted_at":"2026-05-07T00:40:32Z","abstract_excerpt":"Recent growth in reinforcement learning (RL) has surfaced a need for diverse, specialized training environments. Hand-curated environments with fixed task and reward difficulties become ineffective signals as model performance improves, and sparse rewards over long horizons induce mode collapse on specific workflows or tool structures. World models that simulate environment states have matched pure rollout performance, making them promising for scaling diversity on-demand. However, autoregressive (AR) world models suffer from a left-to-right bias preventing conditioning on globally interdepend"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16204","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/2607.16204/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":"2026-07-21T00:20:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wq6331gfe3bFfc7z4HqJ8B+yvqRsWRvu8jFfp80pYhJ5Tt+H73FZrDoZujNMCVYrKsNrEs6ok8kJmHjbl1DzDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:36:18.501698Z"},"content_sha256":"f86c54a52d516b7cbbccce5a8b499ce1a99179c4ea38e2bc431cd533309cf376","schema_version":"1.0","event_id":"sha256:f86c54a52d516b7cbbccce5a8b499ce1a99179c4ea38e2bc431cd533309cf376"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KDGLKJ2GIY4XDYWHEXO3B7K6CM/bundle.json","state_url":"https://pith.science/pith/KDGLKJ2GIY4XDYWHEXO3B7K6CM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KDGLKJ2GIY4XDYWHEXO3B7K6CM/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":"2026-08-04T08:36:18Z","links":{"resolver":"https://pith.science/pith/KDGLKJ2GIY4XDYWHEXO3B7K6CM","bundle":"https://pith.science/pith/KDGLKJ2GIY4XDYWHEXO3B7K6CM/bundle.json","state":"https://pith.science/pith/KDGLKJ2GIY4XDYWHEXO3B7K6CM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KDGLKJ2GIY4XDYWHEXO3B7K6CM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KDGLKJ2GIY4XDYWHEXO3B7K6CM","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":"d1226495241b2395499a728d7fda489aff618256fb013557c2315a9e6f72bc58","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-07T00:40:32Z","title_canon_sha256":"01d0cbe33866682f702886fe93bdca011ef22b0efd21557a633230f85ad389b4"},"schema_version":"1.0","source":{"id":"2607.16204","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16204","created_at":"2026-07-21T00:20:05Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16204v1","created_at":"2026-07-21T00:20:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16204","created_at":"2026-07-21T00:20:05Z"},{"alias_kind":"pith_short_12","alias_value":"KDGLKJ2GIY4X","created_at":"2026-07-21T00:20:05Z"},{"alias_kind":"pith_short_16","alias_value":"KDGLKJ2GIY4XDYWH","created_at":"2026-07-21T00:20:05Z"},{"alias_kind":"pith_short_8","alias_value":"KDGLKJ2G","created_at":"2026-07-21T00:20:05Z"}],"graph_snapshots":[{"event_id":"sha256:f86c54a52d516b7cbbccce5a8b499ce1a99179c4ea38e2bc431cd533309cf376","target":"graph","created_at":"2026-07-21T00:20:05Z","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/2607.16204/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent growth in reinforcement learning (RL) has surfaced a need for diverse, specialized training environments. Hand-curated environments with fixed task and reward difficulties become ineffective signals as model performance improves, and sparse rewards over long horizons induce mode collapse on specific workflows or tool structures. World models that simulate environment states have matched pure rollout performance, making them promising for scaling diversity on-demand. However, autoregressive (AR) world models suffer from a left-to-right bias preventing conditioning on globally interdepend","authors_text":"Darshan Deshpande","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-07T00:40:32Z","title":"Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16204","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":"sha256:81ca113911d69397e01cfef8a3f0b0304de9de76b2d8b0bc8620ba7cb23da474","target":"record","created_at":"2026-07-21T00:20:05Z","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":"d1226495241b2395499a728d7fda489aff618256fb013557c2315a9e6f72bc58","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-07T00:40:32Z","title_canon_sha256":"01d0cbe33866682f702886fe93bdca011ef22b0efd21557a633230f85ad389b4"},"schema_version":"1.0","source":{"id":"2607.16204","kind":"arxiv","version":1}},"canonical_sha256":"50ccb52746463971e2c725ddb0fd5e1303509a77a914ee9c85a0185b4857db5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50ccb52746463971e2c725ddb0fd5e1303509a77a914ee9c85a0185b4857db5d","first_computed_at":"2026-07-21T00:20:05.580037Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T00:20:05.580037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9fZcvmrtr1AORpnsrwxFUgckr5DlqngwM+nIym67TwdfZ/yNd8L+EehZR+X3fTcNc4ZKgQTAtZQUCy+YMmYnCg==","signature_status":"signed_v1","signed_at":"2026-07-21T00:20:05.580969Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.16204","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81ca113911d69397e01cfef8a3f0b0304de9de76b2d8b0bc8620ba7cb23da474","sha256:f86c54a52d516b7cbbccce5a8b499ce1a99179c4ea38e2bc431cd533309cf376"],"state_sha256":"e1305373e224c57baa91d5c6d18c9ac6612275f4876abc4f70f4bfa3a3d3df88"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XNhp94bfGr+nGw9gHKcjsi0/xLXC0HOm83R8qFJ5aeYDzJJbvEsusTtxO+1Uv33Rp1xQbwPm1olchTTinzCKAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T08:36:18.507011Z","bundle_sha256":"bad17e2504b6aa041d06604e7949b51ca4cc87041d9dc85fb3bf6307a59dde2b"}}