{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KKZQZ4KMCCEEFPQX2DAOERDZFY","short_pith_number":"pith:KKZQZ4KM","canonical_record":{"source":{"id":"2606.01599","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T02:52:49Z","cross_cats_sorted":[],"title_canon_sha256":"e0f889342c3be8fd9d9263e302198404d97460f51800e10fc3a468e91a266181","abstract_canon_sha256":"1f4e347e044f958571b492c1ac3efc313cc1ff87c59ef152a535948ea4cf5ef0"},"schema_version":"1.0"},"canonical_sha256":"52b30cf14c108842be17d0c0e244792e1519cd8caf5cc695ac6306d08006dad1","source":{"kind":"arxiv","id":"2606.01599","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01599","created_at":"2026-06-02T02:04:37Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01599v1","created_at":"2026-06-02T02:04:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01599","created_at":"2026-06-02T02:04:37Z"},{"alias_kind":"pith_short_12","alias_value":"KKZQZ4KMCCEE","created_at":"2026-06-02T02:04:37Z"},{"alias_kind":"pith_short_16","alias_value":"KKZQZ4KMCCEEFPQX","created_at":"2026-06-02T02:04:37Z"},{"alias_kind":"pith_short_8","alias_value":"KKZQZ4KM","created_at":"2026-06-02T02:04:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KKZQZ4KMCCEEFPQX2DAOERDZFY","target":"record","payload":{"canonical_record":{"source":{"id":"2606.01599","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T02:52:49Z","cross_cats_sorted":[],"title_canon_sha256":"e0f889342c3be8fd9d9263e302198404d97460f51800e10fc3a468e91a266181","abstract_canon_sha256":"1f4e347e044f958571b492c1ac3efc313cc1ff87c59ef152a535948ea4cf5ef0"},"schema_version":"1.0"},"canonical_sha256":"52b30cf14c108842be17d0c0e244792e1519cd8caf5cc695ac6306d08006dad1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:37.669116Z","signature_b64":"PLMSqsjl8AHByBSmOcZ6W2OctgG8khLBeBcb1rlI6uRBTShI1dxCCSm7kXKKL4aFzK8KZWohh1dioJv7OvHSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52b30cf14c108842be17d0c0e244792e1519cd8caf5cc695ac6306d08006dad1","last_reissued_at":"2026-06-02T02:04:37.668691Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:37.668691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.01599","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":"2026-06-02T02:04:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fuNlDIEEoSVKV1seDzcMrDNbkd8Y7ct6BT0c81+PLMiPTQnUWSVN0CaqLTi1tvcaAiJBEp1hSvohHicr+iFKCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T10:41:54.126203Z"},"content_sha256":"0b627581f073f73b8d179764c3e4395be8b0d4b94df3581e48774d8fb6bd1d6c","schema_version":"1.0","event_id":"sha256:0b627581f073f73b8d179764c3e4395be8b0d4b94df3581e48774d8fb6bd1d6c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KKZQZ4KMCCEEFPQX2DAOERDZFY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jingyuan Huang, Jin Sun, Ninghao Liu, Ruitong Sun, Tianze Yang, Yucheng Shi","submitted_at":"2026-06-01T02:52:49Z","abstract_excerpt":"Reinforcement learning (RL) for visual reasoning needs scalable, verifiable, and controllable training signals. Existing visual RL post-training trains on static curated datasets, with fixed image-question-answer samples bounded by their collection budget. In this work, we introduce TRON (Targeted, Rule-verifiable Online eNvironments), an online environment substrate: a training rollout is generated on demand by a controllable generator-verifier program that samples a fresh latent visual state, renders an image, asks a question, and exactly verifies the answer. A single run can therefore draw "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01599","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/2606.01599/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":"2026-06-02T02:04:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kq36T9ypqYt5LLo5qTqlNFgBar4XFSpHwhWkUhcx1iEzfKxY0pXVsQJPrWidKNT7m1ZbLWedhZMRqQZtknHaAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T10:41:54.126584Z"},"content_sha256":"0fd1124bdaf87e2571406e56225ad3d8eb3e583045b566da82b57270a97637ea","schema_version":"1.0","event_id":"sha256:0fd1124bdaf87e2571406e56225ad3d8eb3e583045b566da82b57270a97637ea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KKZQZ4KMCCEEFPQX2DAOERDZFY/bundle.json","state_url":"https://pith.science/pith/KKZQZ4KMCCEEFPQX2DAOERDZFY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KKZQZ4KMCCEEFPQX2DAOERDZFY/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":"2026-06-08T10:41:54Z","links":{"resolver":"https://pith.science/pith/KKZQZ4KMCCEEFPQX2DAOERDZFY","bundle":"https://pith.science/pith/KKZQZ4KMCCEEFPQX2DAOERDZFY/bundle.json","state":"https://pith.science/pith/KKZQZ4KMCCEEFPQX2DAOERDZFY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KKZQZ4KMCCEEFPQX2DAOERDZFY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KKZQZ4KMCCEEFPQX2DAOERDZFY","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":"1f4e347e044f958571b492c1ac3efc313cc1ff87c59ef152a535948ea4cf5ef0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T02:52:49Z","title_canon_sha256":"e0f889342c3be8fd9d9263e302198404d97460f51800e10fc3a468e91a266181"},"schema_version":"1.0","source":{"id":"2606.01599","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01599","created_at":"2026-06-02T02:04:37Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01599v1","created_at":"2026-06-02T02:04:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01599","created_at":"2026-06-02T02:04:37Z"},{"alias_kind":"pith_short_12","alias_value":"KKZQZ4KMCCEE","created_at":"2026-06-02T02:04:37Z"},{"alias_kind":"pith_short_16","alias_value":"KKZQZ4KMCCEEFPQX","created_at":"2026-06-02T02:04:37Z"},{"alias_kind":"pith_short_8","alias_value":"KKZQZ4KM","created_at":"2026-06-02T02:04:37Z"}],"graph_snapshots":[{"event_id":"sha256:0fd1124bdaf87e2571406e56225ad3d8eb3e583045b566da82b57270a97637ea","target":"graph","created_at":"2026-06-02T02:04:37Z","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/2606.01599/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) for visual reasoning needs scalable, verifiable, and controllable training signals. Existing visual RL post-training trains on static curated datasets, with fixed image-question-answer samples bounded by their collection budget. In this work, we introduce TRON (Targeted, Rule-verifiable Online eNvironments), an online environment substrate: a training rollout is generated on demand by a controllable generator-verifier program that samples a fresh latent visual state, renders an image, asks a question, and exactly verifies the answer. A single run can therefore draw ","authors_text":"Jingyuan Huang, Jin Sun, Ninghao Liu, Ruitong Sun, Tianze Yang, Yucheng Shi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T02:52:49Z","title":"TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01599","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":"sha256:0b627581f073f73b8d179764c3e4395be8b0d4b94df3581e48774d8fb6bd1d6c","target":"record","created_at":"2026-06-02T02:04:37Z","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":"1f4e347e044f958571b492c1ac3efc313cc1ff87c59ef152a535948ea4cf5ef0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T02:52:49Z","title_canon_sha256":"e0f889342c3be8fd9d9263e302198404d97460f51800e10fc3a468e91a266181"},"schema_version":"1.0","source":{"id":"2606.01599","kind":"arxiv","version":1}},"canonical_sha256":"52b30cf14c108842be17d0c0e244792e1519cd8caf5cc695ac6306d08006dad1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52b30cf14c108842be17d0c0e244792e1519cd8caf5cc695ac6306d08006dad1","first_computed_at":"2026-06-02T02:04:37.668691Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:37.668691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PLMSqsjl8AHByBSmOcZ6W2OctgG8khLBeBcb1rlI6uRBTShI1dxCCSm7kXKKL4aFzK8KZWohh1dioJv7OvHSCw==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:37.669116Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01599","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b627581f073f73b8d179764c3e4395be8b0d4b94df3581e48774d8fb6bd1d6c","sha256:0fd1124bdaf87e2571406e56225ad3d8eb3e583045b566da82b57270a97637ea"],"state_sha256":"14dcacaa2e9c6f49f6cb4fc1a1bb1d9666859bc0a6e9314f4b7b4d72d80b04ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yPi68UQug/syi9oehDD0/KV8XIwnc7gIdF9W4Fw6k8pGh4hOAs6i2g1HCvZkU9Ef7xVvEPCOr1WMJPUTVMmqDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T10:41:54.128572Z","bundle_sha256":"18e8c89efbd6cd269a92e796097a6a6106a385eabe6241af2bcfb10c83c439f2"}}