{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:F7V4C5XWLG6K57WUYXVCYMBCI5","short_pith_number":"pith:F7V4C5XW","canonical_record":{"source":{"id":"2605.26971","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T12:57:12Z","cross_cats_sorted":[],"title_canon_sha256":"9f85660f110225f7d4d69aa12fb74c746ff80e46068ba9a0d13a51c40314b414","abstract_canon_sha256":"57e0536d7d1fa8d1199c18605d1021d262456d5dfb480a2c4b984c33a3104e78"},"schema_version":"1.0"},"canonical_sha256":"2febc176f659bcaefed4c5ea2c302247400c5195d80a0b52256362bc27b28e99","source":{"kind":"arxiv","id":"2605.26971","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26971","created_at":"2026-05-27T01:06:22Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26971v1","created_at":"2026-05-27T01:06:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26971","created_at":"2026-05-27T01:06:22Z"},{"alias_kind":"pith_short_12","alias_value":"F7V4C5XWLG6K","created_at":"2026-05-27T01:06:22Z"},{"alias_kind":"pith_short_16","alias_value":"F7V4C5XWLG6K57WU","created_at":"2026-05-27T01:06:22Z"},{"alias_kind":"pith_short_8","alias_value":"F7V4C5XW","created_at":"2026-05-27T01:06:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:F7V4C5XWLG6K57WUYXVCYMBCI5","target":"record","payload":{"canonical_record":{"source":{"id":"2605.26971","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T12:57:12Z","cross_cats_sorted":[],"title_canon_sha256":"9f85660f110225f7d4d69aa12fb74c746ff80e46068ba9a0d13a51c40314b414","abstract_canon_sha256":"57e0536d7d1fa8d1199c18605d1021d262456d5dfb480a2c4b984c33a3104e78"},"schema_version":"1.0"},"canonical_sha256":"2febc176f659bcaefed4c5ea2c302247400c5195d80a0b52256362bc27b28e99","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:22.148947Z","signature_b64":"YjlCC6y0WWrj0CvOe3Zx91hmmqFpoCHF1ZyaDqAgssS69nNL5GykeFU+taRsnAYxIrxVn18ULlRpjkSH4H1oBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2febc176f659bcaefed4c5ea2c302247400c5195d80a0b52256362bc27b28e99","last_reissued_at":"2026-05-27T01:06:22.148249Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:22.148249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.26971","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":"2026-05-27T01:06:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MnwGkVaZ2p6OunzklcaQR7vkvaktSSvAyYlDfnFlT9RGTHrKyJ7DUlI9FwOp7PSEO/pvcFI02rolp2UzPJ7GCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T19:53:39.836364Z"},"content_sha256":"bf16a587090f6bd028e9a2dc2146f6a535b10bb52d374b23520d985d030251c4","schema_version":"1.0","event_id":"sha256:bf16a587090f6bd028e9a2dc2146f6a535b10bb52d374b23520d985d030251c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:F7V4C5XWLG6K57WUYXVCYMBCI5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RLVR Datasets and Where to Find Them: Tracing Data Lineage for Better Training Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenming Tang, Hsiu-Yuan Huang, Kai Yang, Saiyong Yang, Sanwoo Lee, Weijie Liu, Yangkun Chen, Yunfang Wu","submitted_at":"2026-05-26T12:57:12Z","abstract_excerpt":"The proliferation of Reinforcement Learning from Verifiable Rewards (RLVR) datasets has exacerbated provenance collapse due to unclear lineage among existing datasets. To bridge this fragmented RLVR data landscape, we propose Atomic-source Tracing via Lineage-Aware Search (ATLAS), a systematic framework for tracing RLVR datasets back to their atomic sources, attributing over 99.7% of 1.45M instances to 20 atomic sources. Our analysis reveals that most RLVR datasets are variants of a small set of shared upstream sources, with few introducing genuinely new data, and many facing data contaminatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26971","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/2605.26971/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":"2026-05-27T01:06:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YgZDoiQFXx3kaA/ABuF9iyhqZO8Aiy1C/HgNGYoE2lu3kH5OljXM4Hq1np68xRTksJ4dTNm969MbGaXmoeAvDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T19:53:39.836748Z"},"content_sha256":"d705ae845b5b3abcd9f6c35ab557a5d45fdbf23c6f94c4e75646ca32a8ee0c11","schema_version":"1.0","event_id":"sha256:d705ae845b5b3abcd9f6c35ab557a5d45fdbf23c6f94c4e75646ca32a8ee0c11"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F7V4C5XWLG6K57WUYXVCYMBCI5/bundle.json","state_url":"https://pith.science/pith/F7V4C5XWLG6K57WUYXVCYMBCI5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F7V4C5XWLG6K57WUYXVCYMBCI5/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":"2026-06-02T19:53:39Z","links":{"resolver":"https://pith.science/pith/F7V4C5XWLG6K57WUYXVCYMBCI5","bundle":"https://pith.science/pith/F7V4C5XWLG6K57WUYXVCYMBCI5/bundle.json","state":"https://pith.science/pith/F7V4C5XWLG6K57WUYXVCYMBCI5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F7V4C5XWLG6K57WUYXVCYMBCI5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:F7V4C5XWLG6K57WUYXVCYMBCI5","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":"57e0536d7d1fa8d1199c18605d1021d262456d5dfb480a2c4b984c33a3104e78","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T12:57:12Z","title_canon_sha256":"9f85660f110225f7d4d69aa12fb74c746ff80e46068ba9a0d13a51c40314b414"},"schema_version":"1.0","source":{"id":"2605.26971","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26971","created_at":"2026-05-27T01:06:22Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26971v1","created_at":"2026-05-27T01:06:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26971","created_at":"2026-05-27T01:06:22Z"},{"alias_kind":"pith_short_12","alias_value":"F7V4C5XWLG6K","created_at":"2026-05-27T01:06:22Z"},{"alias_kind":"pith_short_16","alias_value":"F7V4C5XWLG6K57WU","created_at":"2026-05-27T01:06:22Z"},{"alias_kind":"pith_short_8","alias_value":"F7V4C5XW","created_at":"2026-05-27T01:06:22Z"}],"graph_snapshots":[{"event_id":"sha256:d705ae845b5b3abcd9f6c35ab557a5d45fdbf23c6f94c4e75646ca32a8ee0c11","target":"graph","created_at":"2026-05-27T01:06:22Z","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/2605.26971/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The proliferation of Reinforcement Learning from Verifiable Rewards (RLVR) datasets has exacerbated provenance collapse due to unclear lineage among existing datasets. To bridge this fragmented RLVR data landscape, we propose Atomic-source Tracing via Lineage-Aware Search (ATLAS), a systematic framework for tracing RLVR datasets back to their atomic sources, attributing over 99.7% of 1.45M instances to 20 atomic sources. Our analysis reveals that most RLVR datasets are variants of a small set of shared upstream sources, with few introducing genuinely new data, and many facing data contaminatio","authors_text":"Chenming Tang, Hsiu-Yuan Huang, Kai Yang, Saiyong Yang, Sanwoo Lee, Weijie Liu, Yangkun Chen, Yunfang Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T12:57:12Z","title":"RLVR Datasets and Where to Find Them: Tracing Data Lineage for Better Training Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26971","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:bf16a587090f6bd028e9a2dc2146f6a535b10bb52d374b23520d985d030251c4","target":"record","created_at":"2026-05-27T01:06:22Z","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":"57e0536d7d1fa8d1199c18605d1021d262456d5dfb480a2c4b984c33a3104e78","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T12:57:12Z","title_canon_sha256":"9f85660f110225f7d4d69aa12fb74c746ff80e46068ba9a0d13a51c40314b414"},"schema_version":"1.0","source":{"id":"2605.26971","kind":"arxiv","version":1}},"canonical_sha256":"2febc176f659bcaefed4c5ea2c302247400c5195d80a0b52256362bc27b28e99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2febc176f659bcaefed4c5ea2c302247400c5195d80a0b52256362bc27b28e99","first_computed_at":"2026-05-27T01:06:22.148249Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:06:22.148249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YjlCC6y0WWrj0CvOe3Zx91hmmqFpoCHF1ZyaDqAgssS69nNL5GykeFU+taRsnAYxIrxVn18ULlRpjkSH4H1oBg==","signature_status":"signed_v1","signed_at":"2026-05-27T01:06:22.148947Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26971","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf16a587090f6bd028e9a2dc2146f6a535b10bb52d374b23520d985d030251c4","sha256:d705ae845b5b3abcd9f6c35ab557a5d45fdbf23c6f94c4e75646ca32a8ee0c11"],"state_sha256":"30d28ecc430b0ba1a1ed1c7000c31436282e75f03ee39187a44170b19da08f52"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mSQNAs4v7EHszEvipG5F/Cjt5EAGpkKjz5d+D+ne0URHUuJlFthLYJp/KNZ+uGY1PW4Gb+PieqsA05DGsvVRCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T19:53:39.838905Z","bundle_sha256":"2dfa88b91da75ab030c29245922dd71efd75577b932fa8bb9beb90aea0723d98"}}