{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NDEWNSAFFVBF5GV4YCHDKGKOAU","short_pith_number":"pith:NDEWNSAF","canonical_record":{"source":{"id":"2606.28471","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-26T14:45:57Z","cross_cats_sorted":[],"title_canon_sha256":"44de35d19f470afb78098781e6ecd4a137593cca6b053ea2daa5216841c7a97b","abstract_canon_sha256":"804ae25e9cc5c4b5af3b1f1a571c380c7212fa54a6417a64d0919afa527b50a1"},"schema_version":"1.0"},"canonical_sha256":"68c966c8052d425e9abcc08e35194e050e3c296654c573b8d6f8b412eca6c288","source":{"kind":"arxiv","id":"2606.28471","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.28471","created_at":"2026-06-30T00:15:15Z"},{"alias_kind":"arxiv_version","alias_value":"2606.28471v1","created_at":"2026-06-30T00:15:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28471","created_at":"2026-06-30T00:15:15Z"},{"alias_kind":"pith_short_12","alias_value":"NDEWNSAFFVBF","created_at":"2026-06-30T00:15:15Z"},{"alias_kind":"pith_short_16","alias_value":"NDEWNSAFFVBF5GV4","created_at":"2026-06-30T00:15:15Z"},{"alias_kind":"pith_short_8","alias_value":"NDEWNSAF","created_at":"2026-06-30T00:15:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NDEWNSAFFVBF5GV4YCHDKGKOAU","target":"record","payload":{"canonical_record":{"source":{"id":"2606.28471","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-26T14:45:57Z","cross_cats_sorted":[],"title_canon_sha256":"44de35d19f470afb78098781e6ecd4a137593cca6b053ea2daa5216841c7a97b","abstract_canon_sha256":"804ae25e9cc5c4b5af3b1f1a571c380c7212fa54a6417a64d0919afa527b50a1"},"schema_version":"1.0"},"canonical_sha256":"68c966c8052d425e9abcc08e35194e050e3c296654c573b8d6f8b412eca6c288","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T00:15:15.221245Z","signature_b64":"xEY3ZB2AWKd85YWeucLKPUb16nbSL8dHVp7yHQ2FomWgcTmfgxkMTq1CJXgPMIoZG/BcfCymOvJUiONc1B/bBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68c966c8052d425e9abcc08e35194e050e3c296654c573b8d6f8b412eca6c288","last_reissued_at":"2026-06-30T00:15:15.220837Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T00:15:15.220837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.28471","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":"2026-06-30T00:15:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xuJR0Wsca8u6em6AXGOg+itm/QT3Rpn//Q5zcnDY+tP3qqc62CLL6exozRnfq2lIhqjka0LpjG3mht3RSHZACQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T22:59:59.271657Z"},"content_sha256":"d659b2dae803f6e85b7d6ccb7bb4b73cf97e8c3a8974918e2faecd09b9e75803","schema_version":"1.0","event_id":"sha256:d659b2dae803f6e85b7d6ccb7bb4b73cf97e8c3a8974918e2faecd09b9e75803"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NDEWNSAFFVBF5GV4YCHDKGKOAU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data and Evaluation Closed-Loop for Model Capability Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Han Xu, Jiangan Yuan, Zhixuan Li","submitted_at":"2026-06-26T14:45:57Z","abstract_excerpt":"Model capability is the central variable in LLM pre-training, yet is never observed directly: data shapes it prospectively, while evaluation reveals it only retrospectively, compressing samples, prompts, decoding, and scoring rules into one noisy score. Practical optimization runs this backward: a failure is observed first, and the engineer must infer the corpus fix. The two sides speak incompatible vocabularies -- benchmark names and per-sample correctness versus data sources, domains, and quality labels -- so this inference is usually intuition, not method. We close this gap with the \\emph{c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28471","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/2606.28471/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":"2026-06-30T00:15:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/YZ6HhT3S12lh3a8tby8GNhHxgfudxG8vicl60Qc84pg/aiwg8X0ezoDGVgfZY8G6FCVnEFNplRl7dUi6CdRCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T22:59:59.272304Z"},"content_sha256":"6286ac4e5ce7e7412bc5205c672302771156622fd688b4bd06ce930637d36dfd","schema_version":"1.0","event_id":"sha256:6286ac4e5ce7e7412bc5205c672302771156622fd688b4bd06ce930637d36dfd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NDEWNSAFFVBF5GV4YCHDKGKOAU/bundle.json","state_url":"https://pith.science/pith/NDEWNSAFFVBF5GV4YCHDKGKOAU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NDEWNSAFFVBF5GV4YCHDKGKOAU/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":"2026-07-01T22:59:59Z","links":{"resolver":"https://pith.science/pith/NDEWNSAFFVBF5GV4YCHDKGKOAU","bundle":"https://pith.science/pith/NDEWNSAFFVBF5GV4YCHDKGKOAU/bundle.json","state":"https://pith.science/pith/NDEWNSAFFVBF5GV4YCHDKGKOAU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NDEWNSAFFVBF5GV4YCHDKGKOAU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NDEWNSAFFVBF5GV4YCHDKGKOAU","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":"804ae25e9cc5c4b5af3b1f1a571c380c7212fa54a6417a64d0919afa527b50a1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-26T14:45:57Z","title_canon_sha256":"44de35d19f470afb78098781e6ecd4a137593cca6b053ea2daa5216841c7a97b"},"schema_version":"1.0","source":{"id":"2606.28471","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.28471","created_at":"2026-06-30T00:15:15Z"},{"alias_kind":"arxiv_version","alias_value":"2606.28471v1","created_at":"2026-06-30T00:15:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28471","created_at":"2026-06-30T00:15:15Z"},{"alias_kind":"pith_short_12","alias_value":"NDEWNSAFFVBF","created_at":"2026-06-30T00:15:15Z"},{"alias_kind":"pith_short_16","alias_value":"NDEWNSAFFVBF5GV4","created_at":"2026-06-30T00:15:15Z"},{"alias_kind":"pith_short_8","alias_value":"NDEWNSAF","created_at":"2026-06-30T00:15:15Z"}],"graph_snapshots":[{"event_id":"sha256:6286ac4e5ce7e7412bc5205c672302771156622fd688b4bd06ce930637d36dfd","target":"graph","created_at":"2026-06-30T00:15:15Z","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/2606.28471/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model capability is the central variable in LLM pre-training, yet is never observed directly: data shapes it prospectively, while evaluation reveals it only retrospectively, compressing samples, prompts, decoding, and scoring rules into one noisy score. Practical optimization runs this backward: a failure is observed first, and the engineer must infer the corpus fix. The two sides speak incompatible vocabularies -- benchmark names and per-sample correctness versus data sources, domains, and quality labels -- so this inference is usually intuition, not method. We close this gap with the \\emph{c","authors_text":"Han Xu, Jiangan Yuan, Zhixuan Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-26T14:45:57Z","title":"Data and Evaluation Closed-Loop for Model Capability Enhancement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28471","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:d659b2dae803f6e85b7d6ccb7bb4b73cf97e8c3a8974918e2faecd09b9e75803","target":"record","created_at":"2026-06-30T00:15:15Z","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":"804ae25e9cc5c4b5af3b1f1a571c380c7212fa54a6417a64d0919afa527b50a1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-26T14:45:57Z","title_canon_sha256":"44de35d19f470afb78098781e6ecd4a137593cca6b053ea2daa5216841c7a97b"},"schema_version":"1.0","source":{"id":"2606.28471","kind":"arxiv","version":1}},"canonical_sha256":"68c966c8052d425e9abcc08e35194e050e3c296654c573b8d6f8b412eca6c288","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68c966c8052d425e9abcc08e35194e050e3c296654c573b8d6f8b412eca6c288","first_computed_at":"2026-06-30T00:15:15.220837Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T00:15:15.220837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xEY3ZB2AWKd85YWeucLKPUb16nbSL8dHVp7yHQ2FomWgcTmfgxkMTq1CJXgPMIoZG/BcfCymOvJUiONc1B/bBA==","signature_status":"signed_v1","signed_at":"2026-06-30T00:15:15.221245Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.28471","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d659b2dae803f6e85b7d6ccb7bb4b73cf97e8c3a8974918e2faecd09b9e75803","sha256:6286ac4e5ce7e7412bc5205c672302771156622fd688b4bd06ce930637d36dfd"],"state_sha256":"c050a8d2e1b9057805984a94649973320cd1a93282d24899ed343e9fe900eafd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MgOlMtr1FHDgmG8+JQLuoBdzFvGWnwGHGKNeYAkxZG/aqHyWt6lTs78uVjSXSCNMI5dASFQSRyhoIjzhR5crAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T22:59:59.275720Z","bundle_sha256":"d156a87e6b6ffd22c9bfac18ddb13ff93f5656b48d12bdd6cee02ea42ce9053d"}}