{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HJ3FTMLXBKURVUM67ANOPN2TAM","short_pith_number":"pith:HJ3FTMLX","canonical_record":{"source":{"id":"2502.10341","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T18:02:37Z","cross_cats_sorted":[],"title_canon_sha256":"533488a7fa660799330d43c0567433080552c5ac1e446fa895a484405995cf3e","abstract_canon_sha256":"bea927436e0d8c216ea8e39c5b6355fd3ffb5966bd8b7054bbadab542590b015"},"schema_version":"1.0"},"canonical_sha256":"3a7659b1770aa91ad19ef81ae7b7530304b0bb01c69eb4a720200974d99c696d","source":{"kind":"arxiv","id":"2502.10341","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10341","created_at":"2026-07-05T11:38:04Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10341v3","created_at":"2026-07-05T11:38:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10341","created_at":"2026-07-05T11:38:04Z"},{"alias_kind":"pith_short_12","alias_value":"HJ3FTMLXBKUR","created_at":"2026-07-05T11:38:04Z"},{"alias_kind":"pith_short_16","alias_value":"HJ3FTMLXBKURVUM6","created_at":"2026-07-05T11:38:04Z"},{"alias_kind":"pith_short_8","alias_value":"HJ3FTMLX","created_at":"2026-07-05T11:38:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HJ3FTMLXBKURVUM67ANOPN2TAM","target":"record","payload":{"canonical_record":{"source":{"id":"2502.10341","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T18:02:37Z","cross_cats_sorted":[],"title_canon_sha256":"533488a7fa660799330d43c0567433080552c5ac1e446fa895a484405995cf3e","abstract_canon_sha256":"bea927436e0d8c216ea8e39c5b6355fd3ffb5966bd8b7054bbadab542590b015"},"schema_version":"1.0"},"canonical_sha256":"3a7659b1770aa91ad19ef81ae7b7530304b0bb01c69eb4a720200974d99c696d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:04.611373Z","signature_b64":"0bAADfrTKvGihSg5WFetwsSAf5TAPJ1zPjpIaSn3vy4t88agO3ygEjQ9i9TeaaHKVGx1yEtV8Kb+fZXyPolJDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a7659b1770aa91ad19ef81ae7b7530304b0bb01c69eb4a720200974d99c696d","last_reissued_at":"2026-07-05T11:38:04.610822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:04.610822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.10341","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:38:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tO+EGpnU+6tvJhbHA28tsc7O6xVbcJwxdAF2XQPh0T4rkRYQCu++aYhcbxxhSox8D5qQ8d49AuZG1qjHAI0kAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:25:34.791113Z"},"content_sha256":"f351efd3587252ca40a3bdcfa277ba31260437652671e991ff0fe115d47df3d3","schema_version":"1.0","event_id":"sha256:f351efd3587252ca40a3bdcfa277ba31260437652671e991ff0fe115d47df3d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HJ3FTMLXBKURVUM67ANOPN2TAM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Organize the Web: Constructing Domains Enhances Pre-Training Data Curation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Wettig, Danqi Chen, Hannaneh Hajishirzi, Kyle Lo, Luca Soldaini, Sewon Min","submitted_at":"2025-02-14T18:02:37Z","abstract_excerpt":"Modern language models are trained on large, unstructured datasets consisting of trillions of tokens and obtained by crawling the web. The unstructured nature makes it difficult to reason about their contents and develop systematic approaches to data curation. In this paper, we unpack monolithic web corpora by developing taxonomies of their contents and organizing them into domains. We introduce WebOrganizer, a framework for organizing web pages in terms of both their topic and format. Using these two complementary notions of domains, we automatically annotate pre-training data by distilling a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10341","kind":"arxiv","version":3},"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/2502.10341/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":"2026-07-05T11:38:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s/GV7VY3g7b0IcRlP/p+lmJzK1b62F83PlE5itmjeW8h6BXU0MlTTzD9BVMxokNgYRSCrO+7RwqZbioWJs80DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:25:34.791667Z"},"content_sha256":"06bf3a99b35967df6518527dafad346801dfa804991969ad927874c033ebb7da","schema_version":"1.0","event_id":"sha256:06bf3a99b35967df6518527dafad346801dfa804991969ad927874c033ebb7da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HJ3FTMLXBKURVUM67ANOPN2TAM/bundle.json","state_url":"https://pith.science/pith/HJ3FTMLXBKURVUM67ANOPN2TAM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HJ3FTMLXBKURVUM67ANOPN2TAM/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":"2026-08-08T11:25:34Z","links":{"resolver":"https://pith.science/pith/HJ3FTMLXBKURVUM67ANOPN2TAM","bundle":"https://pith.science/pith/HJ3FTMLXBKURVUM67ANOPN2TAM/bundle.json","state":"https://pith.science/pith/HJ3FTMLXBKURVUM67ANOPN2TAM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HJ3FTMLXBKURVUM67ANOPN2TAM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HJ3FTMLXBKURVUM67ANOPN2TAM","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":"bea927436e0d8c216ea8e39c5b6355fd3ffb5966bd8b7054bbadab542590b015","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T18:02:37Z","title_canon_sha256":"533488a7fa660799330d43c0567433080552c5ac1e446fa895a484405995cf3e"},"schema_version":"1.0","source":{"id":"2502.10341","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10341","created_at":"2026-07-05T11:38:04Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10341v3","created_at":"2026-07-05T11:38:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10341","created_at":"2026-07-05T11:38:04Z"},{"alias_kind":"pith_short_12","alias_value":"HJ3FTMLXBKUR","created_at":"2026-07-05T11:38:04Z"},{"alias_kind":"pith_short_16","alias_value":"HJ3FTMLXBKURVUM6","created_at":"2026-07-05T11:38:04Z"},{"alias_kind":"pith_short_8","alias_value":"HJ3FTMLX","created_at":"2026-07-05T11:38:04Z"}],"graph_snapshots":[{"event_id":"sha256:06bf3a99b35967df6518527dafad346801dfa804991969ad927874c033ebb7da","target":"graph","created_at":"2026-07-05T11:38:04Z","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/2502.10341/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern language models are trained on large, unstructured datasets consisting of trillions of tokens and obtained by crawling the web. The unstructured nature makes it difficult to reason about their contents and develop systematic approaches to data curation. In this paper, we unpack monolithic web corpora by developing taxonomies of their contents and organizing them into domains. We introduce WebOrganizer, a framework for organizing web pages in terms of both their topic and format. Using these two complementary notions of domains, we automatically annotate pre-training data by distilling a","authors_text":"Alexander Wettig, Danqi Chen, Hannaneh Hajishirzi, Kyle Lo, Luca Soldaini, Sewon Min","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T18:02:37Z","title":"Organize the Web: Constructing Domains Enhances Pre-Training Data Curation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10341","kind":"arxiv","version":3},"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:f351efd3587252ca40a3bdcfa277ba31260437652671e991ff0fe115d47df3d3","target":"record","created_at":"2026-07-05T11:38:04Z","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":"bea927436e0d8c216ea8e39c5b6355fd3ffb5966bd8b7054bbadab542590b015","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T18:02:37Z","title_canon_sha256":"533488a7fa660799330d43c0567433080552c5ac1e446fa895a484405995cf3e"},"schema_version":"1.0","source":{"id":"2502.10341","kind":"arxiv","version":3}},"canonical_sha256":"3a7659b1770aa91ad19ef81ae7b7530304b0bb01c69eb4a720200974d99c696d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a7659b1770aa91ad19ef81ae7b7530304b0bb01c69eb4a720200974d99c696d","first_computed_at":"2026-07-05T11:38:04.610822Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:04.610822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0bAADfrTKvGihSg5WFetwsSAf5TAPJ1zPjpIaSn3vy4t88agO3ygEjQ9i9TeaaHKVGx1yEtV8Kb+fZXyPolJDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:04.611373Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.10341","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f351efd3587252ca40a3bdcfa277ba31260437652671e991ff0fe115d47df3d3","sha256:06bf3a99b35967df6518527dafad346801dfa804991969ad927874c033ebb7da"],"state_sha256":"abf0e0b0efacffc2fbbc01e920fa566f533d2af683424eaed464cc7247ac6201"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NyRhzvyWAjG2hwROU034bOe4JwQEtcWb1otW47NEkNoajyJWEoWP22qkT1BavgDDCI73SsYXVRNx2krElsS6Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:25:34.796375Z","bundle_sha256":"da23ecc631f2df856814a824a710ef15b99c53405187e53852e9a099252515eb"}}