{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:C2UWTKMJTCR7V4OQZ3ZH4GYBQE","short_pith_number":"pith:C2UWTKMJ","canonical_record":{"source":{"id":"1707.07409","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-24T05:33:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c891be664cb484843979305d172be0f241993281393edae24a3ffc8c83236ad5","abstract_canon_sha256":"91b2071af1f4e1787d790b6bf026aefd1f1c8c3ea388d1ea539be8682bb6fe4d"},"schema_version":"1.0"},"canonical_sha256":"16a969a98998a3faf1d0cef27e1b01810bbc245cbc9aafb88dd5b7b67e462d32","source":{"kind":"arxiv","id":"1707.07409","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.07409","created_at":"2026-05-18T00:39:30Z"},{"alias_kind":"arxiv_version","alias_value":"1707.07409v2","created_at":"2026-05-18T00:39:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.07409","created_at":"2026-05-18T00:39:30Z"},{"alias_kind":"pith_short_12","alias_value":"C2UWTKMJTCR7","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"C2UWTKMJTCR7V4OQ","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"C2UWTKMJ","created_at":"2026-05-18T12:31:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:C2UWTKMJTCR7V4OQZ3ZH4GYBQE","target":"record","payload":{"canonical_record":{"source":{"id":"1707.07409","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-24T05:33:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c891be664cb484843979305d172be0f241993281393edae24a3ffc8c83236ad5","abstract_canon_sha256":"91b2071af1f4e1787d790b6bf026aefd1f1c8c3ea388d1ea539be8682bb6fe4d"},"schema_version":"1.0"},"canonical_sha256":"16a969a98998a3faf1d0cef27e1b01810bbc245cbc9aafb88dd5b7b67e462d32","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:30.777068Z","signature_b64":"5Vb7nKwT/POtHDM85FYswNAN2ruQ9K96CFz+0lkK5c08ajKvzzQm8AWcuNS4CXO7GgYlzaPbnqe5ygev/2pYAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16a969a98998a3faf1d0cef27e1b01810bbc245cbc9aafb88dd5b7b67e462d32","last_reissued_at":"2026-05-18T00:39:30.776405Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:30.776405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.07409","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:39:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fJr1VnN+9qrtE++pU3VkgvOTqhwmSMvb2fLw+rPXnIUF580UVaa+vvAJ1Rg+nPMx749qhWGJ/UrPZzxjXjY5Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T03:22:30.720606Z"},"content_sha256":"1e03058bb9482ce441aa027e78322bc4970414b52ce2f15301b65068d28eaba5","schema_version":"1.0","event_id":"sha256:1e03058bb9482ce441aa027e78322bc4970414b52ce2f15301b65068d28eaba5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:C2UWTKMJTCR7V4OQZ3ZH4GYBQE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Big Data Regression Using Tree Based Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Rajiv Sambasivan, Sourish Das","submitted_at":"2017-07-24T05:33:37Z","abstract_excerpt":"Scaling regression to large datasets is a common problem in many application areas. We propose a two step approach to scaling regression to large datasets. Using a regression tree (CART) to segment the large dataset constitutes the first step of this approach. The second step of this approach is to develop a suitable regression model for each segment. Since segment sizes are not very large, we have the ability to apply sophisticated regression techniques if required. A nice feature of this two step approach is that it can yield models that have good explanatory power as well as good predictive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.07409","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:39:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XkVitbTZYVFM3KYmUATSLs4bHQ/k/49z4CQdFkQMXzcPeCuTVOjpdig84/12MJdaPWU4+knSmnAIF8pMyArKDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T03:22:30.721341Z"},"content_sha256":"8a4fa3b089f83a6e80e9d879c89b6cfa366fd730b15d02ad2b729518a4b364d0","schema_version":"1.0","event_id":"sha256:8a4fa3b089f83a6e80e9d879c89b6cfa366fd730b15d02ad2b729518a4b364d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C2UWTKMJTCR7V4OQZ3ZH4GYBQE/bundle.json","state_url":"https://pith.science/pith/C2UWTKMJTCR7V4OQZ3ZH4GYBQE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C2UWTKMJTCR7V4OQZ3ZH4GYBQE/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":"2026-06-12T03:22:30Z","links":{"resolver":"https://pith.science/pith/C2UWTKMJTCR7V4OQZ3ZH4GYBQE","bundle":"https://pith.science/pith/C2UWTKMJTCR7V4OQZ3ZH4GYBQE/bundle.json","state":"https://pith.science/pith/C2UWTKMJTCR7V4OQZ3ZH4GYBQE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C2UWTKMJTCR7V4OQZ3ZH4GYBQE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:C2UWTKMJTCR7V4OQZ3ZH4GYBQE","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":"91b2071af1f4e1787d790b6bf026aefd1f1c8c3ea388d1ea539be8682bb6fe4d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-24T05:33:37Z","title_canon_sha256":"c891be664cb484843979305d172be0f241993281393edae24a3ffc8c83236ad5"},"schema_version":"1.0","source":{"id":"1707.07409","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.07409","created_at":"2026-05-18T00:39:30Z"},{"alias_kind":"arxiv_version","alias_value":"1707.07409v2","created_at":"2026-05-18T00:39:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.07409","created_at":"2026-05-18T00:39:30Z"},{"alias_kind":"pith_short_12","alias_value":"C2UWTKMJTCR7","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"C2UWTKMJTCR7V4OQ","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"C2UWTKMJ","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:8a4fa3b089f83a6e80e9d879c89b6cfa366fd730b15d02ad2b729518a4b364d0","target":"graph","created_at":"2026-05-18T00:39:30Z","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"},"paper":{"abstract_excerpt":"Scaling regression to large datasets is a common problem in many application areas. We propose a two step approach to scaling regression to large datasets. Using a regression tree (CART) to segment the large dataset constitutes the first step of this approach. The second step of this approach is to develop a suitable regression model for each segment. Since segment sizes are not very large, we have the ability to apply sophisticated regression techniques if required. A nice feature of this two step approach is that it can yield models that have good explanatory power as well as good predictive","authors_text":"Rajiv Sambasivan, Sourish Das","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-24T05:33:37Z","title":"Big Data Regression Using Tree Based Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.07409","kind":"arxiv","version":2},"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":"sha256:1e03058bb9482ce441aa027e78322bc4970414b52ce2f15301b65068d28eaba5","target":"record","created_at":"2026-05-18T00:39:30Z","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":"91b2071af1f4e1787d790b6bf026aefd1f1c8c3ea388d1ea539be8682bb6fe4d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-24T05:33:37Z","title_canon_sha256":"c891be664cb484843979305d172be0f241993281393edae24a3ffc8c83236ad5"},"schema_version":"1.0","source":{"id":"1707.07409","kind":"arxiv","version":2}},"canonical_sha256":"16a969a98998a3faf1d0cef27e1b01810bbc245cbc9aafb88dd5b7b67e462d32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16a969a98998a3faf1d0cef27e1b01810bbc245cbc9aafb88dd5b7b67e462d32","first_computed_at":"2026-05-18T00:39:30.776405Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:39:30.776405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5Vb7nKwT/POtHDM85FYswNAN2ruQ9K96CFz+0lkK5c08ajKvzzQm8AWcuNS4CXO7GgYlzaPbnqe5ygev/2pYAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:39:30.777068Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.07409","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e03058bb9482ce441aa027e78322bc4970414b52ce2f15301b65068d28eaba5","sha256:8a4fa3b089f83a6e80e9d879c89b6cfa366fd730b15d02ad2b729518a4b364d0"],"state_sha256":"22b7a11bc54901a39ef1f72aef20fb59fd9a05adcf0117f8b3cbfb01829608b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nUFpeongIkqrcg7sS+2gB64qWA4Hro9dBdPHgfUGZbQupUio3iD1el0hRwzRLX2927F/vRPcmXc7SlJTKr4eBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T03:22:30.725884Z","bundle_sha256":"04fd7ca77b4c7d0c9145474cd50b172b5f1427a9c83e5a35be1c8e9a44268ad8"}}