{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:DPC63LPF3MMDKWQ2MR2PQGXBVC","short_pith_number":"pith:DPC63LPF","canonical_record":{"source":{"id":"2212.14099","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-28T21:22:57Z","cross_cats_sorted":[],"title_canon_sha256":"efb75ccb2abd400ec4dcd8dd738119cecfcd87156c6d80a6c877404a9f457d51","abstract_canon_sha256":"28afad3b4170c6d7235f3a8a1968ddac67fc6c33366dec0052b3ac7ec19f0762"},"schema_version":"1.0"},"canonical_sha256":"1bc5edade5db18355a1a6474f81ae1a88689a71869edb31351540b82ad86d036","source":{"kind":"arxiv","id":"2212.14099","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.14099","created_at":"2026-07-05T05:29:06Z"},{"alias_kind":"arxiv_version","alias_value":"2212.14099v1","created_at":"2026-07-05T05:29:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.14099","created_at":"2026-07-05T05:29:06Z"},{"alias_kind":"pith_short_12","alias_value":"DPC63LPF3MMD","created_at":"2026-07-05T05:29:06Z"},{"alias_kind":"pith_short_16","alias_value":"DPC63LPF3MMDKWQ2","created_at":"2026-07-05T05:29:06Z"},{"alias_kind":"pith_short_8","alias_value":"DPC63LPF","created_at":"2026-07-05T05:29:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:DPC63LPF3MMDKWQ2MR2PQGXBVC","target":"record","payload":{"canonical_record":{"source":{"id":"2212.14099","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-28T21:22:57Z","cross_cats_sorted":[],"title_canon_sha256":"efb75ccb2abd400ec4dcd8dd738119cecfcd87156c6d80a6c877404a9f457d51","abstract_canon_sha256":"28afad3b4170c6d7235f3a8a1968ddac67fc6c33366dec0052b3ac7ec19f0762"},"schema_version":"1.0"},"canonical_sha256":"1bc5edade5db18355a1a6474f81ae1a88689a71869edb31351540b82ad86d036","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:29:06.124798Z","signature_b64":"WfaVBD3q7xrO6ZbD8NEsBTpM5wCTVob2DY6zwb6prAI/6nqfT/KHZmtmOEP/G7kjMIKX0kl072e8Dc02u4vBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bc5edade5db18355a1a6474f81ae1a88689a71869edb31351540b82ad86d036","last_reissued_at":"2026-07-05T05:29:06.124465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:29:06.124465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.14099","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":"2026-07-05T05:29:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Fv25gYW5ePb/SXNmM+gWsu1DZtrkB2nB2dVD/UF0tvy7tmmsMhOWjiuXyenjO7eNMKGnOH3EGIgH0rGEqk8DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:16:02.493684Z"},"content_sha256":"bab4dd20e42a9dc6b9ee9745bbbb62d0801dd88b2d3e7185f6aa4e78359962a7","schema_version":"1.0","event_id":"sha256:bab4dd20e42a9dc6b9ee9745bbbb62d0801dd88b2d3e7185f6aa4e78359962a7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:DPC63LPF3MMDKWQ2MR2PQGXBVC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Curator: Creating Large-Scale Curated Labelled Datasets using Self-Supervised Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ajay Krishnan, Anirudh Koul, Siddha Ganju, Tarun Narayanan","submitted_at":"2022-12-28T21:22:57Z","abstract_excerpt":"Applying Machine learning to domains like Earth Sciences is impeded by the lack of labeled data, despite a large corpus of raw data available in such domains. For instance, training a wildfire classifier on satellite imagery requires curating a massive and diverse dataset, which is an expensive and time-consuming process that can span from weeks to months. Searching for relevant examples in over 40 petabytes of unlabelled data requires researchers to manually hunt for such images, much like finding a needle in a haystack. We present a no-code end-to-end pipeline, Curator, which dramatically mi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.14099","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/2212.14099/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":"2026-07-05T05:29:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"26ak5iBgFvhaVi+1A8FtzMKtAIRG7/6luoW0A9e/QoklP7F46hGxS0HROTsX1VdcNuqhXUo1jzJPp8OcVg3nDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:16:02.494055Z"},"content_sha256":"49ec2484a0c8fac3321950adc1f112f69d7eff19e8a35775d85fa1b3aa1da2ae","schema_version":"1.0","event_id":"sha256:49ec2484a0c8fac3321950adc1f112f69d7eff19e8a35775d85fa1b3aa1da2ae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DPC63LPF3MMDKWQ2MR2PQGXBVC/bundle.json","state_url":"https://pith.science/pith/DPC63LPF3MMDKWQ2MR2PQGXBVC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DPC63LPF3MMDKWQ2MR2PQGXBVC/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":"2026-07-09T05:16:02Z","links":{"resolver":"https://pith.science/pith/DPC63LPF3MMDKWQ2MR2PQGXBVC","bundle":"https://pith.science/pith/DPC63LPF3MMDKWQ2MR2PQGXBVC/bundle.json","state":"https://pith.science/pith/DPC63LPF3MMDKWQ2MR2PQGXBVC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DPC63LPF3MMDKWQ2MR2PQGXBVC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DPC63LPF3MMDKWQ2MR2PQGXBVC","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":"28afad3b4170c6d7235f3a8a1968ddac67fc6c33366dec0052b3ac7ec19f0762","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-28T21:22:57Z","title_canon_sha256":"efb75ccb2abd400ec4dcd8dd738119cecfcd87156c6d80a6c877404a9f457d51"},"schema_version":"1.0","source":{"id":"2212.14099","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.14099","created_at":"2026-07-05T05:29:06Z"},{"alias_kind":"arxiv_version","alias_value":"2212.14099v1","created_at":"2026-07-05T05:29:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.14099","created_at":"2026-07-05T05:29:06Z"},{"alias_kind":"pith_short_12","alias_value":"DPC63LPF3MMD","created_at":"2026-07-05T05:29:06Z"},{"alias_kind":"pith_short_16","alias_value":"DPC63LPF3MMDKWQ2","created_at":"2026-07-05T05:29:06Z"},{"alias_kind":"pith_short_8","alias_value":"DPC63LPF","created_at":"2026-07-05T05:29:06Z"}],"graph_snapshots":[{"event_id":"sha256:49ec2484a0c8fac3321950adc1f112f69d7eff19e8a35775d85fa1b3aa1da2ae","target":"graph","created_at":"2026-07-05T05:29:06Z","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/2212.14099/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Applying Machine learning to domains like Earth Sciences is impeded by the lack of labeled data, despite a large corpus of raw data available in such domains. For instance, training a wildfire classifier on satellite imagery requires curating a massive and diverse dataset, which is an expensive and time-consuming process that can span from weeks to months. Searching for relevant examples in over 40 petabytes of unlabelled data requires researchers to manually hunt for such images, much like finding a needle in a haystack. We present a no-code end-to-end pipeline, Curator, which dramatically mi","authors_text":"Ajay Krishnan, Anirudh Koul, Siddha Ganju, Tarun Narayanan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-28T21:22:57Z","title":"Curator: Creating Large-Scale Curated Labelled Datasets using Self-Supervised Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.14099","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:bab4dd20e42a9dc6b9ee9745bbbb62d0801dd88b2d3e7185f6aa4e78359962a7","target":"record","created_at":"2026-07-05T05:29:06Z","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":"28afad3b4170c6d7235f3a8a1968ddac67fc6c33366dec0052b3ac7ec19f0762","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-28T21:22:57Z","title_canon_sha256":"efb75ccb2abd400ec4dcd8dd738119cecfcd87156c6d80a6c877404a9f457d51"},"schema_version":"1.0","source":{"id":"2212.14099","kind":"arxiv","version":1}},"canonical_sha256":"1bc5edade5db18355a1a6474f81ae1a88689a71869edb31351540b82ad86d036","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1bc5edade5db18355a1a6474f81ae1a88689a71869edb31351540b82ad86d036","first_computed_at":"2026-07-05T05:29:06.124465Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:29:06.124465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WfaVBD3q7xrO6ZbD8NEsBTpM5wCTVob2DY6zwb6prAI/6nqfT/KHZmtmOEP/G7kjMIKX0kl072e8Dc02u4vBBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:29:06.124798Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.14099","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bab4dd20e42a9dc6b9ee9745bbbb62d0801dd88b2d3e7185f6aa4e78359962a7","sha256:49ec2484a0c8fac3321950adc1f112f69d7eff19e8a35775d85fa1b3aa1da2ae"],"state_sha256":"162e3dda3c1baf55117ff13d3615699bd613b7c26cf93e945c5f607487517097"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4vaqVLwA/vQIUabUvn6EPXO4Z1R098LG/Ux8SQhVUGuVG7fMvOQ4LwRUwN/LC3wz4URbUax6VuUsI7f9oSj/DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:16:02.497362Z","bundle_sha256":"629416a2fb031d07fb3e5a5536eeaff7adfb36dffde35f3f4e29f50e4a8edb93"}}