{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DBY2YMV6W7ZLOCTSM7IEYLPNJZ","short_pith_number":"pith:DBY2YMV6","canonical_record":{"source":{"id":"2306.13141","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2023-06-22T18:00:17Z","cross_cats_sorted":[],"title_canon_sha256":"408e7d37239d2151f892249aa06a6e5fad2cb3399265a2402bdb3cf16f7f76d1","abstract_canon_sha256":"31a56bc56d59916b515b0d3813c9eafe6a6bb0e1b646b47e709db358b45dc5f5"},"schema_version":"1.0"},"canonical_sha256":"1871ac32beb7f2b70a7267d04c2ded4e4cfe0dfcee006b3405322080559223a2","source":{"kind":"arxiv","id":"2306.13141","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.13141","created_at":"2026-07-05T06:26:03Z"},{"alias_kind":"arxiv_version","alias_value":"2306.13141v2","created_at":"2026-07-05T06:26:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.13141","created_at":"2026-07-05T06:26:03Z"},{"alias_kind":"pith_short_12","alias_value":"DBY2YMV6W7ZL","created_at":"2026-07-05T06:26:03Z"},{"alias_kind":"pith_short_16","alias_value":"DBY2YMV6W7ZLOCTS","created_at":"2026-07-05T06:26:03Z"},{"alias_kind":"pith_short_8","alias_value":"DBY2YMV6","created_at":"2026-07-05T06:26:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DBY2YMV6W7ZLOCTSM7IEYLPNJZ","target":"record","payload":{"canonical_record":{"source":{"id":"2306.13141","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2023-06-22T18:00:17Z","cross_cats_sorted":[],"title_canon_sha256":"408e7d37239d2151f892249aa06a6e5fad2cb3399265a2402bdb3cf16f7f76d1","abstract_canon_sha256":"31a56bc56d59916b515b0d3813c9eafe6a6bb0e1b646b47e709db358b45dc5f5"},"schema_version":"1.0"},"canonical_sha256":"1871ac32beb7f2b70a7267d04c2ded4e4cfe0dfcee006b3405322080559223a2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:03.279438Z","signature_b64":"vABFwE/KSzy02T5nEcekmmHd3qIecZzNNHmZQYpauc2cwHRBbHxfSsB6hSIKu3El1tJqgJi9KFRi8c0NIz8TDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1871ac32beb7f2b70a7267d04c2ded4e4cfe0dfcee006b3405322080559223a2","last_reissued_at":"2026-07-05T06:26:03.278968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:03.278968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.13141","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":"2026-07-05T06:26:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"txHgxF4c7WmLOT/JeRpQJfrsEQ2grYAHjDnmQZcWvBwk8/xVcjl8Xe1jfdZaqhKqn/tH6KksMFiqkfowWoRAAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:38:19.943985Z"},"content_sha256":"1823a0a9494aae100a42fc7dad6b193bec1ce85b4b7e194d53a6f19aabffb6e3","schema_version":"1.0","event_id":"sha256:1823a0a9494aae100a42fc7dad6b193bec1ce85b4b7e194d53a6f19aabffb6e3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DBY2YMV6W7ZLOCTSM7IEYLPNJZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Hate Scaling Laws For Data-Swamps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Abeba Birhane, Sang Han, Vinay Prabhu, Vishnu Naresh Boddeti","submitted_at":"2023-06-22T18:00:17Z","abstract_excerpt":"`Scale the model, scale the data, scale the GPU-farms' is the reigning sentiment in the world of generative AI today. While model scaling has been extensively studied, data scaling and its downstream impacts remain under explored. This is especially of critical importance in the context of visio-linguistic datasets whose main source is the World Wide Web, condensed and packaged as the CommonCrawl dump. This large scale data-dump, which is known to have numerous drawbacks, is repeatedly mined and serves as the data-motherlode for large generative models. In this paper, we: 1) investigate the ef"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.13141","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.13141/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":"2026-07-05T06:26:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3PVG32C83Vm4qAwN2uxovGaEGZGBNkfHGc30Rl20hbkpKPIMSjMj89esAczJMmO5usCsj8r2EdALQTUmeCN0BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:38:19.944916Z"},"content_sha256":"c4fc63618e8abaf05098a15340aab0716cebf679515145c853335d9820667f6c","schema_version":"1.0","event_id":"sha256:c4fc63618e8abaf05098a15340aab0716cebf679515145c853335d9820667f6c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DBY2YMV6W7ZLOCTSM7IEYLPNJZ/bundle.json","state_url":"https://pith.science/pith/DBY2YMV6W7ZLOCTSM7IEYLPNJZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DBY2YMV6W7ZLOCTSM7IEYLPNJZ/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":"2026-08-09T17:38:19Z","links":{"resolver":"https://pith.science/pith/DBY2YMV6W7ZLOCTSM7IEYLPNJZ","bundle":"https://pith.science/pith/DBY2YMV6W7ZLOCTSM7IEYLPNJZ/bundle.json","state":"https://pith.science/pith/DBY2YMV6W7ZLOCTSM7IEYLPNJZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DBY2YMV6W7ZLOCTSM7IEYLPNJZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DBY2YMV6W7ZLOCTSM7IEYLPNJZ","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":"31a56bc56d59916b515b0d3813c9eafe6a6bb0e1b646b47e709db358b45dc5f5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2023-06-22T18:00:17Z","title_canon_sha256":"408e7d37239d2151f892249aa06a6e5fad2cb3399265a2402bdb3cf16f7f76d1"},"schema_version":"1.0","source":{"id":"2306.13141","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.13141","created_at":"2026-07-05T06:26:03Z"},{"alias_kind":"arxiv_version","alias_value":"2306.13141v2","created_at":"2026-07-05T06:26:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.13141","created_at":"2026-07-05T06:26:03Z"},{"alias_kind":"pith_short_12","alias_value":"DBY2YMV6W7ZL","created_at":"2026-07-05T06:26:03Z"},{"alias_kind":"pith_short_16","alias_value":"DBY2YMV6W7ZLOCTS","created_at":"2026-07-05T06:26:03Z"},{"alias_kind":"pith_short_8","alias_value":"DBY2YMV6","created_at":"2026-07-05T06:26:03Z"}],"graph_snapshots":[{"event_id":"sha256:c4fc63618e8abaf05098a15340aab0716cebf679515145c853335d9820667f6c","target":"graph","created_at":"2026-07-05T06:26:03Z","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/2306.13141/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"`Scale the model, scale the data, scale the GPU-farms' is the reigning sentiment in the world of generative AI today. While model scaling has been extensively studied, data scaling and its downstream impacts remain under explored. This is especially of critical importance in the context of visio-linguistic datasets whose main source is the World Wide Web, condensed and packaged as the CommonCrawl dump. This large scale data-dump, which is known to have numerous drawbacks, is repeatedly mined and serves as the data-motherlode for large generative models. In this paper, we: 1) investigate the ef","authors_text":"Abeba Birhane, Sang Han, Vinay Prabhu, Vishnu Naresh Boddeti","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2023-06-22T18:00:17Z","title":"On Hate Scaling Laws For Data-Swamps"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.13141","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":"sha256:1823a0a9494aae100a42fc7dad6b193bec1ce85b4b7e194d53a6f19aabffb6e3","target":"record","created_at":"2026-07-05T06:26:03Z","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":"31a56bc56d59916b515b0d3813c9eafe6a6bb0e1b646b47e709db358b45dc5f5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2023-06-22T18:00:17Z","title_canon_sha256":"408e7d37239d2151f892249aa06a6e5fad2cb3399265a2402bdb3cf16f7f76d1"},"schema_version":"1.0","source":{"id":"2306.13141","kind":"arxiv","version":2}},"canonical_sha256":"1871ac32beb7f2b70a7267d04c2ded4e4cfe0dfcee006b3405322080559223a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1871ac32beb7f2b70a7267d04c2ded4e4cfe0dfcee006b3405322080559223a2","first_computed_at":"2026-07-05T06:26:03.278968Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:26:03.278968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vABFwE/KSzy02T5nEcekmmHd3qIecZzNNHmZQYpauc2cwHRBbHxfSsB6hSIKu3El1tJqgJi9KFRi8c0NIz8TDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:26:03.279438Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.13141","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1823a0a9494aae100a42fc7dad6b193bec1ce85b4b7e194d53a6f19aabffb6e3","sha256:c4fc63618e8abaf05098a15340aab0716cebf679515145c853335d9820667f6c"],"state_sha256":"e6c002fd32e951f143fe2bd3892c218c70a746c3f1e63b1140c94b780723a776"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KsAdYXUCefiPxTbSuZigxkC0hKpcguIJRNpg9IoJyyRtNAipBgbcPe/sfTqRCdEPN/wRAOQx2nNpOZkAJqniBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T17:38:19.952937Z","bundle_sha256":"3922d20cf6a953c598f6dd58cd8f5b52b6424afae49adca84008796fbd182430"}}