{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6G6QB4YSEFAI5FNUQVZOZCPO46","short_pith_number":"pith:6G6QB4YS","canonical_record":{"source":{"id":"2606.23611","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T17:11:15Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"82559285d401d0c2f6b82a14ba7f39ed013d8187cd94cee7136c4f546e50fb9a","abstract_canon_sha256":"1d922a901efde8a3378a118f28a576c78570dd098ff7374191e304e157848beb"},"schema_version":"1.0"},"canonical_sha256":"f1bd00f31221408e95b48572ec89eee79c23c9e8c50ffa7778040e0cbb8f4b04","source":{"kind":"arxiv","id":"2606.23611","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23611","created_at":"2026-06-23T03:14:32Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23611v1","created_at":"2026-06-23T03:14:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23611","created_at":"2026-06-23T03:14:32Z"},{"alias_kind":"pith_short_12","alias_value":"6G6QB4YSEFAI","created_at":"2026-06-23T03:14:32Z"},{"alias_kind":"pith_short_16","alias_value":"6G6QB4YSEFAI5FNU","created_at":"2026-06-23T03:14:32Z"},{"alias_kind":"pith_short_8","alias_value":"6G6QB4YS","created_at":"2026-06-23T03:14:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6G6QB4YSEFAI5FNUQVZOZCPO46","target":"record","payload":{"canonical_record":{"source":{"id":"2606.23611","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T17:11:15Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"82559285d401d0c2f6b82a14ba7f39ed013d8187cd94cee7136c4f546e50fb9a","abstract_canon_sha256":"1d922a901efde8a3378a118f28a576c78570dd098ff7374191e304e157848beb"},"schema_version":"1.0"},"canonical_sha256":"f1bd00f31221408e95b48572ec89eee79c23c9e8c50ffa7778040e0cbb8f4b04","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:32.220929Z","signature_b64":"a5QVZ5y1yfE7X28Zvkr5/w+JHKtLgbufCO9c8E9sJurSjxONudwMVwxwpiYSVmLhMXs/i12uZbobJvU+SFizCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1bd00f31221408e95b48572ec89eee79c23c9e8c50ffa7778040e0cbb8f4b04","last_reissued_at":"2026-06-23T03:14:32.220514Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:32.220514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.23611","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":"2026-06-23T03:14:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DfJS/vacH5AmpIZ6B4FHT9KGwxxlz4yAL1ncUqxd7Tgy5pt3doG/oJg1q7Rd6g4jTHGnnOvnO1yl8BY4LYucAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T11:51:18.171506Z"},"content_sha256":"ebd4104067b128f48ee7dffe293f7246a836832ba1455c496c7dbc7afecf6d58","schema_version":"1.0","event_id":"sha256:ebd4104067b128f48ee7dffe293f7246a836832ba1455c496c7dbc7afecf6d58"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6G6QB4YSEFAI5FNUQVZOZCPO46","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Selection Through Iterative Self-Filtering for Vision-Language Settings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aaron Courville, Andrei Liviu Nicolicioiu, Morgane M. Moss, Sarvjeet Singh Ghotra","submitted_at":"2026-06-22T17:11:15Z","abstract_excerpt":"The availability of large amounts of clean data is paramount to training neural networks. However, at large scales, manual oversight is impractical, resulting in sizeable datasets that can be very noisy. Attempts to mitigate this obstacle to producing performant vision-language models have so far involved heuristics, curated reference datasets, and using pre-trained models. Here we propose a novel, bootstrapped method in which a CLIP model is trained on an evolving, self-selected dataset. This evolving dataset constitutes a balance of filtered, highly probable clean samples as well as diverse "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23611","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/2606.23611/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":"2026-06-23T03:14:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"adWGB5E5r3+aIwGsz2L0IEhqe8J9RVVk6yJQTJY2HUTllA/WOePpZZAQ8fHJFTqJOYHM/2uXavuEjBsuCt4DCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T11:51:18.171882Z"},"content_sha256":"d7b07aba77553f7096b419919567573fc99792cadfd62b163c788b1f68dad43e","schema_version":"1.0","event_id":"sha256:d7b07aba77553f7096b419919567573fc99792cadfd62b163c788b1f68dad43e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6G6QB4YSEFAI5FNUQVZOZCPO46/bundle.json","state_url":"https://pith.science/pith/6G6QB4YSEFAI5FNUQVZOZCPO46/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6G6QB4YSEFAI5FNUQVZOZCPO46/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":"2026-06-28T11:51:18Z","links":{"resolver":"https://pith.science/pith/6G6QB4YSEFAI5FNUQVZOZCPO46","bundle":"https://pith.science/pith/6G6QB4YSEFAI5FNUQVZOZCPO46/bundle.json","state":"https://pith.science/pith/6G6QB4YSEFAI5FNUQVZOZCPO46/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6G6QB4YSEFAI5FNUQVZOZCPO46/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6G6QB4YSEFAI5FNUQVZOZCPO46","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":"1d922a901efde8a3378a118f28a576c78570dd098ff7374191e304e157848beb","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T17:11:15Z","title_canon_sha256":"82559285d401d0c2f6b82a14ba7f39ed013d8187cd94cee7136c4f546e50fb9a"},"schema_version":"1.0","source":{"id":"2606.23611","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23611","created_at":"2026-06-23T03:14:32Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23611v1","created_at":"2026-06-23T03:14:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23611","created_at":"2026-06-23T03:14:32Z"},{"alias_kind":"pith_short_12","alias_value":"6G6QB4YSEFAI","created_at":"2026-06-23T03:14:32Z"},{"alias_kind":"pith_short_16","alias_value":"6G6QB4YSEFAI5FNU","created_at":"2026-06-23T03:14:32Z"},{"alias_kind":"pith_short_8","alias_value":"6G6QB4YS","created_at":"2026-06-23T03:14:32Z"}],"graph_snapshots":[{"event_id":"sha256:d7b07aba77553f7096b419919567573fc99792cadfd62b163c788b1f68dad43e","target":"graph","created_at":"2026-06-23T03:14:32Z","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/2606.23611/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The availability of large amounts of clean data is paramount to training neural networks. However, at large scales, manual oversight is impractical, resulting in sizeable datasets that can be very noisy. Attempts to mitigate this obstacle to producing performant vision-language models have so far involved heuristics, curated reference datasets, and using pre-trained models. Here we propose a novel, bootstrapped method in which a CLIP model is trained on an evolving, self-selected dataset. This evolving dataset constitutes a balance of filtered, highly probable clean samples as well as diverse ","authors_text":"Aaron Courville, Andrei Liviu Nicolicioiu, Morgane M. Moss, Sarvjeet Singh Ghotra","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T17:11:15Z","title":"Data Selection Through Iterative Self-Filtering for Vision-Language Settings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23611","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:ebd4104067b128f48ee7dffe293f7246a836832ba1455c496c7dbc7afecf6d58","target":"record","created_at":"2026-06-23T03:14:32Z","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":"1d922a901efde8a3378a118f28a576c78570dd098ff7374191e304e157848beb","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T17:11:15Z","title_canon_sha256":"82559285d401d0c2f6b82a14ba7f39ed013d8187cd94cee7136c4f546e50fb9a"},"schema_version":"1.0","source":{"id":"2606.23611","kind":"arxiv","version":1}},"canonical_sha256":"f1bd00f31221408e95b48572ec89eee79c23c9e8c50ffa7778040e0cbb8f4b04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1bd00f31221408e95b48572ec89eee79c23c9e8c50ffa7778040e0cbb8f4b04","first_computed_at":"2026-06-23T03:14:32.220514Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:14:32.220514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a5QVZ5y1yfE7X28Zvkr5/w+JHKtLgbufCO9c8E9sJurSjxONudwMVwxwpiYSVmLhMXs/i12uZbobJvU+SFizCw==","signature_status":"signed_v1","signed_at":"2026-06-23T03:14:32.220929Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.23611","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ebd4104067b128f48ee7dffe293f7246a836832ba1455c496c7dbc7afecf6d58","sha256:d7b07aba77553f7096b419919567573fc99792cadfd62b163c788b1f68dad43e"],"state_sha256":"c50cad23d62a96c30961bfa333d1f03e49c5ea8aa2e94039a44db58999666a60"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sJzzNma+TjwiLOf9QcrVCmiR428GU0fVPXD7Fc73d+rMLNjz0Zv+YBq5JSDk1BB5HVWEqjOTREe18n0wzebECw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T11:51:18.173838Z","bundle_sha256":"dd4c2d9c5bc627ca93e6fe16a6a0731a087b4801686a1e7dbd9e22df83825336"}}