{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Z5BOOC46S4XZK7N74NFE6QOQ7S","short_pith_number":"pith:Z5BOOC46","canonical_record":{"source":{"id":"2409.13860","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-20T19:17:52Z","cross_cats_sorted":[],"title_canon_sha256":"f6d23861080a59b69932ef9317099e4c12c9afd817c97d0dcc7558a875e8df22","abstract_canon_sha256":"0b21df90a96161dd1a917382884be5d5b288cf539dd3f37575761a2a849847c8"},"schema_version":"1.0"},"canonical_sha256":"cf42e70b9e972f957dbfe34a4f41d0fcb8770bacae94273a48d966b3f89c94d0","source":{"kind":"arxiv","id":"2409.13860","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.13860","created_at":"2026-07-05T09:10:07Z"},{"alias_kind":"arxiv_version","alias_value":"2409.13860v1","created_at":"2026-07-05T09:10:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13860","created_at":"2026-07-05T09:10:07Z"},{"alias_kind":"pith_short_12","alias_value":"Z5BOOC46S4XZ","created_at":"2026-07-05T09:10:07Z"},{"alias_kind":"pith_short_16","alias_value":"Z5BOOC46S4XZK7N7","created_at":"2026-07-05T09:10:07Z"},{"alias_kind":"pith_short_8","alias_value":"Z5BOOC46","created_at":"2026-07-05T09:10:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Z5BOOC46S4XZK7N74NFE6QOQ7S","target":"record","payload":{"canonical_record":{"source":{"id":"2409.13860","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-20T19:17:52Z","cross_cats_sorted":[],"title_canon_sha256":"f6d23861080a59b69932ef9317099e4c12c9afd817c97d0dcc7558a875e8df22","abstract_canon_sha256":"0b21df90a96161dd1a917382884be5d5b288cf539dd3f37575761a2a849847c8"},"schema_version":"1.0"},"canonical_sha256":"cf42e70b9e972f957dbfe34a4f41d0fcb8770bacae94273a48d966b3f89c94d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:07.802077Z","signature_b64":"mOBaFs2ZjjtoXMQxhVKSBF10Gf8FUElqk3xSyuOKyTidrZwz67s8KvHlGjJp61Xx2VE5I1TNhrNouF0MHiHCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf42e70b9e972f957dbfe34a4f41d0fcb8770bacae94273a48d966b3f89c94d0","last_reissued_at":"2026-07-05T09:10:07.801626Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:07.801626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.13860","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":"2026-07-05T09:10:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cD8SBAocQV39PJoq+o/DBDOlIu2iHc9fiN3ukAtLicM5E9WL/9ci+3YDwVKpkuutWpr+dGld1HOydHq06dm4Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:52:54.521852Z"},"content_sha256":"f5d6525fe18af81eb75383cf3081e0941c36ecfeebedb0e01665fadf8bc011e2","schema_version":"1.0","event_id":"sha256:f5d6525fe18af81eb75383cf3081e0941c36ecfeebedb0e01665fadf8bc011e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Z5BOOC46S4XZK7N74NFE6QOQ7S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SSE: Multimodal Semantic Data Selection and Enrichment for Industrial-scale Data Assimilation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jose M. Alvarez, Maying Shen, Nadine Chang, Sifei Liu","submitted_at":"2024-09-20T19:17:52Z","abstract_excerpt":"In recent years, the data collected for artificial intelligence has grown to an unmanageable amount. Particularly within industrial applications, such as autonomous vehicles, model training computation budgets are being exceeded while model performance is saturating -- and yet more data continues to pour in. To navigate the flood of data, we propose a framework to select the most semantically diverse and important dataset portion. Then, we further semantically enrich it by discovering meaningful new data from a massive unlabeled data pool. Importantly, we can provide explainability by leveragi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13860","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/2409.13860/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":"2026-07-05T09:10:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cdDusqX9HgsYsBl37ma/wgEurDkkCSrByRP8wmFw7n5rkQCEt9MjWblq+CssRVyR13J7PnNhp0q5Vg2K22wODQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:52:54.522431Z"},"content_sha256":"d0b3b60d6588ad8106d28be8bea2758261fbc8d698828c0e6d45c04f02dced0e","schema_version":"1.0","event_id":"sha256:d0b3b60d6588ad8106d28be8bea2758261fbc8d698828c0e6d45c04f02dced0e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z5BOOC46S4XZK7N74NFE6QOQ7S/bundle.json","state_url":"https://pith.science/pith/Z5BOOC46S4XZK7N74NFE6QOQ7S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z5BOOC46S4XZK7N74NFE6QOQ7S/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":"2026-08-09T15:52:54Z","links":{"resolver":"https://pith.science/pith/Z5BOOC46S4XZK7N74NFE6QOQ7S","bundle":"https://pith.science/pith/Z5BOOC46S4XZK7N74NFE6QOQ7S/bundle.json","state":"https://pith.science/pith/Z5BOOC46S4XZK7N74NFE6QOQ7S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z5BOOC46S4XZK7N74NFE6QOQ7S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Z5BOOC46S4XZK7N74NFE6QOQ7S","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":"0b21df90a96161dd1a917382884be5d5b288cf539dd3f37575761a2a849847c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-20T19:17:52Z","title_canon_sha256":"f6d23861080a59b69932ef9317099e4c12c9afd817c97d0dcc7558a875e8df22"},"schema_version":"1.0","source":{"id":"2409.13860","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.13860","created_at":"2026-07-05T09:10:07Z"},{"alias_kind":"arxiv_version","alias_value":"2409.13860v1","created_at":"2026-07-05T09:10:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13860","created_at":"2026-07-05T09:10:07Z"},{"alias_kind":"pith_short_12","alias_value":"Z5BOOC46S4XZ","created_at":"2026-07-05T09:10:07Z"},{"alias_kind":"pith_short_16","alias_value":"Z5BOOC46S4XZK7N7","created_at":"2026-07-05T09:10:07Z"},{"alias_kind":"pith_short_8","alias_value":"Z5BOOC46","created_at":"2026-07-05T09:10:07Z"}],"graph_snapshots":[{"event_id":"sha256:d0b3b60d6588ad8106d28be8bea2758261fbc8d698828c0e6d45c04f02dced0e","target":"graph","created_at":"2026-07-05T09:10:07Z","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/2409.13860/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, the data collected for artificial intelligence has grown to an unmanageable amount. Particularly within industrial applications, such as autonomous vehicles, model training computation budgets are being exceeded while model performance is saturating -- and yet more data continues to pour in. To navigate the flood of data, we propose a framework to select the most semantically diverse and important dataset portion. Then, we further semantically enrich it by discovering meaningful new data from a massive unlabeled data pool. Importantly, we can provide explainability by leveragi","authors_text":"Jose M. Alvarez, Maying Shen, Nadine Chang, Sifei Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-20T19:17:52Z","title":"SSE: Multimodal Semantic Data Selection and Enrichment for Industrial-scale Data Assimilation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13860","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:f5d6525fe18af81eb75383cf3081e0941c36ecfeebedb0e01665fadf8bc011e2","target":"record","created_at":"2026-07-05T09:10:07Z","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":"0b21df90a96161dd1a917382884be5d5b288cf539dd3f37575761a2a849847c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-20T19:17:52Z","title_canon_sha256":"f6d23861080a59b69932ef9317099e4c12c9afd817c97d0dcc7558a875e8df22"},"schema_version":"1.0","source":{"id":"2409.13860","kind":"arxiv","version":1}},"canonical_sha256":"cf42e70b9e972f957dbfe34a4f41d0fcb8770bacae94273a48d966b3f89c94d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf42e70b9e972f957dbfe34a4f41d0fcb8770bacae94273a48d966b3f89c94d0","first_computed_at":"2026-07-05T09:10:07.801626Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:07.801626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mOBaFs2ZjjtoXMQxhVKSBF10Gf8FUElqk3xSyuOKyTidrZwz67s8KvHlGjJp61Xx2VE5I1TNhrNouF0MHiHCBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:07.802077Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.13860","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5d6525fe18af81eb75383cf3081e0941c36ecfeebedb0e01665fadf8bc011e2","sha256:d0b3b60d6588ad8106d28be8bea2758261fbc8d698828c0e6d45c04f02dced0e"],"state_sha256":"a6918b796bd740bf224bebba499a7fe6b6d8466626de8462b5aa7804a2df0dfd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/79Ao5q9/nb1/J/gv5FTL2N4+u69E9MKbOI4JWRjOGZaxzq1MY8Iu4+sRrHpJFbwudxbKXpF0c5slbORJZ+gAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T15:52:54.526793Z","bundle_sha256":"f829e8878298f6278488e5e1da5f65aa25af139231400e70de0e183824ac0371"}}