{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LDXD74FPAZS2G2O63VXCX5A4IR","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":"7609e50f50645f21b2cf7449fc85bdd5b8861a690d3ee6f9533bb756163a7929","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-10T23:31:38Z","title_canon_sha256":"6d3af2e268e7ef562fbbb357660fd396cc75ffdf35d407661ac2d3843e5c5479"},"schema_version":"1.0","source":{"id":"2009.05175","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.05175","created_at":"2026-07-05T05:11:33Z"},{"alias_kind":"arxiv_version","alias_value":"2009.05175v3","created_at":"2026-07-05T05:11:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.05175","created_at":"2026-07-05T05:11:33Z"},{"alias_kind":"pith_short_12","alias_value":"LDXD74FPAZS2","created_at":"2026-07-05T05:11:33Z"},{"alias_kind":"pith_short_16","alias_value":"LDXD74FPAZS2G2O6","created_at":"2026-07-05T05:11:33Z"},{"alias_kind":"pith_short_8","alias_value":"LDXD74FP","created_at":"2026-07-05T05:11:33Z"}],"graph_snapshots":[{"event_id":"sha256:51c8281c2a27c26644906af504be11bb9ae0b63acfb4c8c502b867e290033b66","target":"graph","created_at":"2026-07-05T05:11:33Z","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/2009.05175/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training large-scale image captioning (IC) models demands access to a rich and diverse set of training examples, gathered from the wild, often from noisy alt-text data. However, recent modeling approaches to IC often fall short in terms of performance in this case, because they assume a clean annotated dataset (as opposed to the noisier alt-text--based annotations), and employ an end-to-end generation approach, which often lacks both controllability and interpretability. We address these problems by breaking down the task into two simpler, more controllable tasks -- skeleton prediction and ske","authors_text":"Ashish Thapliyal, Khyathi Raghavi Chandu, Piyush Sharma, Radu Soricut, Soravit Changpinyo","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-10T23:31:38Z","title":"Denoising Large-Scale Image Captioning from Alt-text Data using Content Selection Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.05175","kind":"arxiv","version":3},"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":"sha256:05f37e9eb22f8cdca82acada3d67b69a14e4374f33e2f668391a1a1680cd199b","target":"record","created_at":"2026-07-05T05:11:33Z","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":"7609e50f50645f21b2cf7449fc85bdd5b8861a690d3ee6f9533bb756163a7929","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-10T23:31:38Z","title_canon_sha256":"6d3af2e268e7ef562fbbb357660fd396cc75ffdf35d407661ac2d3843e5c5479"},"schema_version":"1.0","source":{"id":"2009.05175","kind":"arxiv","version":3}},"canonical_sha256":"58ee3ff0af0665a369dedd6e2bf41c4471370024f938bbe5d07fbb322ad4f90a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58ee3ff0af0665a369dedd6e2bf41c4471370024f938bbe5d07fbb322ad4f90a","first_computed_at":"2026-07-05T05:11:33.652327Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:11:33.652327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ww+5TydSL0xE/1P2NrbCHg4s88D867tyzwnmhgZFUQQgSMlcg7LLf3X1AAVEDygQVhEsYdRfUxOp65+jjyvZAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:11:33.652778Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.05175","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05f37e9eb22f8cdca82acada3d67b69a14e4374f33e2f668391a1a1680cd199b","sha256:51c8281c2a27c26644906af504be11bb9ae0b63acfb4c8c502b867e290033b66"],"state_sha256":"afa0618968c611fe09b7f1eaba850d6e7b1ae21350ee0e70c3230f886bc0e724"}