{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LDXD74FPAZS2G2O63VXCX5A4IR","short_pith_number":"pith:LDXD74FP","schema_version":"1.0","canonical_sha256":"58ee3ff0af0665a369dedd6e2bf41c4471370024f938bbe5d07fbb322ad4f90a","source":{"kind":"arxiv","id":"2009.05175","version":3},"attestation_state":"computed","paper":{"title":"Denoising Large-Scale Image Captioning from Alt-text Data using Content Selection Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Ashish Thapliyal, Khyathi Raghavi Chandu, Piyush Sharma, Radu Soricut, Soravit Changpinyo","submitted_at":"2020-09-10T23:31:38Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2009.05175","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-10T23:31:38Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"6d3af2e268e7ef562fbbb357660fd396cc75ffdf35d407661ac2d3843e5c5479","abstract_canon_sha256":"7609e50f50645f21b2cf7449fc85bdd5b8861a690d3ee6f9533bb756163a7929"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:33.652778Z","signature_b64":"Ww+5TydSL0xE/1P2NrbCHg4s88D867tyzwnmhgZFUQQgSMlcg7LLf3X1AAVEDygQVhEsYdRfUxOp65+jjyvZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58ee3ff0af0665a369dedd6e2bf41c4471370024f938bbe5d07fbb322ad4f90a","last_reissued_at":"2026-07-05T05:11:33.652327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:33.652327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Denoising Large-Scale Image Captioning from Alt-text Data using Content Selection Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Ashish Thapliyal, Khyathi Raghavi Chandu, Piyush Sharma, Radu Soricut, Soravit Changpinyo","submitted_at":"2020-09-10T23:31:38Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.05175","kind":"arxiv","version":3},"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/2009.05175/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2009.05175","created_at":"2026-07-05T05:11:33.652386+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.05175v3","created_at":"2026-07-05T05:11:33.652386+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.05175","created_at":"2026-07-05T05:11:33.652386+00:00"},{"alias_kind":"pith_short_12","alias_value":"LDXD74FPAZS2","created_at":"2026-07-05T05:11:33.652386+00:00"},{"alias_kind":"pith_short_16","alias_value":"LDXD74FPAZS2G2O6","created_at":"2026-07-05T05:11:33.652386+00:00"},{"alias_kind":"pith_short_8","alias_value":"LDXD74FP","created_at":"2026-07-05T05:11:33.652386+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LDXD74FPAZS2G2O63VXCX5A4IR","json":"https://pith.science/pith/LDXD74FPAZS2G2O63VXCX5A4IR.json","graph_json":"https://pith.science/api/pith-number/LDXD74FPAZS2G2O63VXCX5A4IR/graph.json","events_json":"https://pith.science/api/pith-number/LDXD74FPAZS2G2O63VXCX5A4IR/events.json","paper":"https://pith.science/paper/LDXD74FP"},"agent_actions":{"view_html":"https://pith.science/pith/LDXD74FPAZS2G2O63VXCX5A4IR","download_json":"https://pith.science/pith/LDXD74FPAZS2G2O63VXCX5A4IR.json","view_paper":"https://pith.science/paper/LDXD74FP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.05175&json=true","fetch_graph":"https://pith.science/api/pith-number/LDXD74FPAZS2G2O63VXCX5A4IR/graph.json","fetch_events":"https://pith.science/api/pith-number/LDXD74FPAZS2G2O63VXCX5A4IR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LDXD74FPAZS2G2O63VXCX5A4IR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LDXD74FPAZS2G2O63VXCX5A4IR/action/storage_attestation","attest_author":"https://pith.science/pith/LDXD74FPAZS2G2O63VXCX5A4IR/action/author_attestation","sign_citation":"https://pith.science/pith/LDXD74FPAZS2G2O63VXCX5A4IR/action/citation_signature","submit_replication":"https://pith.science/pith/LDXD74FPAZS2G2O63VXCX5A4IR/action/replication_record"}},"created_at":"2026-07-05T05:11:33.652386+00:00","updated_at":"2026-07-05T05:11:33.652386+00:00"}