{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:S5M6XT4UCFMUXHRCZHJVSSZ3WI","short_pith_number":"pith:S5M6XT4U","schema_version":"1.0","canonical_sha256":"9759ebcf9411594b9e22c9d3594b3bb23219f5eba5896fea168b9ec5a03244b6","source":{"kind":"arxiv","id":"1908.11310","version":1},"attestation_state":"computed","paper":{"title":"Aesthetic Image Captioning From Weakly-Labelled Photographs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Aakanksha Rana, Aljosa Smolic, Koustav Ghosal","submitted_at":"2019-08-29T15:50:28Z","abstract_excerpt":"Aesthetic image captioning (AIC) refers to the multi-modal task of generating critical textual feedbacks for photographs. While in natural image captioning (NIC), deep models are trained in an end-to-end manner using large curated datasets such as MS-COCO, no such large-scale, clean dataset exists for AIC. Towards this goal, we propose an automatic cleaning strategy to create a benchmarking AIC dataset, by exploiting the images and noisy comments easily available from photography websites. We propose a probabilistic caption-filtering method for cleaning the noisy web-data, and compile a large-"},"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":"1908.11310","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-29T15:50:28Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"78809fecbe9436d3d0c6f8cc622c593a6c818531833750d729aa4657418aafbe","abstract_canon_sha256":"b6ac4fa3d9ee6122d45f332960d5f40f5b424e906fb16ddd133acfc6a9eb3cf5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:00:32.475231Z","signature_b64":"w8TANh/p1SNeqwlK7oUQ0wWVVEnQbf+khUB2UW/gavv98s6w4s/xZp4Uf0y9vitEbQJTiielnRp9EAnViTTDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9759ebcf9411594b9e22c9d3594b3bb23219f5eba5896fea168b9ec5a03244b6","last_reissued_at":"2026-07-05T00:00:32.474788Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:00:32.474788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aesthetic Image Captioning From Weakly-Labelled Photographs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Aakanksha Rana, Aljosa Smolic, Koustav Ghosal","submitted_at":"2019-08-29T15:50:28Z","abstract_excerpt":"Aesthetic image captioning (AIC) refers to the multi-modal task of generating critical textual feedbacks for photographs. While in natural image captioning (NIC), deep models are trained in an end-to-end manner using large curated datasets such as MS-COCO, no such large-scale, clean dataset exists for AIC. Towards this goal, we propose an automatic cleaning strategy to create a benchmarking AIC dataset, by exploiting the images and noisy comments easily available from photography websites. We propose a probabilistic caption-filtering method for cleaning the noisy web-data, and compile a large-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.11310","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/1908.11310/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":"1908.11310","created_at":"2026-07-05T00:00:32.474843+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.11310v1","created_at":"2026-07-05T00:00:32.474843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.11310","created_at":"2026-07-05T00:00:32.474843+00:00"},{"alias_kind":"pith_short_12","alias_value":"S5M6XT4UCFMU","created_at":"2026-07-05T00:00:32.474843+00:00"},{"alias_kind":"pith_short_16","alias_value":"S5M6XT4UCFMUXHRC","created_at":"2026-07-05T00:00:32.474843+00:00"},{"alias_kind":"pith_short_8","alias_value":"S5M6XT4U","created_at":"2026-07-05T00:00:32.474843+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2312.17090","citing_title":"Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels","ref_index":252,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S5M6XT4UCFMUXHRCZHJVSSZ3WI","json":"https://pith.science/pith/S5M6XT4UCFMUXHRCZHJVSSZ3WI.json","graph_json":"https://pith.science/api/pith-number/S5M6XT4UCFMUXHRCZHJVSSZ3WI/graph.json","events_json":"https://pith.science/api/pith-number/S5M6XT4UCFMUXHRCZHJVSSZ3WI/events.json","paper":"https://pith.science/paper/S5M6XT4U"},"agent_actions":{"view_html":"https://pith.science/pith/S5M6XT4UCFMUXHRCZHJVSSZ3WI","download_json":"https://pith.science/pith/S5M6XT4UCFMUXHRCZHJVSSZ3WI.json","view_paper":"https://pith.science/paper/S5M6XT4U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.11310&json=true","fetch_graph":"https://pith.science/api/pith-number/S5M6XT4UCFMUXHRCZHJVSSZ3WI/graph.json","fetch_events":"https://pith.science/api/pith-number/S5M6XT4UCFMUXHRCZHJVSSZ3WI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S5M6XT4UCFMUXHRCZHJVSSZ3WI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S5M6XT4UCFMUXHRCZHJVSSZ3WI/action/storage_attestation","attest_author":"https://pith.science/pith/S5M6XT4UCFMUXHRCZHJVSSZ3WI/action/author_attestation","sign_citation":"https://pith.science/pith/S5M6XT4UCFMUXHRCZHJVSSZ3WI/action/citation_signature","submit_replication":"https://pith.science/pith/S5M6XT4UCFMUXHRCZHJVSSZ3WI/action/replication_record"}},"created_at":"2026-07-05T00:00:32.474843+00:00","updated_at":"2026-07-05T00:00:32.474843+00:00"}