{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JILLZFRKN4O7JCYG4LDWEE2V5R","short_pith_number":"pith:JILLZFRK","schema_version":"1.0","canonical_sha256":"4a16bc962a6f1df48b06e2c7621355ec60985cab3792f22282af2ce4b3bc1008","source":{"kind":"arxiv","id":"2408.15714","version":1},"attestation_state":"computed","paper":{"title":"Pixels to Prose: Understanding the art of Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aarti Sharma, Hrishikesh Singh, Millie Pant","submitted_at":"2024-08-28T11:21:23Z","abstract_excerpt":"In the era of evolving artificial intelligence, machines are increasingly emulating human-like capabilities, including visual perception and linguistic expression. Image captioning stands at the intersection of these domains, enabling machines to interpret visual content and generate descriptive text. This paper provides a thorough review of image captioning techniques, catering to individuals entering the field of machine learning who seek a comprehensive understanding of available options, from foundational methods to state-of-the-art approaches. Beginning with an exploration of primitive ar"},"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":"2408.15714","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T11:21:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3e6c4e6aa0aed091bcf7aed9eb0ee4469639d437509b181430b14559f6409fd1","abstract_canon_sha256":"e5b411d28bf502c10f1cb6adf89b18d7a89290b5a1c96701e3427ed7c18165a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:16.189660Z","signature_b64":"vbUMx56FVELYcQ3La8p1a7umKkepA6x3BZOCqOp0ljbBFQvzMGkcez8RSx5zstjerNpWCmQlMVwZ1msa1oPsCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a16bc962a6f1df48b06e2c7621355ec60985cab3792f22282af2ce4b3bc1008","last_reissued_at":"2026-07-05T09:00:16.189171Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:16.189171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pixels to Prose: Understanding the art of Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aarti Sharma, Hrishikesh Singh, Millie Pant","submitted_at":"2024-08-28T11:21:23Z","abstract_excerpt":"In the era of evolving artificial intelligence, machines are increasingly emulating human-like capabilities, including visual perception and linguistic expression. Image captioning stands at the intersection of these domains, enabling machines to interpret visual content and generate descriptive text. This paper provides a thorough review of image captioning techniques, catering to individuals entering the field of machine learning who seek a comprehensive understanding of available options, from foundational methods to state-of-the-art approaches. Beginning with an exploration of primitive ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15714","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/2408.15714/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":"2408.15714","created_at":"2026-07-05T09:00:16.189231+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.15714v1","created_at":"2026-07-05T09:00:16.189231+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15714","created_at":"2026-07-05T09:00:16.189231+00:00"},{"alias_kind":"pith_short_12","alias_value":"JILLZFRKN4O7","created_at":"2026-07-05T09:00:16.189231+00:00"},{"alias_kind":"pith_short_16","alias_value":"JILLZFRKN4O7JCYG","created_at":"2026-07-05T09:00:16.189231+00:00"},{"alias_kind":"pith_short_8","alias_value":"JILLZFRK","created_at":"2026-07-05T09:00:16.189231+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17950","citing_title":"Plug-and-Adapt: Multimodal Coreference Resolution at First Sight with a Pretrained Alignment Model","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09846","citing_title":"CANVAS: Captioning Art with Narrative Visual-Audio AI Systems","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JILLZFRKN4O7JCYG4LDWEE2V5R","json":"https://pith.science/pith/JILLZFRKN4O7JCYG4LDWEE2V5R.json","graph_json":"https://pith.science/api/pith-number/JILLZFRKN4O7JCYG4LDWEE2V5R/graph.json","events_json":"https://pith.science/api/pith-number/JILLZFRKN4O7JCYG4LDWEE2V5R/events.json","paper":"https://pith.science/paper/JILLZFRK"},"agent_actions":{"view_html":"https://pith.science/pith/JILLZFRKN4O7JCYG4LDWEE2V5R","download_json":"https://pith.science/pith/JILLZFRKN4O7JCYG4LDWEE2V5R.json","view_paper":"https://pith.science/paper/JILLZFRK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.15714&json=true","fetch_graph":"https://pith.science/api/pith-number/JILLZFRKN4O7JCYG4LDWEE2V5R/graph.json","fetch_events":"https://pith.science/api/pith-number/JILLZFRKN4O7JCYG4LDWEE2V5R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JILLZFRKN4O7JCYG4LDWEE2V5R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JILLZFRKN4O7JCYG4LDWEE2V5R/action/storage_attestation","attest_author":"https://pith.science/pith/JILLZFRKN4O7JCYG4LDWEE2V5R/action/author_attestation","sign_citation":"https://pith.science/pith/JILLZFRKN4O7JCYG4LDWEE2V5R/action/citation_signature","submit_replication":"https://pith.science/pith/JILLZFRKN4O7JCYG4LDWEE2V5R/action/replication_record"}},"created_at":"2026-07-05T09:00:16.189231+00:00","updated_at":"2026-07-05T09:00:16.189231+00:00"}