{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:IRV7HL5HW24NT2GMIYN2JOQ4XV","short_pith_number":"pith:IRV7HL5H","schema_version":"1.0","canonical_sha256":"446bf3afa7b6b8d9e8cc461ba4ba1cbd4b7e80d9e4a152ff8224e0891865f966","source":{"kind":"arxiv","id":"1412.8419","version":3},"attestation_state":"computed","paper":{"title":"Simple Image Description Generator via a Linear Phrase-Based Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.CL","authors_text":"Pedro O. Pinheiro, Remi Lebret, Ronan Collobert","submitted_at":"2014-12-29T18:43:10Z","abstract_excerpt":"Generating a novel textual description of an image is an interesting problem that connects computer vision and natural language processing. In this paper, we present a simple model that is able to generate descriptive sentences given a sample image. This model has a strong focus on the syntax of the descriptions. We train a purely bilinear model that learns a metric between an image representation (generated from a previously trained Convolutional Neural Network) and phrases that are used to described them. The system is then able to infer phrases from a given image sample. Based on caption sy"},"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":"1412.8419","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-12-29T18:43:10Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"acd6be948d35b5b9880a155592718d0340a67bce336bea0768884bcb709f5321","abstract_canon_sha256":"62ec85900378f984bd4dc58db3b3f9810afa3a6b81d7d2d16890437b768ff7c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:19:00.574213Z","signature_b64":"2BLqHJw0IMSc9/2QOaH4sPlfrPH4j1eQzOWlJ6uttRHIZ9q4tjRDOI7QaXynOABfELAlruhYpsgkd8SO4pnqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"446bf3afa7b6b8d9e8cc461ba4ba1cbd4b7e80d9e4a152ff8224e0891865f966","last_reissued_at":"2026-05-18T02:19:00.573578Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:19:00.573578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simple Image Description Generator via a Linear Phrase-Based Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.CL","authors_text":"Pedro O. Pinheiro, Remi Lebret, Ronan Collobert","submitted_at":"2014-12-29T18:43:10Z","abstract_excerpt":"Generating a novel textual description of an image is an interesting problem that connects computer vision and natural language processing. In this paper, we present a simple model that is able to generate descriptive sentences given a sample image. This model has a strong focus on the syntax of the descriptions. We train a purely bilinear model that learns a metric between an image representation (generated from a previously trained Convolutional Neural Network) and phrases that are used to described them. The system is then able to infer phrases from a given image sample. Based on caption sy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.8419","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":""},"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":"1412.8419","created_at":"2026-05-18T02:19:00.573677+00:00"},{"alias_kind":"arxiv_version","alias_value":"1412.8419v3","created_at":"2026-05-18T02:19:00.573677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.8419","created_at":"2026-05-18T02:19:00.573677+00:00"},{"alias_kind":"pith_short_12","alias_value":"IRV7HL5HW24N","created_at":"2026-05-18T12:28:33.132498+00:00"},{"alias_kind":"pith_short_16","alias_value":"IRV7HL5HW24NT2GM","created_at":"2026-05-18T12:28:33.132498+00:00"},{"alias_kind":"pith_short_8","alias_value":"IRV7HL5H","created_at":"2026-05-18T12:28:33.132498+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1504.00325","citing_title":"Microsoft COCO Captions: Data Collection and Evaluation Server","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IRV7HL5HW24NT2GMIYN2JOQ4XV","json":"https://pith.science/pith/IRV7HL5HW24NT2GMIYN2JOQ4XV.json","graph_json":"https://pith.science/api/pith-number/IRV7HL5HW24NT2GMIYN2JOQ4XV/graph.json","events_json":"https://pith.science/api/pith-number/IRV7HL5HW24NT2GMIYN2JOQ4XV/events.json","paper":"https://pith.science/paper/IRV7HL5H"},"agent_actions":{"view_html":"https://pith.science/pith/IRV7HL5HW24NT2GMIYN2JOQ4XV","download_json":"https://pith.science/pith/IRV7HL5HW24NT2GMIYN2JOQ4XV.json","view_paper":"https://pith.science/paper/IRV7HL5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1412.8419&json=true","fetch_graph":"https://pith.science/api/pith-number/IRV7HL5HW24NT2GMIYN2JOQ4XV/graph.json","fetch_events":"https://pith.science/api/pith-number/IRV7HL5HW24NT2GMIYN2JOQ4XV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IRV7HL5HW24NT2GMIYN2JOQ4XV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IRV7HL5HW24NT2GMIYN2JOQ4XV/action/storage_attestation","attest_author":"https://pith.science/pith/IRV7HL5HW24NT2GMIYN2JOQ4XV/action/author_attestation","sign_citation":"https://pith.science/pith/IRV7HL5HW24NT2GMIYN2JOQ4XV/action/citation_signature","submit_replication":"https://pith.science/pith/IRV7HL5HW24NT2GMIYN2JOQ4XV/action/replication_record"}},"created_at":"2026-05-18T02:19:00.573677+00:00","updated_at":"2026-05-18T02:19:00.573677+00:00"}