{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:YU6MZXJSGU4A5YN5S5I33HAXAN","short_pith_number":"pith:YU6MZXJS","canonical_record":{"source":{"id":"1502.03671","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-02-12T14:17:15Z","cross_cats_sorted":[],"title_canon_sha256":"877b07a64c9a7d500958bf3b10a8dbe470a796e4015a372b9220ef303039ea06","abstract_canon_sha256":"af58d12bf4e81d35ab6296d0c4b40655aae1743ce2d683641e6978ed07a6ca47"},"schema_version":"1.0"},"canonical_sha256":"c53cccdd3235380ee1bd9751bd9c17036af1983af06478107a842996a03eecf9","source":{"kind":"arxiv","id":"1502.03671","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.03671","created_at":"2026-05-18T02:19:16Z"},{"alias_kind":"arxiv_version","alias_value":"1502.03671v2","created_at":"2026-05-18T02:19:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.03671","created_at":"2026-05-18T02:19:16Z"},{"alias_kind":"pith_short_12","alias_value":"YU6MZXJSGU4A","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"YU6MZXJSGU4A5YN5","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"YU6MZXJS","created_at":"2026-05-18T12:29:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:YU6MZXJSGU4A5YN5S5I33HAXAN","target":"record","payload":{"canonical_record":{"source":{"id":"1502.03671","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-02-12T14:17:15Z","cross_cats_sorted":[],"title_canon_sha256":"877b07a64c9a7d500958bf3b10a8dbe470a796e4015a372b9220ef303039ea06","abstract_canon_sha256":"af58d12bf4e81d35ab6296d0c4b40655aae1743ce2d683641e6978ed07a6ca47"},"schema_version":"1.0"},"canonical_sha256":"c53cccdd3235380ee1bd9751bd9c17036af1983af06478107a842996a03eecf9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:19:16.201553Z","signature_b64":"5Zfq9446c3adV+ffeZCHTcLy3HQRyw2Jj+T65cT2GsVTq255o99aeQPrxKsVoDh9mvrTrvsCc/IYIhGt+4BeDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c53cccdd3235380ee1bd9751bd9c17036af1983af06478107a842996a03eecf9","last_reissued_at":"2026-05-18T02:19:16.200850Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:19:16.200850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1502.03671","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:19:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mLBWmF5+gsHwNHmOJQyeGNZt6GW00/CleQns7FuTFA0zghFerMdItP3pBNi36MDyBff0fM14X6844C8f9M3lBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T21:49:46.542141Z"},"content_sha256":"fcb3657fbec70bbd2b0afb235fca1df8115a1cb82313b11a5ac6712eb400bd2a","schema_version":"1.0","event_id":"sha256:fcb3657fbec70bbd2b0afb235fca1df8115a1cb82313b11a5ac6712eb400bd2a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:YU6MZXJSGU4A5YN5S5I33HAXAN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Phrase-based Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Pedro O. Pinheiro, R\\'emi Lebret, Ronan Collobert","submitted_at":"2015-02-12T14:17:15Z","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":"1502.03671","kind":"arxiv","version":2},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:19:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nFGxn8bpuNwNHqi25WaQHVOxY8T0m/JibiQKqlT0I30+S/fhzFS8jdLCmZjq/RV4/Xx6qDHmdTE7toqEXpPYBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T21:49:46.542822Z"},"content_sha256":"448656078f25c2bf7e3b0379425027c93fa5ad17fcc208eeab19ad3ebd860a4b","schema_version":"1.0","event_id":"sha256:448656078f25c2bf7e3b0379425027c93fa5ad17fcc208eeab19ad3ebd860a4b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YU6MZXJSGU4A5YN5S5I33HAXAN/bundle.json","state_url":"https://pith.science/pith/YU6MZXJSGU4A5YN5S5I33HAXAN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YU6MZXJSGU4A5YN5S5I33HAXAN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-23T21:49:46Z","links":{"resolver":"https://pith.science/pith/YU6MZXJSGU4A5YN5S5I33HAXAN","bundle":"https://pith.science/pith/YU6MZXJSGU4A5YN5S5I33HAXAN/bundle.json","state":"https://pith.science/pith/YU6MZXJSGU4A5YN5S5I33HAXAN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YU6MZXJSGU4A5YN5S5I33HAXAN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:YU6MZXJSGU4A5YN5S5I33HAXAN","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":"af58d12bf4e81d35ab6296d0c4b40655aae1743ce2d683641e6978ed07a6ca47","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-02-12T14:17:15Z","title_canon_sha256":"877b07a64c9a7d500958bf3b10a8dbe470a796e4015a372b9220ef303039ea06"},"schema_version":"1.0","source":{"id":"1502.03671","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.03671","created_at":"2026-05-18T02:19:16Z"},{"alias_kind":"arxiv_version","alias_value":"1502.03671v2","created_at":"2026-05-18T02:19:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.03671","created_at":"2026-05-18T02:19:16Z"},{"alias_kind":"pith_short_12","alias_value":"YU6MZXJSGU4A","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"YU6MZXJSGU4A5YN5","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"YU6MZXJS","created_at":"2026-05-18T12:29:52Z"}],"graph_snapshots":[{"event_id":"sha256:448656078f25c2bf7e3b0379425027c93fa5ad17fcc208eeab19ad3ebd860a4b","target":"graph","created_at":"2026-05-18T02:19:16Z","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"},"paper":{"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","authors_text":"Pedro O. Pinheiro, R\\'emi Lebret, Ronan Collobert","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-02-12T14:17:15Z","title":"Phrase-based Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.03671","kind":"arxiv","version":2},"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:fcb3657fbec70bbd2b0afb235fca1df8115a1cb82313b11a5ac6712eb400bd2a","target":"record","created_at":"2026-05-18T02:19:16Z","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":"af58d12bf4e81d35ab6296d0c4b40655aae1743ce2d683641e6978ed07a6ca47","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-02-12T14:17:15Z","title_canon_sha256":"877b07a64c9a7d500958bf3b10a8dbe470a796e4015a372b9220ef303039ea06"},"schema_version":"1.0","source":{"id":"1502.03671","kind":"arxiv","version":2}},"canonical_sha256":"c53cccdd3235380ee1bd9751bd9c17036af1983af06478107a842996a03eecf9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c53cccdd3235380ee1bd9751bd9c17036af1983af06478107a842996a03eecf9","first_computed_at":"2026-05-18T02:19:16.200850Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:19:16.200850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5Zfq9446c3adV+ffeZCHTcLy3HQRyw2Jj+T65cT2GsVTq255o99aeQPrxKsVoDh9mvrTrvsCc/IYIhGt+4BeDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:19:16.201553Z","signed_message":"canonical_sha256_bytes"},"source_id":"1502.03671","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fcb3657fbec70bbd2b0afb235fca1df8115a1cb82313b11a5ac6712eb400bd2a","sha256:448656078f25c2bf7e3b0379425027c93fa5ad17fcc208eeab19ad3ebd860a4b"],"state_sha256":"0256ac5e735edc3c72bb854667de53be9745d437a19b3f8b85d09d42f1728217"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g4HlowEm8DWZlZhnx5J+AQbusw6sGh2/n/Q+Udz1HuWoJHEM6t/Zp38smCOHuc6TJpS/r+wAcp7em/zJBaJuBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T21:49:46.546277Z","bundle_sha256":"1f81df0477311f212cf163cb163cdbff4ca562d6a6c6405ecf845da572bfdcdc"}}