{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:CMPFM7R3PWWHRD7L3B6JORLZDI","short_pith_number":"pith:CMPFM7R3","canonical_record":{"source":{"id":"1811.10787","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-27T03:16:20Z","cross_cats_sorted":[],"title_canon_sha256":"330b5a86d0a38ef4dd2370d8a74f354eef94c815bb88a5fd3648dc7d68f886a2","abstract_canon_sha256":"3b69b347dbc2501520c138a84764794f0dcf1bd4e5af6afdba52bdc891936f39"},"schema_version":"1.0"},"canonical_sha256":"131e567e3b7dac788febd87c9745791a1767a53eea16740fdc00ab6dc15dac74","source":{"kind":"arxiv","id":"1811.10787","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.10787","created_at":"2026-05-17T23:49:17Z"},{"alias_kind":"arxiv_version","alias_value":"1811.10787v2","created_at":"2026-05-17T23:49:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10787","created_at":"2026-05-17T23:49:17Z"},{"alias_kind":"pith_short_12","alias_value":"CMPFM7R3PWWH","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"CMPFM7R3PWWHRD7L","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"CMPFM7R3","created_at":"2026-05-18T12:32:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:CMPFM7R3PWWHRD7L3B6JORLZDI","target":"record","payload":{"canonical_record":{"source":{"id":"1811.10787","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-27T03:16:20Z","cross_cats_sorted":[],"title_canon_sha256":"330b5a86d0a38ef4dd2370d8a74f354eef94c815bb88a5fd3648dc7d68f886a2","abstract_canon_sha256":"3b69b347dbc2501520c138a84764794f0dcf1bd4e5af6afdba52bdc891936f39"},"schema_version":"1.0"},"canonical_sha256":"131e567e3b7dac788febd87c9745791a1767a53eea16740fdc00ab6dc15dac74","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:17.058939Z","signature_b64":"MfgUIjQgwPZaOH/iS9jNkBZdmtaaPx8b59SwUBHFJUISwmgycLIbO2IZ7cVLlNdPu7fTEEBWlXdVF8V2w5CxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"131e567e3b7dac788febd87c9745791a1767a53eea16740fdc00ab6dc15dac74","last_reissued_at":"2026-05-17T23:49:17.058283Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:17.058283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.10787","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":"2026-05-17T23:49:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Soef6eNOFaKZ4UHbzFEFfNHwh9531M1gcGb8qHNdFFkpx8+ThtDyHUlmSQrk1Xg59rjd+3xElQJZ4m+/Z70CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T17:43:08.222861Z"},"content_sha256":"30d00776f1469ad4da511c5682dd5a0a999b0b7d3b74b379dc03e5ff3a3b22e2","schema_version":"1.0","event_id":"sha256:30d00776f1469ad4da511c5682dd5a0a999b0b7d3b74b379dc03e5ff3a3b22e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:CMPFM7R3PWWHRD7L3B6JORLZDI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiebo Luo, Lin Ma, Wei Liu, Yang Feng","submitted_at":"2018-11-27T03:16:20Z","abstract_excerpt":"Deep neural networks have achieved great successes on the image captioning task. However, most of the existing models depend heavily on paired image-sentence datasets, which are very expensive to acquire. In this paper, we make the first attempt to train an image captioning model in an unsupervised manner. Instead of relying on manually labeled image-sentence pairs, our proposed model merely requires an image set, a sentence corpus, and an existing visual concept detector. The sentence corpus is used to teach the captioning model how to generate plausible sentences. Meanwhile, the knowledge in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10787","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":"2026-05-17T23:49:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VOj2KZQsEyc2KNOht258ZB6zU2XhZEcWa4CXAp9lxs4Y8uYjVoObP+d1YcozhUadJkCJ9RKkUAOmKszDAZ3aAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T17:43:08.223344Z"},"content_sha256":"710e59bcedbbbd656350e091a78722a1293eda801f60f32d971d52cf77a01338","schema_version":"1.0","event_id":"sha256:710e59bcedbbbd656350e091a78722a1293eda801f60f32d971d52cf77a01338"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CMPFM7R3PWWHRD7L3B6JORLZDI/bundle.json","state_url":"https://pith.science/pith/CMPFM7R3PWWHRD7L3B6JORLZDI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CMPFM7R3PWWHRD7L3B6JORLZDI/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":"2026-08-16T17:43:08Z","links":{"resolver":"https://pith.science/pith/CMPFM7R3PWWHRD7L3B6JORLZDI","bundle":"https://pith.science/pith/CMPFM7R3PWWHRD7L3B6JORLZDI/bundle.json","state":"https://pith.science/pith/CMPFM7R3PWWHRD7L3B6JORLZDI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CMPFM7R3PWWHRD7L3B6JORLZDI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:CMPFM7R3PWWHRD7L3B6JORLZDI","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":"3b69b347dbc2501520c138a84764794f0dcf1bd4e5af6afdba52bdc891936f39","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-27T03:16:20Z","title_canon_sha256":"330b5a86d0a38ef4dd2370d8a74f354eef94c815bb88a5fd3648dc7d68f886a2"},"schema_version":"1.0","source":{"id":"1811.10787","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.10787","created_at":"2026-05-17T23:49:17Z"},{"alias_kind":"arxiv_version","alias_value":"1811.10787v2","created_at":"2026-05-17T23:49:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10787","created_at":"2026-05-17T23:49:17Z"},{"alias_kind":"pith_short_12","alias_value":"CMPFM7R3PWWH","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"CMPFM7R3PWWHRD7L","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"CMPFM7R3","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:710e59bcedbbbd656350e091a78722a1293eda801f60f32d971d52cf77a01338","target":"graph","created_at":"2026-05-17T23:49:17Z","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":"Deep neural networks have achieved great successes on the image captioning task. However, most of the existing models depend heavily on paired image-sentence datasets, which are very expensive to acquire. In this paper, we make the first attempt to train an image captioning model in an unsupervised manner. Instead of relying on manually labeled image-sentence pairs, our proposed model merely requires an image set, a sentence corpus, and an existing visual concept detector. The sentence corpus is used to teach the captioning model how to generate plausible sentences. Meanwhile, the knowledge in","authors_text":"Jiebo Luo, Lin Ma, Wei Liu, Yang Feng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-27T03:16:20Z","title":"Unsupervised Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10787","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":"sha256:30d00776f1469ad4da511c5682dd5a0a999b0b7d3b74b379dc03e5ff3a3b22e2","target":"record","created_at":"2026-05-17T23:49:17Z","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":"3b69b347dbc2501520c138a84764794f0dcf1bd4e5af6afdba52bdc891936f39","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-27T03:16:20Z","title_canon_sha256":"330b5a86d0a38ef4dd2370d8a74f354eef94c815bb88a5fd3648dc7d68f886a2"},"schema_version":"1.0","source":{"id":"1811.10787","kind":"arxiv","version":2}},"canonical_sha256":"131e567e3b7dac788febd87c9745791a1767a53eea16740fdc00ab6dc15dac74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"131e567e3b7dac788febd87c9745791a1767a53eea16740fdc00ab6dc15dac74","first_computed_at":"2026-05-17T23:49:17.058283Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:17.058283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MfgUIjQgwPZaOH/iS9jNkBZdmtaaPx8b59SwUBHFJUISwmgycLIbO2IZ7cVLlNdPu7fTEEBWlXdVF8V2w5CxDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:17.058939Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.10787","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30d00776f1469ad4da511c5682dd5a0a999b0b7d3b74b379dc03e5ff3a3b22e2","sha256:710e59bcedbbbd656350e091a78722a1293eda801f60f32d971d52cf77a01338"],"state_sha256":"fe3486cb231999ee3dbe751bb37eac803b8e7e3c5433761fd70d4865f3981608"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DB/vP2GFsuEWoLVDO8Brj+9++fSi4RJYu1hMjH5GkNv+AL1j9qhBN4qLehhE+XjuFsbyF8WLXrvOSTdxng+NCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T17:43:08.227275Z","bundle_sha256":"fc968a296a7a9a2e85499e5f88b1f7e7a792e6cf3930fd85ce58d1f12b46f06f"}}