{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:F3XTOI4B72WYFYIZHWWQSYATFG","short_pith_number":"pith:F3XTOI4B","canonical_record":{"source":{"id":"1908.08529","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-22T17:59:08Z","cross_cats_sorted":["cs.CL","cs.LG","stat.ML"],"title_canon_sha256":"9c64ae905993356d66b4d4d91d8ee199c837a9da193d0c9c21aba141b90655c7","abstract_canon_sha256":"06120c8cab78ca78b341c4dae04a26286b552398b4ee05871517b9a41e95d057"},"schema_version":"1.0"},"canonical_sha256":"2eef372381fead82e1193dad096013299f9753f89c27094501d8ea15e0738b41","source":{"kind":"arxiv","id":"1908.08529","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.08529","created_at":"2026-07-04T23:59:13Z"},{"alias_kind":"arxiv_version","alias_value":"1908.08529v1","created_at":"2026-07-04T23:59:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08529","created_at":"2026-07-04T23:59:13Z"},{"alias_kind":"pith_short_12","alias_value":"F3XTOI4B72WY","created_at":"2026-07-04T23:59:13Z"},{"alias_kind":"pith_short_16","alias_value":"F3XTOI4B72WYFYIZ","created_at":"2026-07-04T23:59:13Z"},{"alias_kind":"pith_short_8","alias_value":"F3XTOI4B","created_at":"2026-07-04T23:59:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:F3XTOI4B72WYFYIZHWWQSYATFG","target":"record","payload":{"canonical_record":{"source":{"id":"1908.08529","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-22T17:59:08Z","cross_cats_sorted":["cs.CL","cs.LG","stat.ML"],"title_canon_sha256":"9c64ae905993356d66b4d4d91d8ee199c837a9da193d0c9c21aba141b90655c7","abstract_canon_sha256":"06120c8cab78ca78b341c4dae04a26286b552398b4ee05871517b9a41e95d057"},"schema_version":"1.0"},"canonical_sha256":"2eef372381fead82e1193dad096013299f9753f89c27094501d8ea15e0738b41","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:13.818005Z","signature_b64":"ojhGCmXPdYRn0JrFTdggsMXZa+LxkLeeaw24swrWRkYvVf8qLR/ldqwU6qko6xj2cuPHQcjO3KC1bMV438llBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2eef372381fead82e1193dad096013299f9753f89c27094501d8ea15e0738b41","last_reissued_at":"2026-07-04T23:59:13.817668Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:13.817668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.08529","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:59:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SP9r1EorRoKGzViMr4vXa7SCijNUPp2h2O2B72ZU8Q1QLgQXATqgdtwwPALH1KHfBafUrt+HVeiVOMUAsRS1BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:37:34.733234Z"},"content_sha256":"eb072af784baccf281ace621df940d328ec11bbd85b0de754278bfd7c7c5656f","schema_version":"1.0","event_id":"sha256:eb072af784baccf281ace621df940d328ec11bbd85b0de754278bfd7c7c5656f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:F3XTOI4B72WYFYIZHWWQSYATFG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sequential Latent Spaces for Modeling the Intention During Diverse Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Alexander Schwing, Dhruv Batra, Harsh Agrawal, Jyoti Aneja","submitted_at":"2019-08-22T17:59:08Z","abstract_excerpt":"Diverse and accurate vision+language modeling is an important goal to retain creative freedom and maintain user engagement. However, adequately capturing the intricacies of diversity in language models is challenging. Recent works commonly resort to latent variable models augmented with more or less supervision from object detectors or part-of-speech tags. Common to all those methods is the fact that the latent variable either only initializes the sentence generation process or is identical across the steps of generation. Both methods offer no fine-grained control. To address this concern, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08529","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/1908.08529/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:59:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tA2VrA8Q7NMJzhzbW3fmhJbTe+6WeMsNAuubVyOOV0PLuSz63BhY6ePOjodKKi+ib1CGoSgs7+1QpgidMPs/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:37:34.733763Z"},"content_sha256":"2594248afbbbe329c244ac53a704c7d112298f27016a37fff1c8969d5c7c5365","schema_version":"1.0","event_id":"sha256:2594248afbbbe329c244ac53a704c7d112298f27016a37fff1c8969d5c7c5365"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F3XTOI4B72WYFYIZHWWQSYATFG/bundle.json","state_url":"https://pith.science/pith/F3XTOI4B72WYFYIZHWWQSYATFG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F3XTOI4B72WYFYIZHWWQSYATFG/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":"2026-08-10T07:37:34Z","links":{"resolver":"https://pith.science/pith/F3XTOI4B72WYFYIZHWWQSYATFG","bundle":"https://pith.science/pith/F3XTOI4B72WYFYIZHWWQSYATFG/bundle.json","state":"https://pith.science/pith/F3XTOI4B72WYFYIZHWWQSYATFG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F3XTOI4B72WYFYIZHWWQSYATFG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:F3XTOI4B72WYFYIZHWWQSYATFG","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":"06120c8cab78ca78b341c4dae04a26286b552398b4ee05871517b9a41e95d057","cross_cats_sorted":["cs.CL","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-22T17:59:08Z","title_canon_sha256":"9c64ae905993356d66b4d4d91d8ee199c837a9da193d0c9c21aba141b90655c7"},"schema_version":"1.0","source":{"id":"1908.08529","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.08529","created_at":"2026-07-04T23:59:13Z"},{"alias_kind":"arxiv_version","alias_value":"1908.08529v1","created_at":"2026-07-04T23:59:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08529","created_at":"2026-07-04T23:59:13Z"},{"alias_kind":"pith_short_12","alias_value":"F3XTOI4B72WY","created_at":"2026-07-04T23:59:13Z"},{"alias_kind":"pith_short_16","alias_value":"F3XTOI4B72WYFYIZ","created_at":"2026-07-04T23:59:13Z"},{"alias_kind":"pith_short_8","alias_value":"F3XTOI4B","created_at":"2026-07-04T23:59:13Z"}],"graph_snapshots":[{"event_id":"sha256:2594248afbbbe329c244ac53a704c7d112298f27016a37fff1c8969d5c7c5365","target":"graph","created_at":"2026-07-04T23:59:13Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.08529/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diverse and accurate vision+language modeling is an important goal to retain creative freedom and maintain user engagement. However, adequately capturing the intricacies of diversity in language models is challenging. Recent works commonly resort to latent variable models augmented with more or less supervision from object detectors or part-of-speech tags. Common to all those methods is the fact that the latent variable either only initializes the sentence generation process or is identical across the steps of generation. Both methods offer no fine-grained control. To address this concern, we ","authors_text":"Alexander Schwing, Dhruv Batra, Harsh Agrawal, Jyoti Aneja","cross_cats":["cs.CL","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-22T17:59:08Z","title":"Sequential Latent Spaces for Modeling the Intention During Diverse Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08529","kind":"arxiv","version":1},"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:eb072af784baccf281ace621df940d328ec11bbd85b0de754278bfd7c7c5656f","target":"record","created_at":"2026-07-04T23:59:13Z","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":"06120c8cab78ca78b341c4dae04a26286b552398b4ee05871517b9a41e95d057","cross_cats_sorted":["cs.CL","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-22T17:59:08Z","title_canon_sha256":"9c64ae905993356d66b4d4d91d8ee199c837a9da193d0c9c21aba141b90655c7"},"schema_version":"1.0","source":{"id":"1908.08529","kind":"arxiv","version":1}},"canonical_sha256":"2eef372381fead82e1193dad096013299f9753f89c27094501d8ea15e0738b41","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2eef372381fead82e1193dad096013299f9753f89c27094501d8ea15e0738b41","first_computed_at":"2026-07-04T23:59:13.817668Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:59:13.817668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ojhGCmXPdYRn0JrFTdggsMXZa+LxkLeeaw24swrWRkYvVf8qLR/ldqwU6qko6xj2cuPHQcjO3KC1bMV438llBA==","signature_status":"signed_v1","signed_at":"2026-07-04T23:59:13.818005Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.08529","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb072af784baccf281ace621df940d328ec11bbd85b0de754278bfd7c7c5656f","sha256:2594248afbbbe329c244ac53a704c7d112298f27016a37fff1c8969d5c7c5365"],"state_sha256":"acb82f3b01c5d3503478d5eeeadcacd437dcaa278187da7556618f44334e9229"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HW1N+DW/Zr0MNVqiSGW4LuCUuer6ZBlHQRSLUNu5CaP3rNexTiuK/sCEhOnFGILP9P3suRwiZMrOOi3SvbNfAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T07:37:34.737969Z","bundle_sha256":"afe4a5087d5a4f5577470935e9d8445f3d1f8edbdd8f30bef84ce9ef9a3901ac"}}