{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:UL3QVXBVRONFC5N6MXMU3KKC6C","short_pith_number":"pith:UL3QVXBV","canonical_record":{"source":{"id":"1803.09845","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-27T01:59:56Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b9ed7a73d3f455f646fa96aa6016bd4d1c555cb4f3ce1fdac3775d344d422d71","abstract_canon_sha256":"1ce250452dfdc528ad9d12d906e43d2a68492514cb2e4c3c3d642dd594cc41d3"},"schema_version":"1.0"},"canonical_sha256":"a2f70adc358b9a5175be65d94da942f0aafad00c3e943880e3a5a1b725f0f291","source":{"kind":"arxiv","id":"1803.09845","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.09845","created_at":"2026-05-18T00:20:10Z"},{"alias_kind":"arxiv_version","alias_value":"1803.09845v1","created_at":"2026-05-18T00:20:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09845","created_at":"2026-05-18T00:20:10Z"},{"alias_kind":"pith_short_12","alias_value":"UL3QVXBVRONF","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UL3QVXBVRONFC5N6","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UL3QVXBV","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:UL3QVXBVRONFC5N6MXMU3KKC6C","target":"record","payload":{"canonical_record":{"source":{"id":"1803.09845","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-27T01:59:56Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b9ed7a73d3f455f646fa96aa6016bd4d1c555cb4f3ce1fdac3775d344d422d71","abstract_canon_sha256":"1ce250452dfdc528ad9d12d906e43d2a68492514cb2e4c3c3d642dd594cc41d3"},"schema_version":"1.0"},"canonical_sha256":"a2f70adc358b9a5175be65d94da942f0aafad00c3e943880e3a5a1b725f0f291","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:10.298739Z","signature_b64":"rZKazhYEGW2ozCB6Ol30OeEHRmMHdLkGxXJRM/nmQ72HASI6Ng1BEiCVpcZM/r4RXTioqG8YuXcRIlyNY4z0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2f70adc358b9a5175be65d94da942f0aafad00c3e943880e3a5a1b725f0f291","last_reissued_at":"2026-05-18T00:20:10.298108Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:10.298108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.09845","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":"2026-05-18T00:20:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oN7SmQrU155VCgp8E6Led8CZ8TSWeF955pe1HElvQF3VrUvMVbkc4tX3s0j8Yjqv7kPE0HE6jKEPZuBI1hTuAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T13:30:36.295399Z"},"content_sha256":"cfd250584c7b9486566ee76445af98fc42c273675d660c2f9227f247482fad35","schema_version":"1.0","event_id":"sha256:cfd250584c7b9486566ee76445af98fc42c273675d660c2f9227f247482fad35"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:UL3QVXBVRONFC5N6MXMU3KKC6C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Baby Talk","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Devi Parikh, Dhruv Batra, Jianwei Yang, Jiasen Lu","submitted_at":"2018-03-27T01:59:56Z","abstract_excerpt":"We introduce a novel framework for image captioning that can produce natural language explicitly grounded in entities that object detectors find in the image. Our approach reconciles classical slot filling approaches (that are generally better grounded in images) with modern neural captioning approaches (that are generally more natural sounding and accurate). Our approach first generates a sentence `template' with slot locations explicitly tied to specific image regions. These slots are then filled in by visual concepts identified in the regions by object detectors. The entire architecture (se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09845","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":""},"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":"2026-05-18T00:20:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JbEk/zji5lLTQwudc7izM56pF9rAtRmsUcgTXBAJ+iP2urSHogEIBRVCU2RG1CPmsWrO8WiQJg9ayB6k8elxAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T13:30:36.296069Z"},"content_sha256":"31e4b64340e0a03fd5b2250977f8a3ce97ba40348480db242a2481696b7837d1","schema_version":"1.0","event_id":"sha256:31e4b64340e0a03fd5b2250977f8a3ce97ba40348480db242a2481696b7837d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UL3QVXBVRONFC5N6MXMU3KKC6C/bundle.json","state_url":"https://pith.science/pith/UL3QVXBVRONFC5N6MXMU3KKC6C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UL3QVXBVRONFC5N6MXMU3KKC6C/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":"2026-05-26T13:30:36Z","links":{"resolver":"https://pith.science/pith/UL3QVXBVRONFC5N6MXMU3KKC6C","bundle":"https://pith.science/pith/UL3QVXBVRONFC5N6MXMU3KKC6C/bundle.json","state":"https://pith.science/pith/UL3QVXBVRONFC5N6MXMU3KKC6C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UL3QVXBVRONFC5N6MXMU3KKC6C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:UL3QVXBVRONFC5N6MXMU3KKC6C","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":"1ce250452dfdc528ad9d12d906e43d2a68492514cb2e4c3c3d642dd594cc41d3","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-27T01:59:56Z","title_canon_sha256":"b9ed7a73d3f455f646fa96aa6016bd4d1c555cb4f3ce1fdac3775d344d422d71"},"schema_version":"1.0","source":{"id":"1803.09845","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.09845","created_at":"2026-05-18T00:20:10Z"},{"alias_kind":"arxiv_version","alias_value":"1803.09845v1","created_at":"2026-05-18T00:20:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09845","created_at":"2026-05-18T00:20:10Z"},{"alias_kind":"pith_short_12","alias_value":"UL3QVXBVRONF","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UL3QVXBVRONFC5N6","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UL3QVXBV","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:31e4b64340e0a03fd5b2250977f8a3ce97ba40348480db242a2481696b7837d1","target":"graph","created_at":"2026-05-18T00:20:10Z","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":"We introduce a novel framework for image captioning that can produce natural language explicitly grounded in entities that object detectors find in the image. Our approach reconciles classical slot filling approaches (that are generally better grounded in images) with modern neural captioning approaches (that are generally more natural sounding and accurate). Our approach first generates a sentence `template' with slot locations explicitly tied to specific image regions. These slots are then filled in by visual concepts identified in the regions by object detectors. The entire architecture (se","authors_text":"Devi Parikh, Dhruv Batra, Jianwei Yang, Jiasen Lu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-27T01:59:56Z","title":"Neural Baby Talk"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09845","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:cfd250584c7b9486566ee76445af98fc42c273675d660c2f9227f247482fad35","target":"record","created_at":"2026-05-18T00:20:10Z","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":"1ce250452dfdc528ad9d12d906e43d2a68492514cb2e4c3c3d642dd594cc41d3","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-27T01:59:56Z","title_canon_sha256":"b9ed7a73d3f455f646fa96aa6016bd4d1c555cb4f3ce1fdac3775d344d422d71"},"schema_version":"1.0","source":{"id":"1803.09845","kind":"arxiv","version":1}},"canonical_sha256":"a2f70adc358b9a5175be65d94da942f0aafad00c3e943880e3a5a1b725f0f291","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2f70adc358b9a5175be65d94da942f0aafad00c3e943880e3a5a1b725f0f291","first_computed_at":"2026-05-18T00:20:10.298108Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:10.298108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rZKazhYEGW2ozCB6Ol30OeEHRmMHdLkGxXJRM/nmQ72HASI6Ng1BEiCVpcZM/r4RXTioqG8YuXcRIlyNY4z0AA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:10.298739Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.09845","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfd250584c7b9486566ee76445af98fc42c273675d660c2f9227f247482fad35","sha256:31e4b64340e0a03fd5b2250977f8a3ce97ba40348480db242a2481696b7837d1"],"state_sha256":"c111d0e1c06724e8fc39c34368cd394e9a5179d47493b2809628acc20542cfc4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"so7P7hrCXueTh18nSJ86FIIlDQt6/B53ivB+lRZdTO/oSAmO3xcrWgQ2h12pc8JrzKyxtF9FTBicXH76VD3PCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T13:30:36.299828Z","bundle_sha256":"15af360e5d43d8a22c3c2c003c0d985b3725d0474f0eda0f8c36b1f2e88b2097"}}