{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:UIUMBPH73R75HWAEJO5ZIXAERH","short_pith_number":"pith:UIUMBPH7","canonical_record":{"source":{"id":"1704.06972","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-23T20:17:12Z","cross_cats_sorted":[],"title_canon_sha256":"5c1725f9a716fe840efeb552a054eadbfd998e161b5a831958802062548eae99","abstract_canon_sha256":"2bc38b11e6d9fb70ba4e79e542139024ea02820d73e5d938359416fcb3f7efd9"},"schema_version":"1.0"},"canonical_sha256":"a228c0bcffdc7fd3d8044bbb945c0489d91a1b0e94c0d880b793a9cf5c83ecfb","source":{"kind":"arxiv","id":"1704.06972","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.06972","created_at":"2026-05-18T00:45:55Z"},{"alias_kind":"arxiv_version","alias_value":"1704.06972v1","created_at":"2026-05-18T00:45:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06972","created_at":"2026-05-18T00:45:55Z"},{"alias_kind":"pith_short_12","alias_value":"UIUMBPH73R75","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"UIUMBPH73R75HWAE","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"UIUMBPH7","created_at":"2026-05-18T12:31:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:UIUMBPH73R75HWAEJO5ZIXAERH","target":"record","payload":{"canonical_record":{"source":{"id":"1704.06972","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-23T20:17:12Z","cross_cats_sorted":[],"title_canon_sha256":"5c1725f9a716fe840efeb552a054eadbfd998e161b5a831958802062548eae99","abstract_canon_sha256":"2bc38b11e6d9fb70ba4e79e542139024ea02820d73e5d938359416fcb3f7efd9"},"schema_version":"1.0"},"canonical_sha256":"a228c0bcffdc7fd3d8044bbb945c0489d91a1b0e94c0d880b793a9cf5c83ecfb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:55.168164Z","signature_b64":"5wYOp7zb19lAPQ5HA2EUhPQCzYutIaKylHqUHT1aDnnIOIzqo+KP8HQMmjmq4cvRmu1/fV+fyGKWHutdXFykDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a228c0bcffdc7fd3d8044bbb945c0489d91a1b0e94c0d880b793a9cf5c83ecfb","last_reissued_at":"2026-05-18T00:45:55.167572Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:55.167572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.06972","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":"2026-05-18T00:45:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FTv5wrwx4XBr2SssRhwJU5YmTa01sQCOSqIzqDiWvuvMfVFEifcfiQhDVDjo6PGeJSqROZKSIjBWDv8eWIiUAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T04:19:46.177537Z"},"content_sha256":"2a6ef8fa4ec2ab3b13d713cccc33fe4665bf16edb0b5e350c523f45179c9e924","schema_version":"1.0","event_id":"sha256:2a6ef8fa4ec2ab3b13d713cccc33fe4665bf16edb0b5e350c523f45179c9e924"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:UIUMBPH73R75HWAEJO5ZIXAERH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Skeleton Key: Image Captioning by Skeleton-Attribute Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Garrison W. Cottrell, Scott Cohen, Xiaohui Shen, Yufei Wang, Zhe Lin","submitted_at":"2017-04-23T20:17:12Z","abstract_excerpt":"Recently, there has been a lot of interest in automatically generating descriptions for an image. Most existing language-model based approaches for this task learn to generate an image description word by word in its original word order. However, for humans, it is more natural to locate the objects and their relationships first, and then elaborate on each object, describing notable attributes. We present a coarse-to-fine method that decomposes the original image description into a skeleton sentence and its attributes, and generates the skeleton sentence and attribute phrases separately. By thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.06972","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":"2026-05-18T00:45:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DAWkdjaGcKB+d45LcF23cNZIvhNbGMmnmhV+oYUg9UCjV30mraI14wWhIQ9jTW0MQ7sD7HYxrXREvuUkJ49oAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T04:19:46.177888Z"},"content_sha256":"ba3215d6b3cf28458d4766580737abc59bec31707971a22e15c4f2995c51e381","schema_version":"1.0","event_id":"sha256:ba3215d6b3cf28458d4766580737abc59bec31707971a22e15c4f2995c51e381"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UIUMBPH73R75HWAEJO5ZIXAERH/bundle.json","state_url":"https://pith.science/pith/UIUMBPH73R75HWAEJO5ZIXAERH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UIUMBPH73R75HWAEJO5ZIXAERH/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":"2026-06-02T04:19:46Z","links":{"resolver":"https://pith.science/pith/UIUMBPH73R75HWAEJO5ZIXAERH","bundle":"https://pith.science/pith/UIUMBPH73R75HWAEJO5ZIXAERH/bundle.json","state":"https://pith.science/pith/UIUMBPH73R75HWAEJO5ZIXAERH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UIUMBPH73R75HWAEJO5ZIXAERH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:UIUMBPH73R75HWAEJO5ZIXAERH","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":"2bc38b11e6d9fb70ba4e79e542139024ea02820d73e5d938359416fcb3f7efd9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-23T20:17:12Z","title_canon_sha256":"5c1725f9a716fe840efeb552a054eadbfd998e161b5a831958802062548eae99"},"schema_version":"1.0","source":{"id":"1704.06972","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.06972","created_at":"2026-05-18T00:45:55Z"},{"alias_kind":"arxiv_version","alias_value":"1704.06972v1","created_at":"2026-05-18T00:45:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06972","created_at":"2026-05-18T00:45:55Z"},{"alias_kind":"pith_short_12","alias_value":"UIUMBPH73R75","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"UIUMBPH73R75HWAE","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"UIUMBPH7","created_at":"2026-05-18T12:31:46Z"}],"graph_snapshots":[{"event_id":"sha256:ba3215d6b3cf28458d4766580737abc59bec31707971a22e15c4f2995c51e381","target":"graph","created_at":"2026-05-18T00:45:55Z","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":"Recently, there has been a lot of interest in automatically generating descriptions for an image. Most existing language-model based approaches for this task learn to generate an image description word by word in its original word order. However, for humans, it is more natural to locate the objects and their relationships first, and then elaborate on each object, describing notable attributes. We present a coarse-to-fine method that decomposes the original image description into a skeleton sentence and its attributes, and generates the skeleton sentence and attribute phrases separately. By thi","authors_text":"Garrison W. Cottrell, Scott Cohen, Xiaohui Shen, Yufei Wang, Zhe Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-23T20:17:12Z","title":"Skeleton Key: Image Captioning by Skeleton-Attribute Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.06972","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":"sha256:2a6ef8fa4ec2ab3b13d713cccc33fe4665bf16edb0b5e350c523f45179c9e924","target":"record","created_at":"2026-05-18T00:45:55Z","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":"2bc38b11e6d9fb70ba4e79e542139024ea02820d73e5d938359416fcb3f7efd9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-23T20:17:12Z","title_canon_sha256":"5c1725f9a716fe840efeb552a054eadbfd998e161b5a831958802062548eae99"},"schema_version":"1.0","source":{"id":"1704.06972","kind":"arxiv","version":1}},"canonical_sha256":"a228c0bcffdc7fd3d8044bbb945c0489d91a1b0e94c0d880b793a9cf5c83ecfb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a228c0bcffdc7fd3d8044bbb945c0489d91a1b0e94c0d880b793a9cf5c83ecfb","first_computed_at":"2026-05-18T00:45:55.167572Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:45:55.167572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5wYOp7zb19lAPQ5HA2EUhPQCzYutIaKylHqUHT1aDnnIOIzqo+KP8HQMmjmq4cvRmu1/fV+fyGKWHutdXFykDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:45:55.168164Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.06972","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a6ef8fa4ec2ab3b13d713cccc33fe4665bf16edb0b5e350c523f45179c9e924","sha256:ba3215d6b3cf28458d4766580737abc59bec31707971a22e15c4f2995c51e381"],"state_sha256":"3a042b0a01a101dc42f623c4e5239e418d10502abe45fefbe1d3ff71dc2673c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sqg55c5jR2Xc5HIZQYPOJ/69/F8zFU0JO7V2yjDsxab0JJcsO3cLKdq8aKErv9eO8kiWZz2gYKoTxqpyDivTBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T04:19:46.179906Z","bundle_sha256":"2b434d15467473b1bee3ba49a7b96e74685761b6245bae7c38c7755e310b11c8"}}