{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:RIAJYRWKAP2ICYR452DABEXYOH","short_pith_number":"pith:RIAJYRWK","canonical_record":{"source":{"id":"2101.11911","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-28T10:26:08Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"18c6bc1ace80daacbfcf1788e956752e5363cd6ece24dfdec74a4205befabb0f","abstract_canon_sha256":"4cfabbd4908c4bce8a19228abca4a45844a18ee0a1523d18c47f4e40db749986"},"schema_version":"1.0"},"canonical_sha256":"8a009c46ca03f481623cee860092f871ea3c6b0a4650f45ba62b773038b135aa","source":{"kind":"arxiv","id":"2101.11911","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.11911","created_at":"2026-07-05T02:10:32Z"},{"alias_kind":"arxiv_version","alias_value":"2101.11911v1","created_at":"2026-07-05T02:10:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.11911","created_at":"2026-07-05T02:10:32Z"},{"alias_kind":"pith_short_12","alias_value":"RIAJYRWKAP2I","created_at":"2026-07-05T02:10:32Z"},{"alias_kind":"pith_short_16","alias_value":"RIAJYRWKAP2ICYR4","created_at":"2026-07-05T02:10:32Z"},{"alias_kind":"pith_short_8","alias_value":"RIAJYRWK","created_at":"2026-07-05T02:10:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:RIAJYRWKAP2ICYR452DABEXYOH","target":"record","payload":{"canonical_record":{"source":{"id":"2101.11911","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-28T10:26:08Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"18c6bc1ace80daacbfcf1788e956752e5363cd6ece24dfdec74a4205befabb0f","abstract_canon_sha256":"4cfabbd4908c4bce8a19228abca4a45844a18ee0a1523d18c47f4e40db749986"},"schema_version":"1.0"},"canonical_sha256":"8a009c46ca03f481623cee860092f871ea3c6b0a4650f45ba62b773038b135aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:10:32.109535Z","signature_b64":"aMyYaWB2+DX6m7p1TPYLZKPWXeacgMsIQcUHPtkjFIanRJtdm4vDUCZV7X1DoWgNyoELBjYUEvsvUDwtquerBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a009c46ca03f481623cee860092f871ea3c6b0a4650f45ba62b773038b135aa","last_reissued_at":"2026-07-05T02:10:32.109078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:10:32.109078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.11911","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":"2026-07-05T02:10:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"onGU3TZfmPCfve3aQOGkM+6wbC50/5FctmIiAKB79ye5l5fSXSkt/kYWIaY8OMYG28PwPo1HtKaTWpBjqpZWBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T11:53:51.892989Z"},"content_sha256":"6d0d992fc41c0666a6ce229538c83b9f3be822cc29e7767aa9441a43f9652f27","schema_version":"1.0","event_id":"sha256:6d0d992fc41c0666a6ce229538c83b9f3be822cc29e7767aa9441a43f9652f27"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:RIAJYRWKAP2ICYR452DABEXYOH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Role of Syntactic Planning in Compositional Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Desmond Elliott, Emanuele Bugliarello","submitted_at":"2021-01-28T10:26:08Z","abstract_excerpt":"Image captioning has focused on generalizing to images drawn from the same distribution as the training set, and not to the more challenging problem of generalizing to different distributions of images. Recently, Nikolaus et al. (2019) introduced a dataset to assess compositional generalization in image captioning, where models are evaluated on their ability to describe images with unseen adjective-noun and noun-verb compositions. In this work, we investigate different methods to improve compositional generalization by planning the syntactic structure of a caption. Our experiments show that jo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.11911","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/2101.11911/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":"2026-07-05T02:10:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SXgfE6PVp9YgtRR50A0u8kuhPrK5pdfv+cKZ1dZMHN2SHmw6MkM4uj4CKJx8tmpCM8XivPt4dpM2zo/gikp1BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T11:53:51.893377Z"},"content_sha256":"64f03519e30fb09dd5a1469e65580944dc7805855daa58c01794c4a5544e0854","schema_version":"1.0","event_id":"sha256:64f03519e30fb09dd5a1469e65580944dc7805855daa58c01794c4a5544e0854"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RIAJYRWKAP2ICYR452DABEXYOH/bundle.json","state_url":"https://pith.science/pith/RIAJYRWKAP2ICYR452DABEXYOH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RIAJYRWKAP2ICYR452DABEXYOH/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":"2026-07-05T11:53:51Z","links":{"resolver":"https://pith.science/pith/RIAJYRWKAP2ICYR452DABEXYOH","bundle":"https://pith.science/pith/RIAJYRWKAP2ICYR452DABEXYOH/bundle.json","state":"https://pith.science/pith/RIAJYRWKAP2ICYR452DABEXYOH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RIAJYRWKAP2ICYR452DABEXYOH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RIAJYRWKAP2ICYR452DABEXYOH","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":"4cfabbd4908c4bce8a19228abca4a45844a18ee0a1523d18c47f4e40db749986","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-28T10:26:08Z","title_canon_sha256":"18c6bc1ace80daacbfcf1788e956752e5363cd6ece24dfdec74a4205befabb0f"},"schema_version":"1.0","source":{"id":"2101.11911","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.11911","created_at":"2026-07-05T02:10:32Z"},{"alias_kind":"arxiv_version","alias_value":"2101.11911v1","created_at":"2026-07-05T02:10:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.11911","created_at":"2026-07-05T02:10:32Z"},{"alias_kind":"pith_short_12","alias_value":"RIAJYRWKAP2I","created_at":"2026-07-05T02:10:32Z"},{"alias_kind":"pith_short_16","alias_value":"RIAJYRWKAP2ICYR4","created_at":"2026-07-05T02:10:32Z"},{"alias_kind":"pith_short_8","alias_value":"RIAJYRWK","created_at":"2026-07-05T02:10:32Z"}],"graph_snapshots":[{"event_id":"sha256:64f03519e30fb09dd5a1469e65580944dc7805855daa58c01794c4a5544e0854","target":"graph","created_at":"2026-07-05T02:10:32Z","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/2101.11911/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image captioning has focused on generalizing to images drawn from the same distribution as the training set, and not to the more challenging problem of generalizing to different distributions of images. Recently, Nikolaus et al. (2019) introduced a dataset to assess compositional generalization in image captioning, where models are evaluated on their ability to describe images with unseen adjective-noun and noun-verb compositions. In this work, we investigate different methods to improve compositional generalization by planning the syntactic structure of a caption. Our experiments show that jo","authors_text":"Desmond Elliott, Emanuele Bugliarello","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-28T10:26:08Z","title":"The Role of Syntactic Planning in Compositional Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.11911","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":"sha256:6d0d992fc41c0666a6ce229538c83b9f3be822cc29e7767aa9441a43f9652f27","target":"record","created_at":"2026-07-05T02:10:32Z","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":"4cfabbd4908c4bce8a19228abca4a45844a18ee0a1523d18c47f4e40db749986","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-28T10:26:08Z","title_canon_sha256":"18c6bc1ace80daacbfcf1788e956752e5363cd6ece24dfdec74a4205befabb0f"},"schema_version":"1.0","source":{"id":"2101.11911","kind":"arxiv","version":1}},"canonical_sha256":"8a009c46ca03f481623cee860092f871ea3c6b0a4650f45ba62b773038b135aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a009c46ca03f481623cee860092f871ea3c6b0a4650f45ba62b773038b135aa","first_computed_at":"2026-07-05T02:10:32.109078Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:10:32.109078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aMyYaWB2+DX6m7p1TPYLZKPWXeacgMsIQcUHPtkjFIanRJtdm4vDUCZV7X1DoWgNyoELBjYUEvsvUDwtquerBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:10:32.109535Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.11911","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d0d992fc41c0666a6ce229538c83b9f3be822cc29e7767aa9441a43f9652f27","sha256:64f03519e30fb09dd5a1469e65580944dc7805855daa58c01794c4a5544e0854"],"state_sha256":"cf2cefae6057cbe48d7e4f761ea891521137e42867aa2448a0da6e1e7af97f36"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pdM69aVuCM8QYryQduZXpKGmINpR+2oem3iuIhmd9ciOcKEErb/vjSokAi6zC6fxjDrV5CpPdC9+MWviJjtcBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T11:53:51.895343Z","bundle_sha256":"486d1bb1c04aaaeeaa1ff946f9aab59e9f5d95efaf87e939910bdd539a6fceb0"}}