{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RRCCA5PFFVSZPVJZXUNWQUOLR3","short_pith_number":"pith:RRCCA5PF","canonical_record":{"source":{"id":"1809.04144","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-11T20:32:21Z","cross_cats_sorted":[],"title_canon_sha256":"c3808f48065296a823261f3166930293fcdca098effdd5077a3608925287dc38","abstract_canon_sha256":"99fb0533d0adcc72d41b90cb624044941d561af775fd9e28fdbbfacb42827074"},"schema_version":"1.0"},"canonical_sha256":"8c442075e52d6597d539bd1b6851cb8ec6e0ce07739a0dd369abaa1f40e86f2e","source":{"kind":"arxiv","id":"1809.04144","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04144","created_at":"2026-05-18T00:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04144v1","created_at":"2026-05-18T00:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04144","created_at":"2026-05-18T00:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"RRCCA5PFFVSZ","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RRCCA5PFFVSZPVJZ","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RRCCA5PF","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RRCCA5PFFVSZPVJZXUNWQUOLR3","target":"record","payload":{"canonical_record":{"source":{"id":"1809.04144","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-11T20:32:21Z","cross_cats_sorted":[],"title_canon_sha256":"c3808f48065296a823261f3166930293fcdca098effdd5077a3608925287dc38","abstract_canon_sha256":"99fb0533d0adcc72d41b90cb624044941d561af775fd9e28fdbbfacb42827074"},"schema_version":"1.0"},"canonical_sha256":"8c442075e52d6597d539bd1b6851cb8ec6e0ce07739a0dd369abaa1f40e86f2e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:55.363653Z","signature_b64":"q+CBlud5HZO4dsSTgzlFwzsz0Kw5Ej9U7xVzDvWipy0LD3EUTAPK2mmkGkFgC1Fza+TI9jcjOK72YksGIwbTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c442075e52d6597d539bd1b6851cb8ec6e0ce07739a0dd369abaa1f40e86f2e","last_reissued_at":"2026-05-18T00:05:55.362971Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:55.362971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.04144","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":"2026-05-18T00:05:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"srh61F7AtP/pnDcyTaNVquUOzk9DKmteUpXBpBZsjDoZV9usULWHmM9zZyC+o6eZZg8Xxti5kSC+TTPzLEMMDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T19:26:23.721336Z"},"content_sha256":"81e15b5ffc84dd42e6d10f7f3e4ce767ecbe781fa138f2fed4b014b82249e0c4","schema_version":"1.0","event_id":"sha256:81e15b5ffc84dd42e6d10f7f3e4ce767ecbe781fa138f2fed4b014b82249e0c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RRCCA5PFFVSZPVJZXUNWQUOLR3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"End-to-end Image Captioning Exploits Multimodal Distributional Similarity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Josiah Wang, Lucia Specia, Pranava Madhyastha","submitted_at":"2018-09-11T20:32:21Z","abstract_excerpt":"We hypothesize that end-to-end neural image captioning systems work seemingly well because they exploit and learn `distributional similarity' in a multimodal feature space by mapping a test image to similar training images in this space and generating a caption from the same space. To validate our hypothesis, we focus on the `image' side of image captioning, and vary the input image representation but keep the RNN text generation component of a CNN-RNN model constant. Our analysis indicates that image captioning models (i) are capable of separating structure from noisy input representations; ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04144","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":"2026-05-18T00:05:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H5J+VYX+xoE/QWQ+xGFX/Tb6PK3JapF2tiU7kKqVCU+znxF7ZRtdS4BzR7CYK0rmVqgxSqYNOZwCE8qOrErHBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T19:26:23.721681Z"},"content_sha256":"5afeb735b2543e730c00ea39f2da1453c81854ac9fec92ee41277903f856591f","schema_version":"1.0","event_id":"sha256:5afeb735b2543e730c00ea39f2da1453c81854ac9fec92ee41277903f856591f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RRCCA5PFFVSZPVJZXUNWQUOLR3/bundle.json","state_url":"https://pith.science/pith/RRCCA5PFFVSZPVJZXUNWQUOLR3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RRCCA5PFFVSZPVJZXUNWQUOLR3/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":"2026-06-02T19:26:23Z","links":{"resolver":"https://pith.science/pith/RRCCA5PFFVSZPVJZXUNWQUOLR3","bundle":"https://pith.science/pith/RRCCA5PFFVSZPVJZXUNWQUOLR3/bundle.json","state":"https://pith.science/pith/RRCCA5PFFVSZPVJZXUNWQUOLR3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RRCCA5PFFVSZPVJZXUNWQUOLR3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RRCCA5PFFVSZPVJZXUNWQUOLR3","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":"99fb0533d0adcc72d41b90cb624044941d561af775fd9e28fdbbfacb42827074","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-11T20:32:21Z","title_canon_sha256":"c3808f48065296a823261f3166930293fcdca098effdd5077a3608925287dc38"},"schema_version":"1.0","source":{"id":"1809.04144","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04144","created_at":"2026-05-18T00:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04144v1","created_at":"2026-05-18T00:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04144","created_at":"2026-05-18T00:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"RRCCA5PFFVSZ","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RRCCA5PFFVSZPVJZ","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RRCCA5PF","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:5afeb735b2543e730c00ea39f2da1453c81854ac9fec92ee41277903f856591f","target":"graph","created_at":"2026-05-18T00:05:55Z","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":"We hypothesize that end-to-end neural image captioning systems work seemingly well because they exploit and learn `distributional similarity' in a multimodal feature space by mapping a test image to similar training images in this space and generating a caption from the same space. To validate our hypothesis, we focus on the `image' side of image captioning, and vary the input image representation but keep the RNN text generation component of a CNN-RNN model constant. Our analysis indicates that image captioning models (i) are capable of separating structure from noisy input representations; (","authors_text":"Josiah Wang, Lucia Specia, Pranava Madhyastha","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-11T20:32:21Z","title":"End-to-end Image Captioning Exploits Multimodal Distributional Similarity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04144","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":"sha256:81e15b5ffc84dd42e6d10f7f3e4ce767ecbe781fa138f2fed4b014b82249e0c4","target":"record","created_at":"2026-05-18T00:05:55Z","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":"99fb0533d0adcc72d41b90cb624044941d561af775fd9e28fdbbfacb42827074","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-11T20:32:21Z","title_canon_sha256":"c3808f48065296a823261f3166930293fcdca098effdd5077a3608925287dc38"},"schema_version":"1.0","source":{"id":"1809.04144","kind":"arxiv","version":1}},"canonical_sha256":"8c442075e52d6597d539bd1b6851cb8ec6e0ce07739a0dd369abaa1f40e86f2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c442075e52d6597d539bd1b6851cb8ec6e0ce07739a0dd369abaa1f40e86f2e","first_computed_at":"2026-05-18T00:05:55.362971Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:55.362971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q+CBlud5HZO4dsSTgzlFwzsz0Kw5Ej9U7xVzDvWipy0LD3EUTAPK2mmkGkFgC1Fza+TI9jcjOK72YksGIwbTDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:55.363653Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.04144","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81e15b5ffc84dd42e6d10f7f3e4ce767ecbe781fa138f2fed4b014b82249e0c4","sha256:5afeb735b2543e730c00ea39f2da1453c81854ac9fec92ee41277903f856591f"],"state_sha256":"aeb97b2bc616a55d683733f333856874f23e2153738405530d06341f26b668f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CdAiaUoCoFpcnajyyhezUEh0WmtaCu6d6llzOWNl0htuzubiYxSSNVZ8Sp28EUIrPFTYDpgP39FGAgG227IfCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T19:26:23.723639Z","bundle_sha256":"c117163a4a6dab47dca019e5d2158856bce6f8746675cce6eb3d7766ca22cc70"}}