{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:LYHKDFR3YKI4ZMLXCQXA266YPA","short_pith_number":"pith:LYHKDFR3","canonical_record":{"source":{"id":"2102.11526","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-23T07:20:12Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"f2105511012dcb36c2d1cdc2500c042f8fd0582de19357ad4d07ab0ae47c669c","abstract_canon_sha256":"791164ca222af56967074edce6756ed398aad3cee0398660ae109eff95e7dbb1"},"schema_version":"1.0"},"canonical_sha256":"5e0ea1963bc291ccb177142e0d7bd8783f0cfb93f4532e85c00fa532f408f010","source":{"kind":"arxiv","id":"2102.11526","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.11526","created_at":"2026-07-05T02:17:51Z"},{"alias_kind":"arxiv_version","alias_value":"2102.11526v1","created_at":"2026-07-05T02:17:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.11526","created_at":"2026-07-05T02:17:51Z"},{"alias_kind":"pith_short_12","alias_value":"LYHKDFR3YKI4","created_at":"2026-07-05T02:17:51Z"},{"alias_kind":"pith_short_16","alias_value":"LYHKDFR3YKI4ZMLX","created_at":"2026-07-05T02:17:51Z"},{"alias_kind":"pith_short_8","alias_value":"LYHKDFR3","created_at":"2026-07-05T02:17:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:LYHKDFR3YKI4ZMLXCQXA266YPA","target":"record","payload":{"canonical_record":{"source":{"id":"2102.11526","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-23T07:20:12Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"f2105511012dcb36c2d1cdc2500c042f8fd0582de19357ad4d07ab0ae47c669c","abstract_canon_sha256":"791164ca222af56967074edce6756ed398aad3cee0398660ae109eff95e7dbb1"},"schema_version":"1.0"},"canonical_sha256":"5e0ea1963bc291ccb177142e0d7bd8783f0cfb93f4532e85c00fa532f408f010","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:17:51.656875Z","signature_b64":"5hSgvXds9ThUaeaHVkRgY0WcOZTXrxswnGwb21qcovhMaMvlmqRsnmj2vb7tqw8LnMmtX4l9LMYHS96cXYnwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e0ea1963bc291ccb177142e0d7bd8783f0cfb93f4532e85c00fa532f408f010","last_reissued_at":"2026-07-05T02:17:51.656469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:17:51.656469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.11526","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":"2026-07-05T02:17:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lnmei0lIN7Ydg68Llp4ydTMe9VaZkNdhjUDoN9Bw/OrK3G94Rf1RPZKd7Zmij3ciub2sYt0fXBtObJGTr/gADA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T08:54:29.465212Z"},"content_sha256":"37f545b5a94f178915fa3ad7e10d0226cf4c7343b174da3678d9f9206a99d75b","schema_version":"1.0","event_id":"sha256:37f545b5a94f178915fa3ad7e10d0226cf4c7343b174da3678d9f9206a99d75b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:LYHKDFR3YKI4ZMLXCQXA266YPA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhanced Modality Transition for Image Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Yadan Luo, Zi Huang, Ziwei Wang","submitted_at":"2021-02-23T07:20:12Z","abstract_excerpt":"Image captioning model is a cross-modality knowledge discovery task, which targets at automatically describing an image with an informative and coherent sentence. To generate the captions, the previous encoder-decoder frameworks directly forward the visual vectors to the recurrent language model, forcing the recurrent units to generate a sentence based on the visual features. Although these sentences are generally readable, they still suffer from the lack of details and highlights, due to the fact that the substantial gap between the image and text modalities is not sufficiently addressed. In "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.11526","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/2102.11526/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":"2026-07-05T02:17:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R6o4KD9A+5jWbpdtUqV5/9qSaZFkNxMZlcMtzAte54TbOVrHdnvmpB4TCatHSaKbHA0aAEdhUv6ZUbTQgq1BAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T08:54:29.465713Z"},"content_sha256":"105726ac494606b64397865f4f733d02c45541d083030bbb1f9b57c6526d3d81","schema_version":"1.0","event_id":"sha256:105726ac494606b64397865f4f733d02c45541d083030bbb1f9b57c6526d3d81"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LYHKDFR3YKI4ZMLXCQXA266YPA/bundle.json","state_url":"https://pith.science/pith/LYHKDFR3YKI4ZMLXCQXA266YPA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LYHKDFR3YKI4ZMLXCQXA266YPA/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":"2026-08-17T08:54:29Z","links":{"resolver":"https://pith.science/pith/LYHKDFR3YKI4ZMLXCQXA266YPA","bundle":"https://pith.science/pith/LYHKDFR3YKI4ZMLXCQXA266YPA/bundle.json","state":"https://pith.science/pith/LYHKDFR3YKI4ZMLXCQXA266YPA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LYHKDFR3YKI4ZMLXCQXA266YPA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:LYHKDFR3YKI4ZMLXCQXA266YPA","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":"791164ca222af56967074edce6756ed398aad3cee0398660ae109eff95e7dbb1","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-23T07:20:12Z","title_canon_sha256":"f2105511012dcb36c2d1cdc2500c042f8fd0582de19357ad4d07ab0ae47c669c"},"schema_version":"1.0","source":{"id":"2102.11526","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.11526","created_at":"2026-07-05T02:17:51Z"},{"alias_kind":"arxiv_version","alias_value":"2102.11526v1","created_at":"2026-07-05T02:17:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.11526","created_at":"2026-07-05T02:17:51Z"},{"alias_kind":"pith_short_12","alias_value":"LYHKDFR3YKI4","created_at":"2026-07-05T02:17:51Z"},{"alias_kind":"pith_short_16","alias_value":"LYHKDFR3YKI4ZMLX","created_at":"2026-07-05T02:17:51Z"},{"alias_kind":"pith_short_8","alias_value":"LYHKDFR3","created_at":"2026-07-05T02:17:51Z"}],"graph_snapshots":[{"event_id":"sha256:105726ac494606b64397865f4f733d02c45541d083030bbb1f9b57c6526d3d81","target":"graph","created_at":"2026-07-05T02:17:51Z","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/2102.11526/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image captioning model is a cross-modality knowledge discovery task, which targets at automatically describing an image with an informative and coherent sentence. To generate the captions, the previous encoder-decoder frameworks directly forward the visual vectors to the recurrent language model, forcing the recurrent units to generate a sentence based on the visual features. Although these sentences are generally readable, they still suffer from the lack of details and highlights, due to the fact that the substantial gap between the image and text modalities is not sufficiently addressed. In ","authors_text":"Yadan Luo, Zi Huang, Ziwei Wang","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-23T07:20:12Z","title":"Enhanced Modality Transition for Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.11526","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":"sha256:37f545b5a94f178915fa3ad7e10d0226cf4c7343b174da3678d9f9206a99d75b","target":"record","created_at":"2026-07-05T02:17:51Z","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":"791164ca222af56967074edce6756ed398aad3cee0398660ae109eff95e7dbb1","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-23T07:20:12Z","title_canon_sha256":"f2105511012dcb36c2d1cdc2500c042f8fd0582de19357ad4d07ab0ae47c669c"},"schema_version":"1.0","source":{"id":"2102.11526","kind":"arxiv","version":1}},"canonical_sha256":"5e0ea1963bc291ccb177142e0d7bd8783f0cfb93f4532e85c00fa532f408f010","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e0ea1963bc291ccb177142e0d7bd8783f0cfb93f4532e85c00fa532f408f010","first_computed_at":"2026-07-05T02:17:51.656469Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:17:51.656469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5hSgvXds9ThUaeaHVkRgY0WcOZTXrxswnGwb21qcovhMaMvlmqRsnmj2vb7tqw8LnMmtX4l9LMYHS96cXYnwAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:17:51.656875Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.11526","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37f545b5a94f178915fa3ad7e10d0226cf4c7343b174da3678d9f9206a99d75b","sha256:105726ac494606b64397865f4f733d02c45541d083030bbb1f9b57c6526d3d81"],"state_sha256":"0671abc25524611a96733090b31aafdf7f734bde4afa6b84c81c156b5294ac1e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"srQIvcHXw6+uMsprBl19VOUzaQFOxsyn0Xhp3PmYNv6RZ4r6Fqf3h+oD4RL0NMGSb2k2xiXcKdM/7kdS6HZjBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T08:54:29.469479Z","bundle_sha256":"ef5e1f359e1b3551492bcc0d2aabba8ad5edb1459a3d9f247cf6c0e4334b5faa"}}