{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NFECBVGPDSTGCLHGTEV5O6QDNK","short_pith_number":"pith:NFECBVGP","canonical_record":{"source":{"id":"2305.16944","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T13:59:45Z","cross_cats_sorted":[],"title_canon_sha256":"e6b0b09327b599fa1c37207e8d66cba39d8d10830598d9689a57ed0d34f9986e","abstract_canon_sha256":"d4c2d1aff44d638aa77d196fcb8134ec566d102cf32b9e495a4ae2b34a9c8b72"},"schema_version":"1.0"},"canonical_sha256":"694820d4cf1ca6612ce6992bd77a036a8e0ea142477d813a224da2b032292240","source":{"kind":"arxiv","id":"2305.16944","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16944","created_at":"2026-07-05T06:20:44Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16944v3","created_at":"2026-07-05T06:20:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16944","created_at":"2026-07-05T06:20:44Z"},{"alias_kind":"pith_short_12","alias_value":"NFECBVGPDSTG","created_at":"2026-07-05T06:20:44Z"},{"alias_kind":"pith_short_16","alias_value":"NFECBVGPDSTGCLHG","created_at":"2026-07-05T06:20:44Z"},{"alias_kind":"pith_short_8","alias_value":"NFECBVGP","created_at":"2026-07-05T06:20:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NFECBVGPDSTGCLHGTEV5O6QDNK","target":"record","payload":{"canonical_record":{"source":{"id":"2305.16944","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T13:59:45Z","cross_cats_sorted":[],"title_canon_sha256":"e6b0b09327b599fa1c37207e8d66cba39d8d10830598d9689a57ed0d34f9986e","abstract_canon_sha256":"d4c2d1aff44d638aa77d196fcb8134ec566d102cf32b9e495a4ae2b34a9c8b72"},"schema_version":"1.0"},"canonical_sha256":"694820d4cf1ca6612ce6992bd77a036a8e0ea142477d813a224da2b032292240","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:44.400092Z","signature_b64":"yvPZPuSwrB1ixDbadUZB6IDh03dYYj7aaSRbwvkacL9tTNJSDm4zpTSEXFZrStF8faD3Mm4tI78uBBAqUTTODg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"694820d4cf1ca6612ce6992bd77a036a8e0ea142477d813a224da2b032292240","last_reissued_at":"2026-07-05T06:20:44.399614Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:44.399614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.16944","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:20:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"piTvIFNgNbt5O5zK1hGDH58bB9rMcRtkVVsv9BJJ2DmRa3nLk91Zf64J+ylsHV+9wUBmtrGl9g4JsHBAf1w0Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T06:38:23.235385Z"},"content_sha256":"20ae3afdff337f186321d2d9578009471371a6fe76f481fa60a9a1713f9b7637","schema_version":"1.0","event_id":"sha256:20ae3afdff337f186321d2d9578009471371a6fe76f481fa60a9a1713f9b7637"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NFECBVGPDSTGCLHGTEV5O6QDNK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Imagine: Visually-Augmented Natural Language Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ji-Rong Wen, Junyi Li, Tianyi Tang, Wayne Xin Zhao, Yifan Du, Yushuo Chen","submitted_at":"2023-05-26T13:59:45Z","abstract_excerpt":"People often imagine relevant scenes to aid in the writing process. In this work, we aim to utilize visual information for composition in the same manner as humans. We propose a method, LIVE, that makes pre-trained language models (PLMs) Learn to Imagine for Visuallyaugmented natural language gEneration. First, we imagine the scene based on the text: we use a diffusion model to synthesize high-quality images conditioned on the input texts. Second, we use CLIP to determine whether the text can evoke the imagination in a posterior way. Finally, our imagination is dynamic, and we conduct synthesi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16944","kind":"arxiv","version":3},"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/2305.16944/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":"2026-07-05T06:20:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZtZaNoGIngtgilK7dKECsyrk/BvfSVF739teWedaIz3S6GftVvKPrAZCotNq5ZNpqmB+AdSOlGctK2bV9vhvDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T06:38:23.235939Z"},"content_sha256":"62718b70cc25fe30644f4b093b6137ded14f61089fc6c601e78d585c070112ba","schema_version":"1.0","event_id":"sha256:62718b70cc25fe30644f4b093b6137ded14f61089fc6c601e78d585c070112ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NFECBVGPDSTGCLHGTEV5O6QDNK/bundle.json","state_url":"https://pith.science/pith/NFECBVGPDSTGCLHGTEV5O6QDNK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NFECBVGPDSTGCLHGTEV5O6QDNK/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":"2026-08-15T06:38:23Z","links":{"resolver":"https://pith.science/pith/NFECBVGPDSTGCLHGTEV5O6QDNK","bundle":"https://pith.science/pith/NFECBVGPDSTGCLHGTEV5O6QDNK/bundle.json","state":"https://pith.science/pith/NFECBVGPDSTGCLHGTEV5O6QDNK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NFECBVGPDSTGCLHGTEV5O6QDNK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NFECBVGPDSTGCLHGTEV5O6QDNK","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":"d4c2d1aff44d638aa77d196fcb8134ec566d102cf32b9e495a4ae2b34a9c8b72","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T13:59:45Z","title_canon_sha256":"e6b0b09327b599fa1c37207e8d66cba39d8d10830598d9689a57ed0d34f9986e"},"schema_version":"1.0","source":{"id":"2305.16944","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16944","created_at":"2026-07-05T06:20:44Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16944v3","created_at":"2026-07-05T06:20:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16944","created_at":"2026-07-05T06:20:44Z"},{"alias_kind":"pith_short_12","alias_value":"NFECBVGPDSTG","created_at":"2026-07-05T06:20:44Z"},{"alias_kind":"pith_short_16","alias_value":"NFECBVGPDSTGCLHG","created_at":"2026-07-05T06:20:44Z"},{"alias_kind":"pith_short_8","alias_value":"NFECBVGP","created_at":"2026-07-05T06:20:44Z"}],"graph_snapshots":[{"event_id":"sha256:62718b70cc25fe30644f4b093b6137ded14f61089fc6c601e78d585c070112ba","target":"graph","created_at":"2026-07-05T06:20:44Z","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/2305.16944/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"People often imagine relevant scenes to aid in the writing process. In this work, we aim to utilize visual information for composition in the same manner as humans. We propose a method, LIVE, that makes pre-trained language models (PLMs) Learn to Imagine for Visuallyaugmented natural language gEneration. First, we imagine the scene based on the text: we use a diffusion model to synthesize high-quality images conditioned on the input texts. Second, we use CLIP to determine whether the text can evoke the imagination in a posterior way. Finally, our imagination is dynamic, and we conduct synthesi","authors_text":"Ji-Rong Wen, Junyi Li, Tianyi Tang, Wayne Xin Zhao, Yifan Du, Yushuo Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T13:59:45Z","title":"Learning to Imagine: Visually-Augmented Natural Language Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16944","kind":"arxiv","version":3},"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":"sha256:20ae3afdff337f186321d2d9578009471371a6fe76f481fa60a9a1713f9b7637","target":"record","created_at":"2026-07-05T06:20:44Z","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":"d4c2d1aff44d638aa77d196fcb8134ec566d102cf32b9e495a4ae2b34a9c8b72","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T13:59:45Z","title_canon_sha256":"e6b0b09327b599fa1c37207e8d66cba39d8d10830598d9689a57ed0d34f9986e"},"schema_version":"1.0","source":{"id":"2305.16944","kind":"arxiv","version":3}},"canonical_sha256":"694820d4cf1ca6612ce6992bd77a036a8e0ea142477d813a224da2b032292240","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"694820d4cf1ca6612ce6992bd77a036a8e0ea142477d813a224da2b032292240","first_computed_at":"2026-07-05T06:20:44.399614Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:20:44.399614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yvPZPuSwrB1ixDbadUZB6IDh03dYYj7aaSRbwvkacL9tTNJSDm4zpTSEXFZrStF8faD3Mm4tI78uBBAqUTTODg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:20:44.400092Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.16944","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20ae3afdff337f186321d2d9578009471371a6fe76f481fa60a9a1713f9b7637","sha256:62718b70cc25fe30644f4b093b6137ded14f61089fc6c601e78d585c070112ba"],"state_sha256":"c1b8b523febc13e7a832abd4b8ac88b6cf8f7bcbcff0f1a90658f1a7c8090ace"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"phyZh4RZcZMMqjHlhGgHU5X1b66xXGHwRpwsw69+dH3IrHGuvLgP8UG/5LUbZu1FZypTNtFD/PKun5ruFz0kDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T06:38:23.240048Z","bundle_sha256":"d2bfd7ebd5ffc5a17eea58731f5e8977749c8325b6207d6cef19ae5741491794"}}