{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TIDACNHJGVD5ZXO4WCHDSWO5NW","short_pith_number":"pith:TIDACNHJ","canonical_record":{"source":{"id":"2311.00618","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-01T16:12:40Z","cross_cats_sorted":[],"title_canon_sha256":"423f63ed20d9ec96d0ff425e6c8ac71f3cfec53ee558d52bf8e518d69b920fc2","abstract_canon_sha256":"472b2c05e674e840fab54c96cfd84b86531cddce61588726a80cc1a7de2fb3fc"},"schema_version":"1.0"},"canonical_sha256":"9a060134e93547dcdddcb08e3959dd6d8870686aa78a64e14e9a4aa48f58d7c0","source":{"kind":"arxiv","id":"2311.00618","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00618","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00618v1","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00618","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"pith_short_12","alias_value":"TIDACNHJGVD5","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"pith_short_16","alias_value":"TIDACNHJGVD5ZXO4","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"pith_short_8","alias_value":"TIDACNHJ","created_at":"2026-07-05T07:08:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TIDACNHJGVD5ZXO4WCHDSWO5NW","target":"record","payload":{"canonical_record":{"source":{"id":"2311.00618","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-01T16:12:40Z","cross_cats_sorted":[],"title_canon_sha256":"423f63ed20d9ec96d0ff425e6c8ac71f3cfec53ee558d52bf8e518d69b920fc2","abstract_canon_sha256":"472b2c05e674e840fab54c96cfd84b86531cddce61588726a80cc1a7de2fb3fc"},"schema_version":"1.0"},"canonical_sha256":"9a060134e93547dcdddcb08e3959dd6d8870686aa78a64e14e9a4aa48f58d7c0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:01.007453Z","signature_b64":"FvOYoXzA5KxsVrOfVDrsX5IoF+FC6bOKZI+kawPNugNIT6+N9SSDsA0fxtDXrVB3rkFq8kpPJtH5Vl2k5JU+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a060134e93547dcdddcb08e3959dd6d8870686aa78a64e14e9a4aa48f58d7c0","last_reissued_at":"2026-07-05T07:08:01.006855Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:01.006855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.00618","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":"2026-07-05T07:08:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ybjq3Z6DkZkXPLlnAjzVEuksolzoHWN0qMfrussEbi/qkIVVOXshzWJkjLo5ljI7POACoo6HXL2RlUEJrtiKBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T14:18:13.891955Z"},"content_sha256":"bbf4223f55d4ad9066223f0fa977ba62e50116d01dd0ed9d753a3153e40cfd0b","schema_version":"1.0","event_id":"sha256:bbf4223f55d4ad9066223f0fa977ba62e50116d01dd0ed9d753a3153e40cfd0b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TIDACNHJGVD5ZXO4WCHDSWO5NW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"De-Diffusion Makes Text a Strong Cross-Modal Interface","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Chen Wei, Chenxi Liu, Jiahui Yu, Siyuan Qiao, Zhishuai Zhang","submitted_at":"2023-11-01T16:12:40Z","abstract_excerpt":"We demonstrate text as a strong cross-modal interface. Rather than relying on deep embeddings to connect image and language as the interface representation, our approach represents an image as text, from which we enjoy the interpretability and flexibility inherent to natural language. We employ an autoencoder that uses a pre-trained text-to-image diffusion model for decoding. The encoder is trained to transform an input image into text, which is then fed into the fixed text-to-image diffusion decoder to reconstruct the original input -- a process we term De-Diffusion. Experiments validate both"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00618","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/2311.00618/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":"2026-07-05T07:08:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JEctpqByMlEhFjACeMMB0ulOCVREOsF4I1uQcLb6EpfV8QhybnDq1cbzhPalVAnFI8Q4zB6Qb3I9NUXKtZV0AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T14:18:13.892480Z"},"content_sha256":"210305be6b88a4de6bb4624a067a9dcbd3ec0806ee253b2ee30ed4ba8b2489ab","schema_version":"1.0","event_id":"sha256:210305be6b88a4de6bb4624a067a9dcbd3ec0806ee253b2ee30ed4ba8b2489ab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TIDACNHJGVD5ZXO4WCHDSWO5NW/bundle.json","state_url":"https://pith.science/pith/TIDACNHJGVD5ZXO4WCHDSWO5NW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TIDACNHJGVD5ZXO4WCHDSWO5NW/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":"2026-07-31T14:18:13Z","links":{"resolver":"https://pith.science/pith/TIDACNHJGVD5ZXO4WCHDSWO5NW","bundle":"https://pith.science/pith/TIDACNHJGVD5ZXO4WCHDSWO5NW/bundle.json","state":"https://pith.science/pith/TIDACNHJGVD5ZXO4WCHDSWO5NW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TIDACNHJGVD5ZXO4WCHDSWO5NW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TIDACNHJGVD5ZXO4WCHDSWO5NW","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":"472b2c05e674e840fab54c96cfd84b86531cddce61588726a80cc1a7de2fb3fc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-01T16:12:40Z","title_canon_sha256":"423f63ed20d9ec96d0ff425e6c8ac71f3cfec53ee558d52bf8e518d69b920fc2"},"schema_version":"1.0","source":{"id":"2311.00618","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00618","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00618v1","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00618","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"pith_short_12","alias_value":"TIDACNHJGVD5","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"pith_short_16","alias_value":"TIDACNHJGVD5ZXO4","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"pith_short_8","alias_value":"TIDACNHJ","created_at":"2026-07-05T07:08:01Z"}],"graph_snapshots":[{"event_id":"sha256:210305be6b88a4de6bb4624a067a9dcbd3ec0806ee253b2ee30ed4ba8b2489ab","target":"graph","created_at":"2026-07-05T07:08:01Z","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/2311.00618/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We demonstrate text as a strong cross-modal interface. Rather than relying on deep embeddings to connect image and language as the interface representation, our approach represents an image as text, from which we enjoy the interpretability and flexibility inherent to natural language. We employ an autoencoder that uses a pre-trained text-to-image diffusion model for decoding. The encoder is trained to transform an input image into text, which is then fed into the fixed text-to-image diffusion decoder to reconstruct the original input -- a process we term De-Diffusion. Experiments validate both","authors_text":"Alan Yuille, Chen Wei, Chenxi Liu, Jiahui Yu, Siyuan Qiao, Zhishuai Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-01T16:12:40Z","title":"De-Diffusion Makes Text a Strong Cross-Modal Interface"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00618","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:bbf4223f55d4ad9066223f0fa977ba62e50116d01dd0ed9d753a3153e40cfd0b","target":"record","created_at":"2026-07-05T07:08:01Z","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":"472b2c05e674e840fab54c96cfd84b86531cddce61588726a80cc1a7de2fb3fc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-01T16:12:40Z","title_canon_sha256":"423f63ed20d9ec96d0ff425e6c8ac71f3cfec53ee558d52bf8e518d69b920fc2"},"schema_version":"1.0","source":{"id":"2311.00618","kind":"arxiv","version":1}},"canonical_sha256":"9a060134e93547dcdddcb08e3959dd6d8870686aa78a64e14e9a4aa48f58d7c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a060134e93547dcdddcb08e3959dd6d8870686aa78a64e14e9a4aa48f58d7c0","first_computed_at":"2026-07-05T07:08:01.006855Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:08:01.006855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FvOYoXzA5KxsVrOfVDrsX5IoF+FC6bOKZI+kawPNugNIT6+N9SSDsA0fxtDXrVB3rkFq8kpPJtH5Vl2k5JU+Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:08:01.007453Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.00618","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbf4223f55d4ad9066223f0fa977ba62e50116d01dd0ed9d753a3153e40cfd0b","sha256:210305be6b88a4de6bb4624a067a9dcbd3ec0806ee253b2ee30ed4ba8b2489ab"],"state_sha256":"9cf80a85dbfd9d07b0690dcdde6117d69e31ce9616942e4ba4a2f58baa623786"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TGjPiNRnVgoHOv2hVTbIn+qUxkuj7NFm9AglfeB4kxJnlT2b2wOSbOkSoTifj46Q7IMKZP8ypawpBTeaPbVtDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T14:18:13.898826Z","bundle_sha256":"0fbb549b9c4d0e0bae1f3fd03b999986d3f827ef7903635b9d2c35b318c71954"}}