{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UV4TBWPUMDRUUYBOY4VBFH27CQ","short_pith_number":"pith:UV4TBWPU","canonical_record":{"source":{"id":"2412.12627","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T07:41:23Z","cross_cats_sorted":[],"title_canon_sha256":"7be6b2a7e250eaa0ce20fddede7368cd2c572271243c5cc80995ea80a3e4b494","abstract_canon_sha256":"80dba13204de16b33f659c9eb691e1a7adc1554e2bc6794bb6a9abcaa382b6e5"},"schema_version":"1.0"},"canonical_sha256":"a57930d9f460e34a602ec72a129f5f142bf78954f5f1f914f1f5ac803cc9d9bc","source":{"kind":"arxiv","id":"2412.12627","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12627","created_at":"2026-07-05T09:56:57Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12627v2","created_at":"2026-07-05T09:56:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12627","created_at":"2026-07-05T09:56:57Z"},{"alias_kind":"pith_short_12","alias_value":"UV4TBWPUMDRU","created_at":"2026-07-05T09:56:57Z"},{"alias_kind":"pith_short_16","alias_value":"UV4TBWPUMDRUUYBO","created_at":"2026-07-05T09:56:57Z"},{"alias_kind":"pith_short_8","alias_value":"UV4TBWPU","created_at":"2026-07-05T09:56:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UV4TBWPUMDRUUYBOY4VBFH27CQ","target":"record","payload":{"canonical_record":{"source":{"id":"2412.12627","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T07:41:23Z","cross_cats_sorted":[],"title_canon_sha256":"7be6b2a7e250eaa0ce20fddede7368cd2c572271243c5cc80995ea80a3e4b494","abstract_canon_sha256":"80dba13204de16b33f659c9eb691e1a7adc1554e2bc6794bb6a9abcaa382b6e5"},"schema_version":"1.0"},"canonical_sha256":"a57930d9f460e34a602ec72a129f5f142bf78954f5f1f914f1f5ac803cc9d9bc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:57.824297Z","signature_b64":"WgUMsALXA+E1Bmqn2lTGAmaCN0KFR3vITSIsSg+M2wXGNAyoZ+a+aH1Kom39ESXUJ86hJrBOOYHetyB2zLFTBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a57930d9f460e34a602ec72a129f5f142bf78954f5f1f914f1f5ac803cc9d9bc","last_reissued_at":"2026-07-05T09:56:57.823877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:57.823877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.12627","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:56:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YvYk0nHx1LV5/yow88AoTmWdNP3ZRrzPjrZXKsuXKDPEym11+QASXgigE8hz/1lwDb83hwtDCAlu047zcWgyAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T13:52:21.414780Z"},"content_sha256":"a97563bc2b75660c39782683a7594e167dc6e88713af6b001113cc28a6460cf9","schema_version":"1.0","event_id":"sha256:a97563bc2b75660c39782683a7594e167dc6e88713af6b001113cc28a6460cf9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UV4TBWPUMDRUUYBOY4VBFH27CQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Make Imagination Clearer! Stable Diffusion-based Visual Imagination for Multimodal Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andong Chen, Kehai Chen, Min Zhang, Muyun Yang, Tiejun Zhao, Yuchen Song","submitted_at":"2024-12-17T07:41:23Z","abstract_excerpt":"Visual information has been introduced for enhancing machine translation (MT), and its effectiveness heavily relies on the availability of large amounts of bilingual parallel sentence pairs with manual image annotations. In this paper, we introduce a stable diffusion-based imagination network into a multimodal large language model (MLLM) to explicitly generate an image for each source sentence, thereby advancing the multimodel MT. Particularly, we build heuristic human feedback with reinforcement learning to ensure the consistency of the generated image with the source sentence without the sup"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12627","kind":"arxiv","version":2},"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/2412.12627/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":"2026-07-05T09:56:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q5yZvW1kq+g2eBns8cBypdq0wWda//otXE/9qHb1+e/uppg9qP1v3LlkRMCoIy7bUUiQHv1kaTPybiR2Iv+/Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T13:52:21.417912Z"},"content_sha256":"591b5b9be08603946d40eefa146bd39068804c5ab4c444ad937ff2f75bb7af94","schema_version":"1.0","event_id":"sha256:591b5b9be08603946d40eefa146bd39068804c5ab4c444ad937ff2f75bb7af94"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UV4TBWPUMDRUUYBOY4VBFH27CQ/bundle.json","state_url":"https://pith.science/pith/UV4TBWPUMDRUUYBOY4VBFH27CQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UV4TBWPUMDRUUYBOY4VBFH27CQ/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":"2026-08-13T13:52:21Z","links":{"resolver":"https://pith.science/pith/UV4TBWPUMDRUUYBOY4VBFH27CQ","bundle":"https://pith.science/pith/UV4TBWPUMDRUUYBOY4VBFH27CQ/bundle.json","state":"https://pith.science/pith/UV4TBWPUMDRUUYBOY4VBFH27CQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UV4TBWPUMDRUUYBOY4VBFH27CQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UV4TBWPUMDRUUYBOY4VBFH27CQ","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":"80dba13204de16b33f659c9eb691e1a7adc1554e2bc6794bb6a9abcaa382b6e5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T07:41:23Z","title_canon_sha256":"7be6b2a7e250eaa0ce20fddede7368cd2c572271243c5cc80995ea80a3e4b494"},"schema_version":"1.0","source":{"id":"2412.12627","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12627","created_at":"2026-07-05T09:56:57Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12627v2","created_at":"2026-07-05T09:56:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12627","created_at":"2026-07-05T09:56:57Z"},{"alias_kind":"pith_short_12","alias_value":"UV4TBWPUMDRU","created_at":"2026-07-05T09:56:57Z"},{"alias_kind":"pith_short_16","alias_value":"UV4TBWPUMDRUUYBO","created_at":"2026-07-05T09:56:57Z"},{"alias_kind":"pith_short_8","alias_value":"UV4TBWPU","created_at":"2026-07-05T09:56:57Z"}],"graph_snapshots":[{"event_id":"sha256:591b5b9be08603946d40eefa146bd39068804c5ab4c444ad937ff2f75bb7af94","target":"graph","created_at":"2026-07-05T09:56:57Z","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/2412.12627/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual information has been introduced for enhancing machine translation (MT), and its effectiveness heavily relies on the availability of large amounts of bilingual parallel sentence pairs with manual image annotations. In this paper, we introduce a stable diffusion-based imagination network into a multimodal large language model (MLLM) to explicitly generate an image for each source sentence, thereby advancing the multimodel MT. Particularly, we build heuristic human feedback with reinforcement learning to ensure the consistency of the generated image with the source sentence without the sup","authors_text":"Andong Chen, Kehai Chen, Min Zhang, Muyun Yang, Tiejun Zhao, Yuchen Song","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T07:41:23Z","title":"Make Imagination Clearer! Stable Diffusion-based Visual Imagination for Multimodal Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12627","kind":"arxiv","version":2},"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:a97563bc2b75660c39782683a7594e167dc6e88713af6b001113cc28a6460cf9","target":"record","created_at":"2026-07-05T09:56:57Z","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":"80dba13204de16b33f659c9eb691e1a7adc1554e2bc6794bb6a9abcaa382b6e5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T07:41:23Z","title_canon_sha256":"7be6b2a7e250eaa0ce20fddede7368cd2c572271243c5cc80995ea80a3e4b494"},"schema_version":"1.0","source":{"id":"2412.12627","kind":"arxiv","version":2}},"canonical_sha256":"a57930d9f460e34a602ec72a129f5f142bf78954f5f1f914f1f5ac803cc9d9bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a57930d9f460e34a602ec72a129f5f142bf78954f5f1f914f1f5ac803cc9d9bc","first_computed_at":"2026-07-05T09:56:57.823877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:57.823877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WgUMsALXA+E1Bmqn2lTGAmaCN0KFR3vITSIsSg+M2wXGNAyoZ+a+aH1Kom39ESXUJ86hJrBOOYHetyB2zLFTBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:57.824297Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.12627","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a97563bc2b75660c39782683a7594e167dc6e88713af6b001113cc28a6460cf9","sha256:591b5b9be08603946d40eefa146bd39068804c5ab4c444ad937ff2f75bb7af94"],"state_sha256":"d25e3f8a37329c22b859f90dc77dc88497cdb675021db64cc48388998d4d8da8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MLfgJV0zFhet+a6Tc6oZX/0AwVYXxDZs8n3uxWOsftGH3+S2Fp5B67pnsW+45zu+5hcisDkdSKyDwrqOpetnBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T13:52:21.491362Z","bundle_sha256":"600a40fd6cade82fc07c021f0f4b5495c8c1b28beaeb113be3426bd8a73710ba"}}