{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DDNP4GZ6C4SKXQPXOAJGCSBB5E","short_pith_number":"pith:DDNP4GZ6","canonical_record":{"source":{"id":"2305.02177","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-03T15:18:37Z","cross_cats_sorted":[],"title_canon_sha256":"3c4b1521b017a0ce1b0d9d683c6d09cb025a0262b09ca256b5fadda44688a180","abstract_canon_sha256":"f9b33df0fad7d98a273c5c9c9b5f4b4472ddfc046b54544e24291bbb76a0a4ed"},"schema_version":"1.0"},"canonical_sha256":"18dafe1b3e1724abc1f77012614821e92725f25ea5b00f6b96eefada6d5bdcdf","source":{"kind":"arxiv","id":"2305.02177","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.02177","created_at":"2026-07-05T07:22:17Z"},{"alias_kind":"arxiv_version","alias_value":"2305.02177v4","created_at":"2026-07-05T07:22:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.02177","created_at":"2026-07-05T07:22:17Z"},{"alias_kind":"pith_short_12","alias_value":"DDNP4GZ6C4SK","created_at":"2026-07-05T07:22:17Z"},{"alias_kind":"pith_short_16","alias_value":"DDNP4GZ6C4SKXQPX","created_at":"2026-07-05T07:22:17Z"},{"alias_kind":"pith_short_8","alias_value":"DDNP4GZ6","created_at":"2026-07-05T07:22:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DDNP4GZ6C4SKXQPXOAJGCSBB5E","target":"record","payload":{"canonical_record":{"source":{"id":"2305.02177","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-03T15:18:37Z","cross_cats_sorted":[],"title_canon_sha256":"3c4b1521b017a0ce1b0d9d683c6d09cb025a0262b09ca256b5fadda44688a180","abstract_canon_sha256":"f9b33df0fad7d98a273c5c9c9b5f4b4472ddfc046b54544e24291bbb76a0a4ed"},"schema_version":"1.0"},"canonical_sha256":"18dafe1b3e1724abc1f77012614821e92725f25ea5b00f6b96eefada6d5bdcdf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:17.407096Z","signature_b64":"HZ/2PJVqG1HbZ5d7IpF8kz/ftp+eWz9gt1LKhJZbFFJcws7JapFmuCfnBTzs9qhz/LBCZWcprXaFHIUvUmElBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18dafe1b3e1724abc1f77012614821e92725f25ea5b00f6b96eefada6d5bdcdf","last_reissued_at":"2026-07-05T07:22:17.406587Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:17.406587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.02177","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:22:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WdEfVmMJui0NIY5pVCV22UOyx8DQC/hjbS8rppeLHxw6eezKOoWKV8r4HpsfJ0BTB4kdryZcoRUWG1LEQHh6Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:24:03.473823Z"},"content_sha256":"d0b34fe9b2cf9f3bebfcd75e036575d74115a269521e99a1106174774c2d0926","schema_version":"1.0","event_id":"sha256:d0b34fe9b2cf9f3bebfcd75e036575d74115a269521e99a1106174774c2d0926"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DDNP4GZ6C4SKXQPXOAJGCSBB5E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transforming Visual Scene Graphs to Image Captions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenliang Li, Fei Huang, Haiyang Xu, Jiawei Peng, Qinghao Ye, Songfang Huang, Xu Yang, Yu Zhang, Zhangzikang Li, Zihua Wang","submitted_at":"2023-05-03T15:18:37Z","abstract_excerpt":"We propose to Transform Scene Graphs (TSG) into more descriptive captions. In TSG, we apply multi-head attention (MHA) to design the Graph Neural Network (GNN) for embedding scene graphs. After embedding, different graph embeddings contain diverse specific knowledge for generating the words with different part-of-speech, e.g., object/attribute embedding is good for generating nouns/adjectives. Motivated by this, we design a Mixture-of-Expert (MOE)-based decoder, where each expert is built on MHA, for discriminating the graph embeddings to generate different kinds of words. Since both the encod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.02177","kind":"arxiv","version":4},"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/2305.02177/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":"2026-07-05T07:22:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ENojmHhD53mq/M5wYUGfy0A3FeLE6yA2tfVZoOCMc79GbHipl5PKNC0Mwae2fVG8f/Wl81IZIWDDl/gknTxdCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:24:03.474336Z"},"content_sha256":"49b0c24e311e08e07055570ee24643613646c9abc62eab145ed37e9ee37bd92c","schema_version":"1.0","event_id":"sha256:49b0c24e311e08e07055570ee24643613646c9abc62eab145ed37e9ee37bd92c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DDNP4GZ6C4SKXQPXOAJGCSBB5E/bundle.json","state_url":"https://pith.science/pith/DDNP4GZ6C4SKXQPXOAJGCSBB5E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DDNP4GZ6C4SKXQPXOAJGCSBB5E/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":"2026-08-14T19:24:03Z","links":{"resolver":"https://pith.science/pith/DDNP4GZ6C4SKXQPXOAJGCSBB5E","bundle":"https://pith.science/pith/DDNP4GZ6C4SKXQPXOAJGCSBB5E/bundle.json","state":"https://pith.science/pith/DDNP4GZ6C4SKXQPXOAJGCSBB5E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DDNP4GZ6C4SKXQPXOAJGCSBB5E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DDNP4GZ6C4SKXQPXOAJGCSBB5E","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":"f9b33df0fad7d98a273c5c9c9b5f4b4472ddfc046b54544e24291bbb76a0a4ed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-03T15:18:37Z","title_canon_sha256":"3c4b1521b017a0ce1b0d9d683c6d09cb025a0262b09ca256b5fadda44688a180"},"schema_version":"1.0","source":{"id":"2305.02177","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.02177","created_at":"2026-07-05T07:22:17Z"},{"alias_kind":"arxiv_version","alias_value":"2305.02177v4","created_at":"2026-07-05T07:22:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.02177","created_at":"2026-07-05T07:22:17Z"},{"alias_kind":"pith_short_12","alias_value":"DDNP4GZ6C4SK","created_at":"2026-07-05T07:22:17Z"},{"alias_kind":"pith_short_16","alias_value":"DDNP4GZ6C4SKXQPX","created_at":"2026-07-05T07:22:17Z"},{"alias_kind":"pith_short_8","alias_value":"DDNP4GZ6","created_at":"2026-07-05T07:22:17Z"}],"graph_snapshots":[{"event_id":"sha256:49b0c24e311e08e07055570ee24643613646c9abc62eab145ed37e9ee37bd92c","target":"graph","created_at":"2026-07-05T07:22:17Z","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/2305.02177/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose to Transform Scene Graphs (TSG) into more descriptive captions. In TSG, we apply multi-head attention (MHA) to design the Graph Neural Network (GNN) for embedding scene graphs. After embedding, different graph embeddings contain diverse specific knowledge for generating the words with different part-of-speech, e.g., object/attribute embedding is good for generating nouns/adjectives. Motivated by this, we design a Mixture-of-Expert (MOE)-based decoder, where each expert is built on MHA, for discriminating the graph embeddings to generate different kinds of words. Since both the encod","authors_text":"Chenliang Li, Fei Huang, Haiyang Xu, Jiawei Peng, Qinghao Ye, Songfang Huang, Xu Yang, Yu Zhang, Zhangzikang Li, Zihua Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-03T15:18:37Z","title":"Transforming Visual Scene Graphs to Image Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.02177","kind":"arxiv","version":4},"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:d0b34fe9b2cf9f3bebfcd75e036575d74115a269521e99a1106174774c2d0926","target":"record","created_at":"2026-07-05T07:22:17Z","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":"f9b33df0fad7d98a273c5c9c9b5f4b4472ddfc046b54544e24291bbb76a0a4ed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-03T15:18:37Z","title_canon_sha256":"3c4b1521b017a0ce1b0d9d683c6d09cb025a0262b09ca256b5fadda44688a180"},"schema_version":"1.0","source":{"id":"2305.02177","kind":"arxiv","version":4}},"canonical_sha256":"18dafe1b3e1724abc1f77012614821e92725f25ea5b00f6b96eefada6d5bdcdf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18dafe1b3e1724abc1f77012614821e92725f25ea5b00f6b96eefada6d5bdcdf","first_computed_at":"2026-07-05T07:22:17.406587Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:22:17.406587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HZ/2PJVqG1HbZ5d7IpF8kz/ftp+eWz9gt1LKhJZbFFJcws7JapFmuCfnBTzs9qhz/LBCZWcprXaFHIUvUmElBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:22:17.407096Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.02177","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d0b34fe9b2cf9f3bebfcd75e036575d74115a269521e99a1106174774c2d0926","sha256:49b0c24e311e08e07055570ee24643613646c9abc62eab145ed37e9ee37bd92c"],"state_sha256":"b27052006f6ca07065ebba7bb049fea22dce433e1667909558bfbd9a68e88c7f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JlWHWAJsFW9oHP3wKbRePWCMZ2PKpDtRCDW7xJXq5iVjwGx+bjKRdnM4TmQO4nP9AhDmlZR1bX4hYRk9n5sICw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T19:24:03.481355Z","bundle_sha256":"638c5874284c83c4e8c8d0b7ffdeb0e226d0adc81b5a77a02fc8242f34ee2806"}}