{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:7V4O3JDVVEXDL74AFCZX2VJ7B7","short_pith_number":"pith:7V4O3JDV","canonical_record":{"source":{"id":"2103.11186","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-20T14:12:13Z","cross_cats_sorted":[],"title_canon_sha256":"fac9e63472622b597d044925a54ee1a9b0722e6d7e778f6fdad387066a47dccc","abstract_canon_sha256":"9141d583b207c502db87b9fe8b65a2c9a3bce1feef50deaf2f9a8ea6bc607dc3"},"schema_version":"1.0"},"canonical_sha256":"fd78eda475a92e35ff8028b37d553f0fea0cb951b4e0ddbe61a38fdae7705856","source":{"kind":"arxiv","id":"2103.11186","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.11186","created_at":"2026-07-05T02:24:57Z"},{"alias_kind":"arxiv_version","alias_value":"2103.11186v1","created_at":"2026-07-05T02:24:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.11186","created_at":"2026-07-05T02:24:57Z"},{"alias_kind":"pith_short_12","alias_value":"7V4O3JDVVEXD","created_at":"2026-07-05T02:24:57Z"},{"alias_kind":"pith_short_16","alias_value":"7V4O3JDVVEXDL74A","created_at":"2026-07-05T02:24:57Z"},{"alias_kind":"pith_short_8","alias_value":"7V4O3JDV","created_at":"2026-07-05T02:24:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:7V4O3JDVVEXDL74AFCZX2VJ7B7","target":"record","payload":{"canonical_record":{"source":{"id":"2103.11186","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-20T14:12:13Z","cross_cats_sorted":[],"title_canon_sha256":"fac9e63472622b597d044925a54ee1a9b0722e6d7e778f6fdad387066a47dccc","abstract_canon_sha256":"9141d583b207c502db87b9fe8b65a2c9a3bce1feef50deaf2f9a8ea6bc607dc3"},"schema_version":"1.0"},"canonical_sha256":"fd78eda475a92e35ff8028b37d553f0fea0cb951b4e0ddbe61a38fdae7705856","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:57.614887Z","signature_b64":"HbyIZtAWIbN+ExLRYN4U0nG97y6bq2KA3Q/N1vu20kumDAyl5q5ljfPb7xpr7TuZUy1zmS93Zsuiwy3t93JDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd78eda475a92e35ff8028b37d553f0fea0cb951b4e0ddbe61a38fdae7705856","last_reissued_at":"2026-07-05T02:24:57.614508Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:57.614508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.11186","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":"2026-07-05T02:24:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LXBK3cKpGWOlkg8uwRslrU2cWaMaUT1MQ+RW/Sc85nAwUKTJD8Xgb9UJC6lXIzLW/+oKftm/sFAiwV84Q594BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:14:25.718088Z"},"content_sha256":"5c22943580d5352a34337e23ae528669ffb8970b89d9bda464b108861eeabfac","schema_version":"1.0","event_id":"sha256:5c22943580d5352a34337e23ae528669ffb8970b89d9bda464b108861eeabfac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:7V4O3JDVVEXDL74AFCZX2VJ7B7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"3M: Multi-style image caption generation using Multi-modality features under Multi-UPDOWN model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Brent Harrison, Chengxi Li","submitted_at":"2021-03-20T14:12:13Z","abstract_excerpt":"In this paper, we build a multi-style generative model for stylish image captioning which uses multi-modality image features, ResNeXt features and text features generated by DenseCap. We propose the 3M model, a Multi-UPDOWN caption model that encodes multi-modality features and decode them to captions. We demonstrate the effectiveness of our model on generating human-like captions by examining its performance on two datasets, the PERSONALITY-CAPTIONS dataset and the FlickrStyle10K dataset. We compare against a variety of state-of-the-art baselines on various automatic NLP metrics such as BLEU,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.11186","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/2103.11186/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":"2026-07-05T02:24:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2DBwRPR5MVr+f29SgQBisWcV/i5g6CPKFx+MkLa4L1BUaoW3v1dCVHjkxxfH9r2wV9OlyPaFv0QTCz6Q/Zo3DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:14:25.718973Z"},"content_sha256":"5a3a11f2fb30068826abd9d1e113ed230f1a713619f6a5c244e35c780eb4ea1f","schema_version":"1.0","event_id":"sha256:5a3a11f2fb30068826abd9d1e113ed230f1a713619f6a5c244e35c780eb4ea1f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7V4O3JDVVEXDL74AFCZX2VJ7B7/bundle.json","state_url":"https://pith.science/pith/7V4O3JDVVEXDL74AFCZX2VJ7B7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7V4O3JDVVEXDL74AFCZX2VJ7B7/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":"2026-08-05T07:14:25Z","links":{"resolver":"https://pith.science/pith/7V4O3JDVVEXDL74AFCZX2VJ7B7","bundle":"https://pith.science/pith/7V4O3JDVVEXDL74AFCZX2VJ7B7/bundle.json","state":"https://pith.science/pith/7V4O3JDVVEXDL74AFCZX2VJ7B7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7V4O3JDVVEXDL74AFCZX2VJ7B7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:7V4O3JDVVEXDL74AFCZX2VJ7B7","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":"9141d583b207c502db87b9fe8b65a2c9a3bce1feef50deaf2f9a8ea6bc607dc3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-20T14:12:13Z","title_canon_sha256":"fac9e63472622b597d044925a54ee1a9b0722e6d7e778f6fdad387066a47dccc"},"schema_version":"1.0","source":{"id":"2103.11186","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.11186","created_at":"2026-07-05T02:24:57Z"},{"alias_kind":"arxiv_version","alias_value":"2103.11186v1","created_at":"2026-07-05T02:24:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.11186","created_at":"2026-07-05T02:24:57Z"},{"alias_kind":"pith_short_12","alias_value":"7V4O3JDVVEXD","created_at":"2026-07-05T02:24:57Z"},{"alias_kind":"pith_short_16","alias_value":"7V4O3JDVVEXDL74A","created_at":"2026-07-05T02:24:57Z"},{"alias_kind":"pith_short_8","alias_value":"7V4O3JDV","created_at":"2026-07-05T02:24:57Z"}],"graph_snapshots":[{"event_id":"sha256:5a3a11f2fb30068826abd9d1e113ed230f1a713619f6a5c244e35c780eb4ea1f","target":"graph","created_at":"2026-07-05T02:24:57Z","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/2103.11186/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we build a multi-style generative model for stylish image captioning which uses multi-modality image features, ResNeXt features and text features generated by DenseCap. We propose the 3M model, a Multi-UPDOWN caption model that encodes multi-modality features and decode them to captions. We demonstrate the effectiveness of our model on generating human-like captions by examining its performance on two datasets, the PERSONALITY-CAPTIONS dataset and the FlickrStyle10K dataset. We compare against a variety of state-of-the-art baselines on various automatic NLP metrics such as BLEU,","authors_text":"Brent Harrison, Chengxi Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-20T14:12:13Z","title":"3M: Multi-style image caption generation using Multi-modality features under Multi-UPDOWN model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.11186","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":"sha256:5c22943580d5352a34337e23ae528669ffb8970b89d9bda464b108861eeabfac","target":"record","created_at":"2026-07-05T02:24:57Z","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":"9141d583b207c502db87b9fe8b65a2c9a3bce1feef50deaf2f9a8ea6bc607dc3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-20T14:12:13Z","title_canon_sha256":"fac9e63472622b597d044925a54ee1a9b0722e6d7e778f6fdad387066a47dccc"},"schema_version":"1.0","source":{"id":"2103.11186","kind":"arxiv","version":1}},"canonical_sha256":"fd78eda475a92e35ff8028b37d553f0fea0cb951b4e0ddbe61a38fdae7705856","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd78eda475a92e35ff8028b37d553f0fea0cb951b4e0ddbe61a38fdae7705856","first_computed_at":"2026-07-05T02:24:57.614508Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:24:57.614508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HbyIZtAWIbN+ExLRYN4U0nG97y6bq2KA3Q/N1vu20kumDAyl5q5ljfPb7xpr7TuZUy1zmS93Zsuiwy3t93JDDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:24:57.614887Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.11186","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c22943580d5352a34337e23ae528669ffb8970b89d9bda464b108861eeabfac","sha256:5a3a11f2fb30068826abd9d1e113ed230f1a713619f6a5c244e35c780eb4ea1f"],"state_sha256":"c74109b69b5d877b97d9e976fd94e988d3ae9d00880d093ef70326f2d79fc296"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kaXr7yJLI35TZPjSBWwaM69sbRWsC6NZopGvtQdrh7GuCD8t/QlJww164SpKzBKOw2SRmLZXLN5m2u4+v7KXAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T07:14:25.724178Z","bundle_sha256":"88ed931c5d29c0884d28794271cdf64d2b587270c8f720c43dd6a7717648ad11"}}