{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:HOBVZACRU3CLRY2UTJUIR3SLUF","short_pith_number":"pith:HOBVZACR","canonical_record":{"source":{"id":"1412.6632","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-20T08:10:04Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"8669324bcee42f1c72d59e71c13efd811e2451a8c20bef5bf15ef0581c7a0b8b","abstract_canon_sha256":"cb3dea41fd4a5371c6e6c098037e6f8dae5e8f1be6d4242aa8d4396a60c21934"},"schema_version":"1.0"},"canonical_sha256":"3b835c8051a6c4b8e3549a6888ee4ba16b27555378fb693cba16430154ead4ed","source":{"kind":"arxiv","id":"1412.6632","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.6632","created_at":"2026-05-18T01:53:08Z"},{"alias_kind":"arxiv_version","alias_value":"1412.6632v5","created_at":"2026-05-18T01:53:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.6632","created_at":"2026-05-18T01:53:08Z"},{"alias_kind":"pith_short_12","alias_value":"HOBVZACRU3CL","created_at":"2026-05-18T12:28:30Z"},{"alias_kind":"pith_short_16","alias_value":"HOBVZACRU3CLRY2U","created_at":"2026-05-18T12:28:30Z"},{"alias_kind":"pith_short_8","alias_value":"HOBVZACR","created_at":"2026-05-18T12:28:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:HOBVZACRU3CLRY2UTJUIR3SLUF","target":"record","payload":{"canonical_record":{"source":{"id":"1412.6632","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-20T08:10:04Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"8669324bcee42f1c72d59e71c13efd811e2451a8c20bef5bf15ef0581c7a0b8b","abstract_canon_sha256":"cb3dea41fd4a5371c6e6c098037e6f8dae5e8f1be6d4242aa8d4396a60c21934"},"schema_version":"1.0"},"canonical_sha256":"3b835c8051a6c4b8e3549a6888ee4ba16b27555378fb693cba16430154ead4ed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:53:08.976636Z","signature_b64":"jvAUfYgQyJ9cBvqpiOCU5YqZaxe5WYxf+Xe1PH+bOv3Aq8R/GRdqolX7VnCFDEzDm9ItJ76eM9S+bvZAYcz8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b835c8051a6c4b8e3549a6888ee4ba16b27555378fb693cba16430154ead4ed","last_reissued_at":"2026-05-18T01:53:08.976160Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:53:08.976160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1412.6632","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:53:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tv/hygRFYpvg7cCkKm4a1vhKtS87aMELCsI5rKAwld+GOVG/G21fdkYbWZaawU0l9TTOyGc42SFvMBWn0oKbCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T14:13:00.405407Z"},"content_sha256":"84e663da33709a889b6bc67b4e926f144370722a34fc41bc8216646fdb953922","schema_version":"1.0","event_id":"sha256:84e663da33709a889b6bc67b4e926f144370722a34fc41bc8216646fdb953922"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:HOBVZACRU3CLRY2UTJUIR3SLUF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Jiang Wang, Junhua Mao, Wei Xu, Yi Yang, Zhiheng Huang","submitted_at":"2014-12-20T08:10:04Z","abstract_excerpt":"In this paper, we present a multimodal Recurrent Neural Network (m-RNN) model for generating novel image captions. It directly models the probability distribution of generating a word given previous words and an image. Image captions are generated by sampling from this distribution. The model consists of two sub-networks: a deep recurrent neural network for sentences and a deep convolutional network for images. These two sub-networks interact with each other in a multimodal layer to form the whole m-RNN model. The effectiveness of our model is validated on four benchmark datasets (IAPR TC-12, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.6632","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T01:53:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zFQAjDXMJZx5YbstCCS9Nd69gXaD/eR5P75DRy0gtqPg2iqCy0xCml8xcHyMLFCIw4od/ceXVXGzrasdbv6LCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T14:13:00.405893Z"},"content_sha256":"bdee47647cd8d9797a923e0628c3c2e00011e305ff2bbcf0049e7572b882ca91","schema_version":"1.0","event_id":"sha256:bdee47647cd8d9797a923e0628c3c2e00011e305ff2bbcf0049e7572b882ca91"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HOBVZACRU3CLRY2UTJUIR3SLUF/bundle.json","state_url":"https://pith.science/pith/HOBVZACRU3CLRY2UTJUIR3SLUF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HOBVZACRU3CLRY2UTJUIR3SLUF/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":"2026-08-15T14:13:00Z","links":{"resolver":"https://pith.science/pith/HOBVZACRU3CLRY2UTJUIR3SLUF","bundle":"https://pith.science/pith/HOBVZACRU3CLRY2UTJUIR3SLUF/bundle.json","state":"https://pith.science/pith/HOBVZACRU3CLRY2UTJUIR3SLUF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HOBVZACRU3CLRY2UTJUIR3SLUF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:HOBVZACRU3CLRY2UTJUIR3SLUF","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":"cb3dea41fd4a5371c6e6c098037e6f8dae5e8f1be6d4242aa8d4396a60c21934","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-20T08:10:04Z","title_canon_sha256":"8669324bcee42f1c72d59e71c13efd811e2451a8c20bef5bf15ef0581c7a0b8b"},"schema_version":"1.0","source":{"id":"1412.6632","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.6632","created_at":"2026-05-18T01:53:08Z"},{"alias_kind":"arxiv_version","alias_value":"1412.6632v5","created_at":"2026-05-18T01:53:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.6632","created_at":"2026-05-18T01:53:08Z"},{"alias_kind":"pith_short_12","alias_value":"HOBVZACRU3CL","created_at":"2026-05-18T12:28:30Z"},{"alias_kind":"pith_short_16","alias_value":"HOBVZACRU3CLRY2U","created_at":"2026-05-18T12:28:30Z"},{"alias_kind":"pith_short_8","alias_value":"HOBVZACR","created_at":"2026-05-18T12:28:30Z"}],"graph_snapshots":[{"event_id":"sha256:bdee47647cd8d9797a923e0628c3c2e00011e305ff2bbcf0049e7572b882ca91","target":"graph","created_at":"2026-05-18T01:53:08Z","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"},"paper":{"abstract_excerpt":"In this paper, we present a multimodal Recurrent Neural Network (m-RNN) model for generating novel image captions. It directly models the probability distribution of generating a word given previous words and an image. Image captions are generated by sampling from this distribution. The model consists of two sub-networks: a deep recurrent neural network for sentences and a deep convolutional network for images. These two sub-networks interact with each other in a multimodal layer to form the whole m-RNN model. The effectiveness of our model is validated on four benchmark datasets (IAPR TC-12, ","authors_text":"Alan Yuille, Jiang Wang, Junhua Mao, Wei Xu, Yi Yang, Zhiheng Huang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-20T08:10:04Z","title":"Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.6632","kind":"arxiv","version":5},"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":"sha256:84e663da33709a889b6bc67b4e926f144370722a34fc41bc8216646fdb953922","target":"record","created_at":"2026-05-18T01:53:08Z","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":"cb3dea41fd4a5371c6e6c098037e6f8dae5e8f1be6d4242aa8d4396a60c21934","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-20T08:10:04Z","title_canon_sha256":"8669324bcee42f1c72d59e71c13efd811e2451a8c20bef5bf15ef0581c7a0b8b"},"schema_version":"1.0","source":{"id":"1412.6632","kind":"arxiv","version":5}},"canonical_sha256":"3b835c8051a6c4b8e3549a6888ee4ba16b27555378fb693cba16430154ead4ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b835c8051a6c4b8e3549a6888ee4ba16b27555378fb693cba16430154ead4ed","first_computed_at":"2026-05-18T01:53:08.976160Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:53:08.976160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jvAUfYgQyJ9cBvqpiOCU5YqZaxe5WYxf+Xe1PH+bOv3Aq8R/GRdqolX7VnCFDEzDm9ItJ76eM9S+bvZAYcz8DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:53:08.976636Z","signed_message":"canonical_sha256_bytes"},"source_id":"1412.6632","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84e663da33709a889b6bc67b4e926f144370722a34fc41bc8216646fdb953922","sha256:bdee47647cd8d9797a923e0628c3c2e00011e305ff2bbcf0049e7572b882ca91"],"state_sha256":"19a17c2a0e57794b6f5af622f76f49790a27e85809ae3e40d2e817eac4acf20f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L8ccZtg6UOtAJDgJA/H2lqcelPAbej9V97NzJWvMNNLmDAb5ZL34LZ2n00HAZvA09GQIsC2PKUMunp4KxhPcAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T14:13:00.411607Z","bundle_sha256":"4368b5aff3dd585d15efdd3c8f9818906cc918dfa2e57cf60b5136f5e28df2d8"}}