{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:ZYLUYRY73GECSGGLKDTAENWTTX","short_pith_number":"pith:ZYLUYRY7","canonical_record":{"source":{"id":"1505.01809","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-05-07T18:36:14Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"edabbfe26fd623706d88559ed43543b7fa54c061fbf631c16122160f845085bc","abstract_canon_sha256":"bc593555df9bd06191bc065176ca79890adf9b921d83634a6b791aee62528696"},"schema_version":"1.0"},"canonical_sha256":"ce174c471fd9882918cb50e60236d39dda1f12d77a9f321a7ab3485087a024b6","source":{"kind":"arxiv","id":"1505.01809","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1505.01809","created_at":"2026-05-18T01:30:07Z"},{"alias_kind":"arxiv_version","alias_value":"1505.01809v3","created_at":"2026-05-18T01:30:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.01809","created_at":"2026-05-18T01:30:07Z"},{"alias_kind":"pith_short_12","alias_value":"ZYLUYRY73GEC","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"ZYLUYRY73GECSGGL","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"ZYLUYRY7","created_at":"2026-05-18T12:29:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:ZYLUYRY73GECSGGLKDTAENWTTX","target":"record","payload":{"canonical_record":{"source":{"id":"1505.01809","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-05-07T18:36:14Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"edabbfe26fd623706d88559ed43543b7fa54c061fbf631c16122160f845085bc","abstract_canon_sha256":"bc593555df9bd06191bc065176ca79890adf9b921d83634a6b791aee62528696"},"schema_version":"1.0"},"canonical_sha256":"ce174c471fd9882918cb50e60236d39dda1f12d77a9f321a7ab3485087a024b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:30:07.982822Z","signature_b64":"XFGlf0uy0Am4FIbjbsGqz/I3oN9mAjkkTls8nXCNlIx3jmA+LNZAmMMlKtL/0xfWLiC7XrwHoDaR3hsgIAl5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce174c471fd9882918cb50e60236d39dda1f12d77a9f321a7ab3485087a024b6","last_reissued_at":"2026-05-18T01:30:07.982435Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:30:07.982435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1505.01809","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:30:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iCP1LDUlgmHAnp8n/SMNbqLbujyI3kinUpNv510gl3gfoDvzu9YWKPj6MPH19SI9PKtZj7FfhiuBa9XEYTFZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T12:00:35.655902Z"},"content_sha256":"cbbca4c58efdf56fe3385cfeaef3498abfe74ebb59e36920cf63fc1e84a23252","schema_version":"1.0","event_id":"sha256:cbbca4c58efdf56fe3385cfeaef3498abfe74ebb59e36920cf63fc1e84a23252"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:ZYLUYRY73GECSGGLKDTAENWTTX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language Models for Image Captioning: The Quirks and What Works","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Geoffrey Zweig, Hao Cheng, Hao Fang, Jacob Devlin, Li Deng, Margaret Mitchell, Saurabh Gupta, Xiaodong He","submitted_at":"2015-05-07T18:36:14Z","abstract_excerpt":"Two recent approaches have achieved state-of-the-art results in image captioning. The first uses a pipelined process where a set of candidate words is generated by a convolutional neural network (CNN) trained on images, and then a maximum entropy (ME) language model is used to arrange these words into a coherent sentence. The second uses the penultimate activation layer of the CNN as input to a recurrent neural network (RNN) that then generates the caption sequence. In this paper, we compare the merits of these different language modeling approaches for the first time by using the same state-o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.01809","kind":"arxiv","version":3},"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":"2026-05-18T01:30:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T+mrMN7k7pwgO/ZoHcuL5AfOq8hr3Ez2DfHBDQRFw49Pl2qHkzsBgDC2kb7GA/AWpL5PguGIvYBgtJQ+iHpmDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T12:00:35.656677Z"},"content_sha256":"a2ea3abe355b6d22db25b4ac6adb91541d85eb88f444675582b06dbe5b521488","schema_version":"1.0","event_id":"sha256:a2ea3abe355b6d22db25b4ac6adb91541d85eb88f444675582b06dbe5b521488"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZYLUYRY73GECSGGLKDTAENWTTX/bundle.json","state_url":"https://pith.science/pith/ZYLUYRY73GECSGGLKDTAENWTTX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZYLUYRY73GECSGGLKDTAENWTTX/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":"2026-05-23T12:00:35Z","links":{"resolver":"https://pith.science/pith/ZYLUYRY73GECSGGLKDTAENWTTX","bundle":"https://pith.science/pith/ZYLUYRY73GECSGGLKDTAENWTTX/bundle.json","state":"https://pith.science/pith/ZYLUYRY73GECSGGLKDTAENWTTX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZYLUYRY73GECSGGLKDTAENWTTX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:ZYLUYRY73GECSGGLKDTAENWTTX","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":"bc593555df9bd06191bc065176ca79890adf9b921d83634a6b791aee62528696","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-05-07T18:36:14Z","title_canon_sha256":"edabbfe26fd623706d88559ed43543b7fa54c061fbf631c16122160f845085bc"},"schema_version":"1.0","source":{"id":"1505.01809","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1505.01809","created_at":"2026-05-18T01:30:07Z"},{"alias_kind":"arxiv_version","alias_value":"1505.01809v3","created_at":"2026-05-18T01:30:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.01809","created_at":"2026-05-18T01:30:07Z"},{"alias_kind":"pith_short_12","alias_value":"ZYLUYRY73GEC","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"ZYLUYRY73GECSGGL","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"ZYLUYRY7","created_at":"2026-05-18T12:29:52Z"}],"graph_snapshots":[{"event_id":"sha256:a2ea3abe355b6d22db25b4ac6adb91541d85eb88f444675582b06dbe5b521488","target":"graph","created_at":"2026-05-18T01:30:07Z","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":"Two recent approaches have achieved state-of-the-art results in image captioning. The first uses a pipelined process where a set of candidate words is generated by a convolutional neural network (CNN) trained on images, and then a maximum entropy (ME) language model is used to arrange these words into a coherent sentence. The second uses the penultimate activation layer of the CNN as input to a recurrent neural network (RNN) that then generates the caption sequence. In this paper, we compare the merits of these different language modeling approaches for the first time by using the same state-o","authors_text":"Geoffrey Zweig, Hao Cheng, Hao Fang, Jacob Devlin, Li Deng, Margaret Mitchell, Saurabh Gupta, Xiaodong He","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-05-07T18:36:14Z","title":"Language Models for Image Captioning: The Quirks and What Works"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.01809","kind":"arxiv","version":3},"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:cbbca4c58efdf56fe3385cfeaef3498abfe74ebb59e36920cf63fc1e84a23252","target":"record","created_at":"2026-05-18T01:30:07Z","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":"bc593555df9bd06191bc065176ca79890adf9b921d83634a6b791aee62528696","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-05-07T18:36:14Z","title_canon_sha256":"edabbfe26fd623706d88559ed43543b7fa54c061fbf631c16122160f845085bc"},"schema_version":"1.0","source":{"id":"1505.01809","kind":"arxiv","version":3}},"canonical_sha256":"ce174c471fd9882918cb50e60236d39dda1f12d77a9f321a7ab3485087a024b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce174c471fd9882918cb50e60236d39dda1f12d77a9f321a7ab3485087a024b6","first_computed_at":"2026-05-18T01:30:07.982435Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:30:07.982435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XFGlf0uy0Am4FIbjbsGqz/I3oN9mAjkkTls8nXCNlIx3jmA+LNZAmMMlKtL/0xfWLiC7XrwHoDaR3hsgIAl5CQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:30:07.982822Z","signed_message":"canonical_sha256_bytes"},"source_id":"1505.01809","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cbbca4c58efdf56fe3385cfeaef3498abfe74ebb59e36920cf63fc1e84a23252","sha256:a2ea3abe355b6d22db25b4ac6adb91541d85eb88f444675582b06dbe5b521488"],"state_sha256":"bc52c3b0ec81db4908e3c1df9980c58926ad7d0f55ef25b924fcac649e9fe07c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gCos7lKeqVCxquQY8Nnt6401FoO5rG4p9Bz2Cf688n4SkMdVK+rb7Lrb/mlNXrFCnNB2w+psyfluasELzWADBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T12:00:35.660699Z","bundle_sha256":"9a42428fe8b2569f7702b1eb341e4e2e02e3845e01bc5f633a31d973ec92bcc7"}}