{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HAQLNNYUTKSQHLDFNJDMFZGBKW","short_pith_number":"pith:HAQLNNYU","schema_version":"1.0","canonical_sha256":"3820b6b7149aa503ac656a46c2e4c155aceb436eb3979baab9d3ab518f087d3f","source":{"kind":"arxiv","id":"1803.11439","version":2},"attestation_state":"computed","paper":{"title":"Regularizing RNNs for Caption Generation by Reconstructing The Past with The Present","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jian Yao, Lin Ma, Wei Liu, Wenhao Jiang, Xinpeng Chen","submitted_at":"2018-03-30T13:15:56Z","abstract_excerpt":"Recently, caption generation with an encoder-decoder framework has been extensively studied and applied in different domains, such as image captioning, code captioning, and so on. In this paper, we propose a novel architecture, namely Auto-Reconstructor Network (ARNet), which, coupling with the conventional encoder-decoder framework, works in an end-to-end fashion to generate captions. ARNet aims at reconstructing the previous hidden state with the present one, besides behaving as the input-dependent transition operator. Therefore, ARNet encourages the current hidden state to embed more inform"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1803.11439","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-30T13:15:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"39639c17ba8e15ee50c2e9fd2d24bac75af65452c49f7ef8a992fd8c564d4611","abstract_canon_sha256":"8d4ac0a2ca2a54170ddf3555c8bdc652b0b899dc929441ff6b135cd34cf6fa8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:01.990732Z","signature_b64":"0aPR24kkiJ9a1IrqgxRscv4IocEUud1SPyKVKc7houCspu/NBl6n5V/+Nb7ugdTgSKns1cvaaWN0Yb4WM9OoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3820b6b7149aa503ac656a46c2e4c155aceb436eb3979baab9d3ab518f087d3f","last_reissued_at":"2026-05-18T00:19:01.990100Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:01.990100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regularizing RNNs for Caption Generation by Reconstructing The Past with The Present","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jian Yao, Lin Ma, Wei Liu, Wenhao Jiang, Xinpeng Chen","submitted_at":"2018-03-30T13:15:56Z","abstract_excerpt":"Recently, caption generation with an encoder-decoder framework has been extensively studied and applied in different domains, such as image captioning, code captioning, and so on. In this paper, we propose a novel architecture, namely Auto-Reconstructor Network (ARNet), which, coupling with the conventional encoder-decoder framework, works in an end-to-end fashion to generate captions. ARNet aims at reconstructing the previous hidden state with the present one, besides behaving as the input-dependent transition operator. Therefore, ARNet encourages the current hidden state to embed more inform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.11439","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1803.11439","created_at":"2026-05-18T00:19:01.990194+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.11439v2","created_at":"2026-05-18T00:19:01.990194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.11439","created_at":"2026-05-18T00:19:01.990194+00:00"},{"alias_kind":"pith_short_12","alias_value":"HAQLNNYUTKSQ","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"HAQLNNYUTKSQHLDF","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"HAQLNNYU","created_at":"2026-05-18T12:32:28.185984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20567","citing_title":"Show, Tell and Summarize: Dense Video Captioning Using Visual Cue Aided Sentence Summarization","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HAQLNNYUTKSQHLDFNJDMFZGBKW","json":"https://pith.science/pith/HAQLNNYUTKSQHLDFNJDMFZGBKW.json","graph_json":"https://pith.science/api/pith-number/HAQLNNYUTKSQHLDFNJDMFZGBKW/graph.json","events_json":"https://pith.science/api/pith-number/HAQLNNYUTKSQHLDFNJDMFZGBKW/events.json","paper":"https://pith.science/paper/HAQLNNYU"},"agent_actions":{"view_html":"https://pith.science/pith/HAQLNNYUTKSQHLDFNJDMFZGBKW","download_json":"https://pith.science/pith/HAQLNNYUTKSQHLDFNJDMFZGBKW.json","view_paper":"https://pith.science/paper/HAQLNNYU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.11439&json=true","fetch_graph":"https://pith.science/api/pith-number/HAQLNNYUTKSQHLDFNJDMFZGBKW/graph.json","fetch_events":"https://pith.science/api/pith-number/HAQLNNYUTKSQHLDFNJDMFZGBKW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HAQLNNYUTKSQHLDFNJDMFZGBKW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HAQLNNYUTKSQHLDFNJDMFZGBKW/action/storage_attestation","attest_author":"https://pith.science/pith/HAQLNNYUTKSQHLDFNJDMFZGBKW/action/author_attestation","sign_citation":"https://pith.science/pith/HAQLNNYUTKSQHLDFNJDMFZGBKW/action/citation_signature","submit_replication":"https://pith.science/pith/HAQLNNYUTKSQHLDFNJDMFZGBKW/action/replication_record"}},"created_at":"2026-05-18T00:19:01.990194+00:00","updated_at":"2026-05-18T00:19:01.990194+00:00"}