{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SHS4T6NIHUOPOTNQ4CTOBLZAAF","short_pith_number":"pith:SHS4T6NI","schema_version":"1.0","canonical_sha256":"91e5c9f9a83d1cf74db0e0a6e0af20017b3c71922c0174a9a0f135b85c35315b","source":{"kind":"arxiv","id":"2006.10923","version":1},"attestation_state":"computed","paper":{"title":"Hyperparameter Analysis for Image Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Amish Patel, Aravind Varier","submitted_at":"2020-06-19T01:49:37Z","abstract_excerpt":"In this paper, we perform a thorough sensitivity analysis on state-of-the-art image captioning approaches using two different architectures: CNN+LSTM and CNN+Transformer. Experiments were carried out using the Flickr8k dataset. The biggest takeaway from the experiments is that fine-tuning the CNN encoder outperforms the baseline and all other experiments carried out for both architectures."},"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":"2006.10923","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-06-19T01:49:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"46c2f13607316258d92070fdb1a07f6b41f0a2ce22b6d0966f5e32fc3aaf42ae","abstract_canon_sha256":"93a8e3b1883657fbc9f69d59d1c7f2d269a32236260b2f6f06f6490b291ea765"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:26.803611Z","signature_b64":"tMdL7YvdgxejhcxJ1ULq90Evd2irEJJ+vB0BHs+EOokhKK8/wDLOX81J7H6wo6TxP5kJsTS+ftaa592SbW96CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91e5c9f9a83d1cf74db0e0a6e0af20017b3c71922c0174a9a0f135b85c35315b","last_reissued_at":"2026-07-05T01:11:26.803060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:26.803060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hyperparameter Analysis for Image Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Amish Patel, Aravind Varier","submitted_at":"2020-06-19T01:49:37Z","abstract_excerpt":"In this paper, we perform a thorough sensitivity analysis on state-of-the-art image captioning approaches using two different architectures: CNN+LSTM and CNN+Transformer. Experiments were carried out using the Flickr8k dataset. The biggest takeaway from the experiments is that fine-tuning the CNN encoder outperforms the baseline and all other experiments carried out for both architectures."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.10923","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/2006.10923/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2006.10923","created_at":"2026-07-05T01:11:26.803113+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.10923v1","created_at":"2026-07-05T01:11:26.803113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.10923","created_at":"2026-07-05T01:11:26.803113+00:00"},{"alias_kind":"pith_short_12","alias_value":"SHS4T6NIHUOP","created_at":"2026-07-05T01:11:26.803113+00:00"},{"alias_kind":"pith_short_16","alias_value":"SHS4T6NIHUOPOTNQ","created_at":"2026-07-05T01:11:26.803113+00:00"},{"alias_kind":"pith_short_8","alias_value":"SHS4T6NI","created_at":"2026-07-05T01:11:26.803113+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.14828","citing_title":"An Ensemble Model with Attention Based Mechanism for Image Captioning","ref_index":83,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SHS4T6NIHUOPOTNQ4CTOBLZAAF","json":"https://pith.science/pith/SHS4T6NIHUOPOTNQ4CTOBLZAAF.json","graph_json":"https://pith.science/api/pith-number/SHS4T6NIHUOPOTNQ4CTOBLZAAF/graph.json","events_json":"https://pith.science/api/pith-number/SHS4T6NIHUOPOTNQ4CTOBLZAAF/events.json","paper":"https://pith.science/paper/SHS4T6NI"},"agent_actions":{"view_html":"https://pith.science/pith/SHS4T6NIHUOPOTNQ4CTOBLZAAF","download_json":"https://pith.science/pith/SHS4T6NIHUOPOTNQ4CTOBLZAAF.json","view_paper":"https://pith.science/paper/SHS4T6NI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.10923&json=true","fetch_graph":"https://pith.science/api/pith-number/SHS4T6NIHUOPOTNQ4CTOBLZAAF/graph.json","fetch_events":"https://pith.science/api/pith-number/SHS4T6NIHUOPOTNQ4CTOBLZAAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SHS4T6NIHUOPOTNQ4CTOBLZAAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SHS4T6NIHUOPOTNQ4CTOBLZAAF/action/storage_attestation","attest_author":"https://pith.science/pith/SHS4T6NIHUOPOTNQ4CTOBLZAAF/action/author_attestation","sign_citation":"https://pith.science/pith/SHS4T6NIHUOPOTNQ4CTOBLZAAF/action/citation_signature","submit_replication":"https://pith.science/pith/SHS4T6NIHUOPOTNQ4CTOBLZAAF/action/replication_record"}},"created_at":"2026-07-05T01:11:26.803113+00:00","updated_at":"2026-07-05T01:11:26.803113+00:00"}