{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:KXPARNZ7SIYYJG2QAXIFG5DPAJ","short_pith_number":"pith:KXPARNZ7","schema_version":"1.0","canonical_sha256":"55de08b73f9231849b5005d053746f0248469aaae25fe491288446da03f0be80","source":{"kind":"arxiv","id":"2009.14405","version":1},"attestation_state":"computed","paper":{"title":"Teacher-Critical Training Strategies for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Jiansheng Chen, Yiqing Huang","submitted_at":"2020-09-30T03:15:12Z","abstract_excerpt":"Existing image captioning models are usually trained by cross-entropy (XE) loss and reinforcement learning (RL), which set ground-truth words as hard targets and force the captioning model to learn from them. However, the widely adopted training strategies suffer from misalignment in XE training and inappropriate reward assignment in RL training. To tackle these problems, we introduce a teacher model that serves as a bridge between the ground-truth caption and the caption model by generating some easier-to-learn word proposals as soft targets. The teacher model is constructed by incorporating "},"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":"2009.14405","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-09-30T03:15:12Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"4d536cc1452a9f3e9654e1b75f9c993aa5e765e5a22ddf17c3a351fb59a1a02e","abstract_canon_sha256":"f68946acb69215c0832a3f6c0014e6e988887fddb888de90eb883d964b91722d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:10.301391Z","signature_b64":"8cM+li0Jrj9lBMhIzJk8hr2YDdYSCg5tt1zLHR/Y3mZXSlLvA4V0EHnKAl1xpPFg9i1afYhI5MJdXr+pBv1aBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55de08b73f9231849b5005d053746f0248469aaae25fe491288446da03f0be80","last_reissued_at":"2026-07-05T04:46:10.300898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:10.300898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Teacher-Critical Training Strategies for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Jiansheng Chen, Yiqing Huang","submitted_at":"2020-09-30T03:15:12Z","abstract_excerpt":"Existing image captioning models are usually trained by cross-entropy (XE) loss and reinforcement learning (RL), which set ground-truth words as hard targets and force the captioning model to learn from them. However, the widely adopted training strategies suffer from misalignment in XE training and inappropriate reward assignment in RL training. To tackle these problems, we introduce a teacher model that serves as a bridge between the ground-truth caption and the caption model by generating some easier-to-learn word proposals as soft targets. The teacher model is constructed by incorporating "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.14405","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/2009.14405/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":"2009.14405","created_at":"2026-07-05T04:46:10.300965+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.14405v1","created_at":"2026-07-05T04:46:10.300965+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.14405","created_at":"2026-07-05T04:46:10.300965+00:00"},{"alias_kind":"pith_short_12","alias_value":"KXPARNZ7SIYY","created_at":"2026-07-05T04:46:10.300965+00:00"},{"alias_kind":"pith_short_16","alias_value":"KXPARNZ7SIYYJG2Q","created_at":"2026-07-05T04:46:10.300965+00:00"},{"alias_kind":"pith_short_8","alias_value":"KXPARNZ7","created_at":"2026-07-05T04:46:10.300965+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KXPARNZ7SIYYJG2QAXIFG5DPAJ","json":"https://pith.science/pith/KXPARNZ7SIYYJG2QAXIFG5DPAJ.json","graph_json":"https://pith.science/api/pith-number/KXPARNZ7SIYYJG2QAXIFG5DPAJ/graph.json","events_json":"https://pith.science/api/pith-number/KXPARNZ7SIYYJG2QAXIFG5DPAJ/events.json","paper":"https://pith.science/paper/KXPARNZ7"},"agent_actions":{"view_html":"https://pith.science/pith/KXPARNZ7SIYYJG2QAXIFG5DPAJ","download_json":"https://pith.science/pith/KXPARNZ7SIYYJG2QAXIFG5DPAJ.json","view_paper":"https://pith.science/paper/KXPARNZ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.14405&json=true","fetch_graph":"https://pith.science/api/pith-number/KXPARNZ7SIYYJG2QAXIFG5DPAJ/graph.json","fetch_events":"https://pith.science/api/pith-number/KXPARNZ7SIYYJG2QAXIFG5DPAJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KXPARNZ7SIYYJG2QAXIFG5DPAJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KXPARNZ7SIYYJG2QAXIFG5DPAJ/action/storage_attestation","attest_author":"https://pith.science/pith/KXPARNZ7SIYYJG2QAXIFG5DPAJ/action/author_attestation","sign_citation":"https://pith.science/pith/KXPARNZ7SIYYJG2QAXIFG5DPAJ/action/citation_signature","submit_replication":"https://pith.science/pith/KXPARNZ7SIYYJG2QAXIFG5DPAJ/action/replication_record"}},"created_at":"2026-07-05T04:46:10.300965+00:00","updated_at":"2026-07-05T04:46:10.300965+00:00"}