{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R6QA7JFGTGQBHNX42NECEVTLW4","short_pith_number":"pith:R6QA7JFG","schema_version":"1.0","canonical_sha256":"8fa00fa4a699a013b6fcd34822566bb727ae91edf6e9b80509ab35b24a7a3d91","source":{"kind":"arxiv","id":"2306.05527","version":2},"attestation_state":"computed","paper":{"title":"Teaching AI to Teach: Leveraging Limited Human Salience Data Into Unlimited Saliency-Based Training","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam Czajka, Aidan Boyd, Colton R. Crum, Kevin Bowyer","submitted_at":"2023-06-08T19:55:44Z","abstract_excerpt":"Machine learning models have shown increased accuracy in classification tasks when the training process incorporates human perceptual information. However, a challenge in training human-guided models is the cost associated with collecting image annotations for human salience. Collecting annotation data for all images in a large training set can be prohibitively expensive. In this work, we utilize \"teacher\" models (trained on a small amount of human-annotated data) to annotate additional data by means of teacher models' saliency maps. Then, \"student\" models are trained using the larger amount o"},"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":"2306.05527","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-08T19:55:44Z","cross_cats_sorted":[],"title_canon_sha256":"2aaf0cabcceae33c3631bfcda75be9cde260438ac06393ff999aced87ca89a5a","abstract_canon_sha256":"b893dc1fb975484fd626a220f528488c0b6de15add30d07bed1f7b3b068fdef2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:05.514936Z","signature_b64":"shx9+q5bf05CJCtSpoDvXBay1ouMb5lSBoLUOrrjYL5w6lFSQGBf8I/e5vTqdyYJeZktMCbeoTEHahQol4BxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fa00fa4a699a013b6fcd34822566bb727ae91edf6e9b80509ab35b24a7a3d91","last_reissued_at":"2026-07-05T07:11:05.514453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:05.514453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Teaching AI to Teach: Leveraging Limited Human Salience Data Into Unlimited Saliency-Based Training","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam Czajka, Aidan Boyd, Colton R. Crum, Kevin Bowyer","submitted_at":"2023-06-08T19:55:44Z","abstract_excerpt":"Machine learning models have shown increased accuracy in classification tasks when the training process incorporates human perceptual information. However, a challenge in training human-guided models is the cost associated with collecting image annotations for human salience. Collecting annotation data for all images in a large training set can be prohibitively expensive. In this work, we utilize \"teacher\" models (trained on a small amount of human-annotated data) to annotate additional data by means of teacher models' saliency maps. Then, \"student\" models are trained using the larger amount o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05527","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.05527/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":"2306.05527","created_at":"2026-07-05T07:11:05.514511+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.05527v2","created_at":"2026-07-05T07:11:05.514511+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05527","created_at":"2026-07-05T07:11:05.514511+00:00"},{"alias_kind":"pith_short_12","alias_value":"R6QA7JFGTGQB","created_at":"2026-07-05T07:11:05.514511+00:00"},{"alias_kind":"pith_short_16","alias_value":"R6QA7JFGTGQBHNX4","created_at":"2026-07-05T07:11:05.514511+00:00"},{"alias_kind":"pith_short_8","alias_value":"R6QA7JFG","created_at":"2026-07-05T07:11:05.514511+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13528","citing_title":"What's Old is New Again: Classical Dimensionality Reduction for Efficient Saliency-Guided Biometric Attack Detection","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2603.17859","citing_title":"VISER: Visually-Informed System for Enhanced Robustness in Open-Set Iris Presentation Attack Detection","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R6QA7JFGTGQBHNX42NECEVTLW4","json":"https://pith.science/pith/R6QA7JFGTGQBHNX42NECEVTLW4.json","graph_json":"https://pith.science/api/pith-number/R6QA7JFGTGQBHNX42NECEVTLW4/graph.json","events_json":"https://pith.science/api/pith-number/R6QA7JFGTGQBHNX42NECEVTLW4/events.json","paper":"https://pith.science/paper/R6QA7JFG"},"agent_actions":{"view_html":"https://pith.science/pith/R6QA7JFGTGQBHNX42NECEVTLW4","download_json":"https://pith.science/pith/R6QA7JFGTGQBHNX42NECEVTLW4.json","view_paper":"https://pith.science/paper/R6QA7JFG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.05527&json=true","fetch_graph":"https://pith.science/api/pith-number/R6QA7JFGTGQBHNX42NECEVTLW4/graph.json","fetch_events":"https://pith.science/api/pith-number/R6QA7JFGTGQBHNX42NECEVTLW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R6QA7JFGTGQBHNX42NECEVTLW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R6QA7JFGTGQBHNX42NECEVTLW4/action/storage_attestation","attest_author":"https://pith.science/pith/R6QA7JFGTGQBHNX42NECEVTLW4/action/author_attestation","sign_citation":"https://pith.science/pith/R6QA7JFGTGQBHNX42NECEVTLW4/action/citation_signature","submit_replication":"https://pith.science/pith/R6QA7JFGTGQBHNX42NECEVTLW4/action/replication_record"}},"created_at":"2026-07-05T07:11:05.514511+00:00","updated_at":"2026-07-05T07:11:05.514511+00:00"}