{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:YAOWZFCUEDIGZVUHLMFLA5T6WO","short_pith_number":"pith:YAOWZFCU","schema_version":"1.0","canonical_sha256":"c01d6c945420d06cd6875b0ab0767eb3aa3cd9946a5753eb27a8d879d5f692c4","source":{"kind":"arxiv","id":"1612.00478","version":1},"attestation_state":"computed","paper":{"title":"In Teacher We Trust: Learning Compressed Models for Pedestrian Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jonathan Shen, Kris M. Kitani, Noranart Vesdapunt, Vishnu N. Boddeti","submitted_at":"2016-12-01T21:37:19Z","abstract_excerpt":"Deep convolutional neural networks continue to advance the state-of-the-art in many domains as they grow bigger and more complex. It has been observed that many of the parameters of a large network are redundant, allowing for the possibility of learning a smaller network that mimics the outputs of the large network through a process called Knowledge Distillation. We show, however, that standard Knowledge Distillation is not effective for learning small models for the task of pedestrian detection. To improve this process, we introduce a higher-dimensional hint layer to increase information flow"},"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":"1612.00478","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-01T21:37:19Z","cross_cats_sorted":[],"title_canon_sha256":"c5aa2767052efed7f115f966c3c15ab3899fa83f5aadcc17acebb817689153a7","abstract_canon_sha256":"56cabbff86fa56c7e649f28ee04d6f4a27e2c8b9e689fa8c625563b3200ed236"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:55:59.894336Z","signature_b64":"HR2ZSe+Y2eGfW6ZA+HAiUpCjAQELkn0yMEv389Ulhpo6niyYCu6IgA9QVuFCNgpJq6Sv31ur0LR9rR7Yv6BNCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c01d6c945420d06cd6875b0ab0767eb3aa3cd9946a5753eb27a8d879d5f692c4","last_reissued_at":"2026-05-18T00:55:59.893613Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:55:59.893613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In Teacher We Trust: Learning Compressed Models for Pedestrian Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jonathan Shen, Kris M. Kitani, Noranart Vesdapunt, Vishnu N. Boddeti","submitted_at":"2016-12-01T21:37:19Z","abstract_excerpt":"Deep convolutional neural networks continue to advance the state-of-the-art in many domains as they grow bigger and more complex. It has been observed that many of the parameters of a large network are redundant, allowing for the possibility of learning a smaller network that mimics the outputs of the large network through a process called Knowledge Distillation. We show, however, that standard Knowledge Distillation is not effective for learning small models for the task of pedestrian detection. To improve this process, we introduce a higher-dimensional hint layer to increase information flow"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.00478","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":""},"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":"1612.00478","created_at":"2026-05-18T00:55:59.893734+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.00478v1","created_at":"2026-05-18T00:55:59.893734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.00478","created_at":"2026-05-18T00:55:59.893734+00:00"},{"alias_kind":"pith_short_12","alias_value":"YAOWZFCUEDIG","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_16","alias_value":"YAOWZFCUEDIGZVUH","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_8","alias_value":"YAOWZFCU","created_at":"2026-05-18T12:30:53.716459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.11025","citing_title":"Towards Generalizing Sensorimotor Control Across Weather Conditions","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YAOWZFCUEDIGZVUHLMFLA5T6WO","json":"https://pith.science/pith/YAOWZFCUEDIGZVUHLMFLA5T6WO.json","graph_json":"https://pith.science/api/pith-number/YAOWZFCUEDIGZVUHLMFLA5T6WO/graph.json","events_json":"https://pith.science/api/pith-number/YAOWZFCUEDIGZVUHLMFLA5T6WO/events.json","paper":"https://pith.science/paper/YAOWZFCU"},"agent_actions":{"view_html":"https://pith.science/pith/YAOWZFCUEDIGZVUHLMFLA5T6WO","download_json":"https://pith.science/pith/YAOWZFCUEDIGZVUHLMFLA5T6WO.json","view_paper":"https://pith.science/paper/YAOWZFCU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.00478&json=true","fetch_graph":"https://pith.science/api/pith-number/YAOWZFCUEDIGZVUHLMFLA5T6WO/graph.json","fetch_events":"https://pith.science/api/pith-number/YAOWZFCUEDIGZVUHLMFLA5T6WO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YAOWZFCUEDIGZVUHLMFLA5T6WO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YAOWZFCUEDIGZVUHLMFLA5T6WO/action/storage_attestation","attest_author":"https://pith.science/pith/YAOWZFCUEDIGZVUHLMFLA5T6WO/action/author_attestation","sign_citation":"https://pith.science/pith/YAOWZFCUEDIGZVUHLMFLA5T6WO/action/citation_signature","submit_replication":"https://pith.science/pith/YAOWZFCUEDIGZVUHLMFLA5T6WO/action/replication_record"}},"created_at":"2026-05-18T00:55:59.893734+00:00","updated_at":"2026-05-18T00:55:59.893734+00:00"}