{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:KZQQ3R6MQZLMDEPSWUDJX22IMT","short_pith_number":"pith:KZQQ3R6M","canonical_record":{"source":{"id":"1412.6550","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-19T22:40:51Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"c3bc2e609ab2b30436e11b3b9d743c43e32d29b3d00eab409106a628206b534c","abstract_canon_sha256":"b5c36af2ae418d3cbb6cb525c0fd90318369ba1593e5468e6d797db8d6eb1e00"},"schema_version":"1.0"},"canonical_sha256":"56610dc7cc8656c191f2b5069beb4864c29131d16aca960b08833884d43ee862","source":{"kind":"arxiv","id":"1412.6550","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.6550","created_at":"2026-05-18T02:48:56Z"},{"alias_kind":"arxiv_version","alias_value":"1412.6550v4","created_at":"2026-05-18T02:48:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.6550","created_at":"2026-05-18T02:48:56Z"},{"alias_kind":"pith_short_12","alias_value":"KZQQ3R6MQZLM","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_16","alias_value":"KZQQ3R6MQZLMDEPS","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_8","alias_value":"KZQQ3R6M","created_at":"2026-05-18T12:28:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:KZQQ3R6MQZLMDEPSWUDJX22IMT","target":"record","payload":{"canonical_record":{"source":{"id":"1412.6550","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-19T22:40:51Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"c3bc2e609ab2b30436e11b3b9d743c43e32d29b3d00eab409106a628206b534c","abstract_canon_sha256":"b5c36af2ae418d3cbb6cb525c0fd90318369ba1593e5468e6d797db8d6eb1e00"},"schema_version":"1.0"},"canonical_sha256":"56610dc7cc8656c191f2b5069beb4864c29131d16aca960b08833884d43ee862","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:48:56.381790Z","signature_b64":"0WmxrovYUcrlDxZoba52pPr+FPWfUAaaCsMShkKoJPscJ6kH978XhFhQv7pFyEFw0hqi5UDYFR+7lTLXpARYAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56610dc7cc8656c191f2b5069beb4864c29131d16aca960b08833884d43ee862","last_reissued_at":"2026-05-18T02:48:56.381163Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:48:56.381163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1412.6550","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:48:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fWFym3+ylF538+do+l+NvHcZmsTnCmr17kyvZIVfxm7bU3N6Fpe9WxjCIat3gYJZWnQsPWrwmyRDAWA8QQcqDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T16:57:14.040761Z"},"content_sha256":"7b18d5c76e5af8fb3052c1be259c1d275357df5c7dc7245d5434053bb16db356","schema_version":"1.0","event_id":"sha256:7b18d5c76e5af8fb3052c1be259c1d275357df5c7dc7245d5434053bb16db356"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:KZQQ3R6MQZLMDEPSWUDJX22IMT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FitNets: Hints for Thin Deep Nets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A deeper but much thinner student network can outperform its larger teacher by using intermediate layer hints during training.","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Adriana Romero, Antoine Chassang, Carlo Gatta, Nicolas Ballas, Samira Ebrahimi Kahou, Yoshua Bengio","submitted_at":"2014-12-19T22:40:51Z","abstract_excerpt":"While depth tends to improve network performances, it also makes gradient-based training more difficult since deeper networks tend to be more non-linear. The recently proposed knowledge distillation approach is aimed at obtaining small and fast-to-execute models, and it has shown that a student network could imitate the soft output of a larger teacher network or ensemble of networks. In this paper, we extend this idea to allow the training of a student that is deeper and thinner than the teacher, using not only the outputs but also the intermediate representations learned by the teacher as hin"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"For example, on CIFAR-10, a deep student network with almost 10.4 times less parameters outperforms a larger, state-of-the-art teacher network.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the added mapping parameters can reliably transfer useful intermediate knowledge from teacher to a much smaller student layer without the extra capacity causing overfitting or unstable training.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"FitNets trains deeper thinner students using teacher intermediate representations as hints plus mapping parameters, yielding a CIFAR-10 student with 10.4x fewer parameters that beats the teacher.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A deeper but much thinner student network can outperform its larger teacher by using intermediate layer hints during training.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"60684e41e36e5149e25cc689a176be470ddf8e46d03f9ec70cdbd45de6cbee81"},"source":{"id":"1412.6550","kind":"arxiv","version":4},"verdict":{"id":"51b0bf8b-5985-4814-b3a2-fdf7890eeb68","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T01:41:27.991454Z","strongest_claim":"For example, on CIFAR-10, a deep student network with almost 10.4 times less parameters outperforms a larger, state-of-the-art teacher network.","one_line_summary":"FitNets trains deeper thinner students using teacher intermediate representations as hints plus mapping parameters, yielding a CIFAR-10 student with 10.4x fewer parameters that beats the teacher.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the added mapping parameters can reliably transfer useful intermediate knowledge from teacher to a much smaller student layer without the extra capacity causing overfitting or unstable training.","pith_extraction_headline":"A deeper but much thinner student network can outperform its larger teacher by using intermediate layer hints during training."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d9c0ff73509e7ea2479d29d13139e226c273d36054b129fa0e2ea1185e6392fc"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"51b0bf8b-5985-4814-b3a2-fdf7890eeb68"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:48:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tg4Dci6BpwKBv+I3x7cr/a4R5/1FXWKd2RKZ4NIRDIFjiCXuFMFsfTTs3W+/ztMcIh93tiPuBkc+djAhI1eNDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T16:57:14.041306Z"},"content_sha256":"b1e015a0be9aeaddef7a4e1176462e7f1a2186cc4b7a88d78d3f684974a64ba9","schema_version":"1.0","event_id":"sha256:b1e015a0be9aeaddef7a4e1176462e7f1a2186cc4b7a88d78d3f684974a64ba9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KZQQ3R6MQZLMDEPSWUDJX22IMT/bundle.json","state_url":"https://pith.science/pith/KZQQ3R6MQZLMDEPSWUDJX22IMT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KZQQ3R6MQZLMDEPSWUDJX22IMT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T16:57:14Z","links":{"resolver":"https://pith.science/pith/KZQQ3R6MQZLMDEPSWUDJX22IMT","bundle":"https://pith.science/pith/KZQQ3R6MQZLMDEPSWUDJX22IMT/bundle.json","state":"https://pith.science/pith/KZQQ3R6MQZLMDEPSWUDJX22IMT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KZQQ3R6MQZLMDEPSWUDJX22IMT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:KZQQ3R6MQZLMDEPSWUDJX22IMT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b5c36af2ae418d3cbb6cb525c0fd90318369ba1593e5468e6d797db8d6eb1e00","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-19T22:40:51Z","title_canon_sha256":"c3bc2e609ab2b30436e11b3b9d743c43e32d29b3d00eab409106a628206b534c"},"schema_version":"1.0","source":{"id":"1412.6550","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.6550","created_at":"2026-05-18T02:48:56Z"},{"alias_kind":"arxiv_version","alias_value":"1412.6550v4","created_at":"2026-05-18T02:48:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.6550","created_at":"2026-05-18T02:48:56Z"},{"alias_kind":"pith_short_12","alias_value":"KZQQ3R6MQZLM","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_16","alias_value":"KZQQ3R6MQZLMDEPS","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_8","alias_value":"KZQQ3R6M","created_at":"2026-05-18T12:28:35Z"}],"graph_snapshots":[{"event_id":"sha256:b1e015a0be9aeaddef7a4e1176462e7f1a2186cc4b7a88d78d3f684974a64ba9","target":"graph","created_at":"2026-05-18T02:48:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"For example, on CIFAR-10, a deep student network with almost 10.4 times less parameters outperforms a larger, state-of-the-art teacher network."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the added mapping parameters can reliably transfer useful intermediate knowledge from teacher to a much smaller student layer without the extra capacity causing overfitting or unstable training."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"FitNets trains deeper thinner students using teacher intermediate representations as hints plus mapping parameters, yielding a CIFAR-10 student with 10.4x fewer parameters that beats the teacher."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A deeper but much thinner student network can outperform its larger teacher by using intermediate layer hints during training."}],"snapshot_sha256":"60684e41e36e5149e25cc689a176be470ddf8e46d03f9ec70cdbd45de6cbee81"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d9c0ff73509e7ea2479d29d13139e226c273d36054b129fa0e2ea1185e6392fc"},"paper":{"abstract_excerpt":"While depth tends to improve network performances, it also makes gradient-based training more difficult since deeper networks tend to be more non-linear. The recently proposed knowledge distillation approach is aimed at obtaining small and fast-to-execute models, and it has shown that a student network could imitate the soft output of a larger teacher network or ensemble of networks. In this paper, we extend this idea to allow the training of a student that is deeper and thinner than the teacher, using not only the outputs but also the intermediate representations learned by the teacher as hin","authors_text":"Adriana Romero, Antoine Chassang, Carlo Gatta, Nicolas Ballas, Samira Ebrahimi Kahou, Yoshua Bengio","cross_cats":["cs.NE"],"headline":"A deeper but much thinner student network can outperform its larger teacher by using intermediate layer hints during training.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-19T22:40:51Z","title":"FitNets: Hints for Thin Deep Nets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.6550","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-14T01:41:27.991454Z","id":"51b0bf8b-5985-4814-b3a2-fdf7890eeb68","model_set":{"reader":"grok-4.3"},"one_line_summary":"FitNets trains deeper thinner students using teacher intermediate representations as hints plus mapping parameters, yielding a CIFAR-10 student with 10.4x fewer parameters that beats the teacher.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A deeper but much thinner student network can outperform its larger teacher by using intermediate layer hints during training.","strongest_claim":"For example, on CIFAR-10, a deep student network with almost 10.4 times less parameters outperforms a larger, state-of-the-art teacher network.","weakest_assumption":"That the added mapping parameters can reliably transfer useful intermediate knowledge from teacher to a much smaller student layer without the extra capacity causing overfitting or unstable training."}},"verdict_id":"51b0bf8b-5985-4814-b3a2-fdf7890eeb68"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7b18d5c76e5af8fb3052c1be259c1d275357df5c7dc7245d5434053bb16db356","target":"record","created_at":"2026-05-18T02:48:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b5c36af2ae418d3cbb6cb525c0fd90318369ba1593e5468e6d797db8d6eb1e00","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-19T22:40:51Z","title_canon_sha256":"c3bc2e609ab2b30436e11b3b9d743c43e32d29b3d00eab409106a628206b534c"},"schema_version":"1.0","source":{"id":"1412.6550","kind":"arxiv","version":4}},"canonical_sha256":"56610dc7cc8656c191f2b5069beb4864c29131d16aca960b08833884d43ee862","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56610dc7cc8656c191f2b5069beb4864c29131d16aca960b08833884d43ee862","first_computed_at":"2026-05-18T02:48:56.381163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:48:56.381163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0WmxrovYUcrlDxZoba52pPr+FPWfUAaaCsMShkKoJPscJ6kH978XhFhQv7pFyEFw0hqi5UDYFR+7lTLXpARYAA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:48:56.381790Z","signed_message":"canonical_sha256_bytes"},"source_id":"1412.6550","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b18d5c76e5af8fb3052c1be259c1d275357df5c7dc7245d5434053bb16db356","sha256:b1e015a0be9aeaddef7a4e1176462e7f1a2186cc4b7a88d78d3f684974a64ba9"],"state_sha256":"4b09e7bc0bd6379b81b0af49b4288ad2cb54deccb10a37e406898da137438747"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I315CkfoRact8vgabdYbpQLwHBwiOUsO38zZX260TTf1crJWxCx2TiXzfMsetusFwsQw++oxSq9d83McSGLNBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T16:57:14.044310Z","bundle_sha256":"f8c8e6f9481ffe37f6ed6474964a0373f20779009c6991166fbe5d3e8b6b91ef"}}