{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LCXAHJNLW64UAIFVRD63MFDBSQ","short_pith_number":"pith:LCXAHJNL","schema_version":"1.0","canonical_sha256":"58ae03a5abb7b94020b588fdb61461942ea37365b0f3ba29a10241c2408bbc43","source":{"kind":"arxiv","id":"2209.04130","version":2},"attestation_state":"computed","paper":{"title":"In-situ animal behavior classification using knowledge distillation and fixed-point quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.SP"],"primary_cat":"cs.LG","authors_text":"Caitlin Phillips, Greg Bishop-hurley, Jordan Yates, Lachlan Currie, Liang Wang, Reza Arablouei","submitted_at":"2022-09-09T06:07:17Z","abstract_excerpt":"We explore the use of knowledge distillation (KD) for learning compact and accurate models that enable classification of animal behavior from accelerometry data on wearable devices. To this end, we take a deep and complex convolutional neural network, known as residual neural network (ResNet), as the teacher model. ResNet is specifically designed for multivariate time-series classification. We use ResNet to distill the knowledge of animal behavior classification datasets into soft labels, which consist of the predicted pseudo-probabilities of every class for each datapoint. We then use the sof"},"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":"2209.04130","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-09T06:07:17Z","cross_cats_sorted":["cs.AI","eess.SP"],"title_canon_sha256":"81ea038665e60248fae84d69f46beb4076209ab27e0d5c5658cdcc0f7e04bbad","abstract_canon_sha256":"6558ac8e53c643a37f08fd275d9b7fdc9c675a96a317f0a6e38d361875b506d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:26:49.232452Z","signature_b64":"wTyvgv8xjDexjtgvtv8SGyKQl+HS5//+wZnx5NRrq2/haKWF6jaAEt4bhcvgtfpj9G7a/f5yy5JfJV9Awe94Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58ae03a5abb7b94020b588fdb61461942ea37365b0f3ba29a10241c2408bbc43","last_reissued_at":"2026-07-05T05:26:49.232012Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:26:49.232012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-situ animal behavior classification using knowledge distillation and fixed-point quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.SP"],"primary_cat":"cs.LG","authors_text":"Caitlin Phillips, Greg Bishop-hurley, Jordan Yates, Lachlan Currie, Liang Wang, Reza Arablouei","submitted_at":"2022-09-09T06:07:17Z","abstract_excerpt":"We explore the use of knowledge distillation (KD) for learning compact and accurate models that enable classification of animal behavior from accelerometry data on wearable devices. To this end, we take a deep and complex convolutional neural network, known as residual neural network (ResNet), as the teacher model. ResNet is specifically designed for multivariate time-series classification. We use ResNet to distill the knowledge of animal behavior classification datasets into soft labels, which consist of the predicted pseudo-probabilities of every class for each datapoint. We then use the sof"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.04130","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/2209.04130/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":"2209.04130","created_at":"2026-07-05T05:26:49.232069+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.04130v2","created_at":"2026-07-05T05:26:49.232069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.04130","created_at":"2026-07-05T05:26:49.232069+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCXAHJNLW64U","created_at":"2026-07-05T05:26:49.232069+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCXAHJNLW64UAIFV","created_at":"2026-07-05T05:26:49.232069+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCXAHJNL","created_at":"2026-07-05T05:26:49.232069+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/LCXAHJNLW64UAIFVRD63MFDBSQ","json":"https://pith.science/pith/LCXAHJNLW64UAIFVRD63MFDBSQ.json","graph_json":"https://pith.science/api/pith-number/LCXAHJNLW64UAIFVRD63MFDBSQ/graph.json","events_json":"https://pith.science/api/pith-number/LCXAHJNLW64UAIFVRD63MFDBSQ/events.json","paper":"https://pith.science/paper/LCXAHJNL"},"agent_actions":{"view_html":"https://pith.science/pith/LCXAHJNLW64UAIFVRD63MFDBSQ","download_json":"https://pith.science/pith/LCXAHJNLW64UAIFVRD63MFDBSQ.json","view_paper":"https://pith.science/paper/LCXAHJNL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.04130&json=true","fetch_graph":"https://pith.science/api/pith-number/LCXAHJNLW64UAIFVRD63MFDBSQ/graph.json","fetch_events":"https://pith.science/api/pith-number/LCXAHJNLW64UAIFVRD63MFDBSQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCXAHJNLW64UAIFVRD63MFDBSQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCXAHJNLW64UAIFVRD63MFDBSQ/action/storage_attestation","attest_author":"https://pith.science/pith/LCXAHJNLW64UAIFVRD63MFDBSQ/action/author_attestation","sign_citation":"https://pith.science/pith/LCXAHJNLW64UAIFVRD63MFDBSQ/action/citation_signature","submit_replication":"https://pith.science/pith/LCXAHJNLW64UAIFVRD63MFDBSQ/action/replication_record"}},"created_at":"2026-07-05T05:26:49.232069+00:00","updated_at":"2026-07-05T05:26:49.232069+00:00"}