{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:OHQ77U5UJOEC3QX5YHW46ZCDQJ","short_pith_number":"pith:OHQ77U5U","canonical_record":{"source":{"id":"1810.01140","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-10-02T09:45:15Z","cross_cats_sorted":[],"title_canon_sha256":"3e4ee54547630d38b0aba1a12db5d846ff354b17856d72473fac8311f0fcc5a4","abstract_canon_sha256":"0ac6da4474e0abc6e3dc57ad2189ae8b14c62ba018e51bcba23b7c7cca8cbb81"},"schema_version":"1.0"},"canonical_sha256":"71e1ffd3b44b882dc2fdc1edcf64438264a37fca6b40a076c5c31f4fe487e183","source":{"kind":"arxiv","id":"1810.01140","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.01140","created_at":"2026-05-18T00:03:55Z"},{"alias_kind":"arxiv_version","alias_value":"1810.01140v2","created_at":"2026-05-18T00:03:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.01140","created_at":"2026-05-18T00:03:55Z"},{"alias_kind":"pith_short_12","alias_value":"OHQ77U5UJOEC","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OHQ77U5UJOEC3QX5","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OHQ77U5U","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:OHQ77U5UJOEC3QX5YHW46ZCDQJ","target":"record","payload":{"canonical_record":{"source":{"id":"1810.01140","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-10-02T09:45:15Z","cross_cats_sorted":[],"title_canon_sha256":"3e4ee54547630d38b0aba1a12db5d846ff354b17856d72473fac8311f0fcc5a4","abstract_canon_sha256":"0ac6da4474e0abc6e3dc57ad2189ae8b14c62ba018e51bcba23b7c7cca8cbb81"},"schema_version":"1.0"},"canonical_sha256":"71e1ffd3b44b882dc2fdc1edcf64438264a37fca6b40a076c5c31f4fe487e183","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:55.239494Z","signature_b64":"DDNL8pyU3/VMEdC7mmE+1+Wyt+TgjcxjdVrCJ0xn4rNmoq5ZH3zjgJaMdsYQPYnWsue0iZoEkkMxHD/6GSUeDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71e1ffd3b44b882dc2fdc1edcf64438264a37fca6b40a076c5c31f4fe487e183","last_reissued_at":"2026-05-18T00:03:55.238971Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:55.238971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.01140","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:03:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hM2vZI3JkY/pzNgtM9E29QhyWT+BcRt0SdLbW01FjK2Yu8Nr9vdA3ct9dTZgI6VyiunhNR9GDmKVGJSYcAbSBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T09:14:24.447790Z"},"content_sha256":"305494188fde5baf3e63b139b3269e300cd03445c6583891e39293f74fddb778","schema_version":"1.0","event_id":"sha256:305494188fde5baf3e63b139b3269e300cd03445c6583891e39293f74fddb778"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:OHQ77U5UJOEC3QX5YHW46ZCDQJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training compact deep learning models for video classification using circulant matrices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandre Araujo, Benjamin Negrevergne, Jamal Atif, Yann Chevaleyre","submitted_at":"2018-10-02T09:45:15Z","abstract_excerpt":"In real world scenarios, model accuracy is hardly the only factor to consider. Large models consume more memory and are computationally more intensive, which makes them difficult to train and to deploy, especially on mobile devices. In this paper, we build on recent results at the crossroads of Linear Algebra and Deep Learning which demonstrate how imposing a structure on large weight matrices can be used to reduce the size of the model. We propose very compact models for video classification based on state-of-the-art network architectures such as Deep Bag-of-Frames, NetVLAD and NetFisherVecto"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.01140","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:03:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vZAj8eI7hK3RQLuxiikYIdDX8tyDYep2x+6QsgxWZuXHoYrJKuOq0EiwnJIZ0abm6W3PCzdQaC7MvE0/HT5sDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T09:14:24.448173Z"},"content_sha256":"0be5e5e006a5dee6f50a92f61edb53a6c764ac93cdc2e5550aa92b59f8f9f7aa","schema_version":"1.0","event_id":"sha256:0be5e5e006a5dee6f50a92f61edb53a6c764ac93cdc2e5550aa92b59f8f9f7aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OHQ77U5UJOEC3QX5YHW46ZCDQJ/bundle.json","state_url":"https://pith.science/pith/OHQ77U5UJOEC3QX5YHW46ZCDQJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OHQ77U5UJOEC3QX5YHW46ZCDQJ/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":"2026-05-26T09:14:24Z","links":{"resolver":"https://pith.science/pith/OHQ77U5UJOEC3QX5YHW46ZCDQJ","bundle":"https://pith.science/pith/OHQ77U5UJOEC3QX5YHW46ZCDQJ/bundle.json","state":"https://pith.science/pith/OHQ77U5UJOEC3QX5YHW46ZCDQJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OHQ77U5UJOEC3QX5YHW46ZCDQJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:OHQ77U5UJOEC3QX5YHW46ZCDQJ","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":"0ac6da4474e0abc6e3dc57ad2189ae8b14c62ba018e51bcba23b7c7cca8cbb81","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-10-02T09:45:15Z","title_canon_sha256":"3e4ee54547630d38b0aba1a12db5d846ff354b17856d72473fac8311f0fcc5a4"},"schema_version":"1.0","source":{"id":"1810.01140","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.01140","created_at":"2026-05-18T00:03:55Z"},{"alias_kind":"arxiv_version","alias_value":"1810.01140v2","created_at":"2026-05-18T00:03:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.01140","created_at":"2026-05-18T00:03:55Z"},{"alias_kind":"pith_short_12","alias_value":"OHQ77U5UJOEC","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OHQ77U5UJOEC3QX5","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OHQ77U5U","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:0be5e5e006a5dee6f50a92f61edb53a6c764ac93cdc2e5550aa92b59f8f9f7aa","target":"graph","created_at":"2026-05-18T00:03:55Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"In real world scenarios, model accuracy is hardly the only factor to consider. Large models consume more memory and are computationally more intensive, which makes them difficult to train and to deploy, especially on mobile devices. In this paper, we build on recent results at the crossroads of Linear Algebra and Deep Learning which demonstrate how imposing a structure on large weight matrices can be used to reduce the size of the model. We propose very compact models for video classification based on state-of-the-art network architectures such as Deep Bag-of-Frames, NetVLAD and NetFisherVecto","authors_text":"Alexandre Araujo, Benjamin Negrevergne, Jamal Atif, Yann Chevaleyre","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-10-02T09:45:15Z","title":"Training compact deep learning models for video classification using circulant matrices"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.01140","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:305494188fde5baf3e63b139b3269e300cd03445c6583891e39293f74fddb778","target":"record","created_at":"2026-05-18T00:03:55Z","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":"0ac6da4474e0abc6e3dc57ad2189ae8b14c62ba018e51bcba23b7c7cca8cbb81","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-10-02T09:45:15Z","title_canon_sha256":"3e4ee54547630d38b0aba1a12db5d846ff354b17856d72473fac8311f0fcc5a4"},"schema_version":"1.0","source":{"id":"1810.01140","kind":"arxiv","version":2}},"canonical_sha256":"71e1ffd3b44b882dc2fdc1edcf64438264a37fca6b40a076c5c31f4fe487e183","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71e1ffd3b44b882dc2fdc1edcf64438264a37fca6b40a076c5c31f4fe487e183","first_computed_at":"2026-05-18T00:03:55.238971Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:03:55.238971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DDNL8pyU3/VMEdC7mmE+1+Wyt+TgjcxjdVrCJ0xn4rNmoq5ZH3zjgJaMdsYQPYnWsue0iZoEkkMxHD/6GSUeDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:03:55.239494Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.01140","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:305494188fde5baf3e63b139b3269e300cd03445c6583891e39293f74fddb778","sha256:0be5e5e006a5dee6f50a92f61edb53a6c764ac93cdc2e5550aa92b59f8f9f7aa"],"state_sha256":"8524c45ad8eb01f0dfb8918b603da20de1922fabc2080ba4f1c68b584f98242f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EkrH3Y709i4STcZj6HfKGT3P8VaLcD4KEbKCgg9PjF2iU9+hreCZQHZ4LRSRFAUOd5a77quq6D9CwX44LLTRDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T09:14:24.450208Z","bundle_sha256":"f8161a75031bd9e1b7311060c07fa0fba883331f643562a5bf202f00d82e023e"}}