{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:CYYI3EXQZEC7ZJSPVFROI3CWW7","short_pith_number":"pith:CYYI3EXQ","canonical_record":{"source":{"id":"2106.14587","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.AT","submitted_at":"2021-06-28T11:50:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7057ddfd3c44abdbe7346c8190f25258610e38435b50e6aa9944c2ccf8cc223c","abstract_canon_sha256":"06ec47536f8f02002d45c64d9e952c6b2183a7311edc24c66a9ca88b458060bb"},"schema_version":"1.0"},"canonical_sha256":"16308d92f0c905fca64fa962e46c56b7d00d9a57fbb895700866c0800360de0c","source":{"kind":"arxiv","id":"2106.14587","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.14587","created_at":"2026-07-05T04:32:11Z"},{"alias_kind":"arxiv_version","alias_value":"2106.14587v3","created_at":"2026-07-05T04:32:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.14587","created_at":"2026-07-05T04:32:11Z"},{"alias_kind":"pith_short_12","alias_value":"CYYI3EXQZEC7","created_at":"2026-07-05T04:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"CYYI3EXQZEC7ZJSP","created_at":"2026-07-05T04:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"CYYI3EXQ","created_at":"2026-07-05T04:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:CYYI3EXQZEC7ZJSPVFROI3CWW7","target":"record","payload":{"canonical_record":{"source":{"id":"2106.14587","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.AT","submitted_at":"2021-06-28T11:50:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7057ddfd3c44abdbe7346c8190f25258610e38435b50e6aa9944c2ccf8cc223c","abstract_canon_sha256":"06ec47536f8f02002d45c64d9e952c6b2183a7311edc24c66a9ca88b458060bb"},"schema_version":"1.0"},"canonical_sha256":"16308d92f0c905fca64fa962e46c56b7d00d9a57fbb895700866c0800360de0c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:11.078515Z","signature_b64":"5jsUJK/SwePgcd1g7myIJ0mCABPH68eaUy+TEjESnDKXPg/5rPIkCWqBuegvzp1wvPNNK7UX0z4RwIv0Tn1MAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16308d92f0c905fca64fa962e46c56b7d00d9a57fbb895700866c0800360de0c","last_reissued_at":"2026-07-05T04:32:11.078042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:11.078042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.14587","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:32:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PA9ONHqoCMR7wSbluDbJWhiEKt8+04NpmQuLHlJhq5E9NOvSH/IpFHLp0d0YnNK5N1gB2EWWIiylFguuzChIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:16:25.672948Z"},"content_sha256":"740b30f9f129546b96a285498d810779d1ad31e2c417847317382255c9997980","schema_version":"1.0","event_id":"sha256:740b30f9f129546b96a285498d810779d1ad31e2c417847317382255c9997980"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:CYYI3EXQZEC7ZJSPVFROI3CWW7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Topos and Stacks of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"math.AT","authors_text":"Daniel Bennequin, Jean-Claude Belfiore","submitted_at":"2021-06-28T11:50:06Z","abstract_excerpt":"Every known artificial deep neural network (DNN) corresponds to an object in a canonical Grothendieck's topos; its learning dynamic corresponds to a flow of morphisms in this topos. Invariance structures in the layers (like CNNs or LSTMs) correspond to Giraud's stacks. This invariance is supposed to be responsible of the generalization property, that is extrapolation from learning data under constraints. The fibers represent pre-semantic categories (Culioli, Thom), over which artificial languages are defined, with internal logics, intuitionist, classical or linear (Girard). Semantic functionin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.14587","kind":"arxiv","version":3},"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/2106.14587/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:32:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HjpGw1lEA5NNb430IxVAx4TtC2c3YacwXpsL2xUFr+VlGMxR04rayZsoiHo/8qTjoEyB/gamZXdwLrx3+LOWCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:16:25.673845Z"},"content_sha256":"0eb3fbb7cb03294c79f9cc83330f49c77917db4feb2e9fd3302a74d48f22e473","schema_version":"1.0","event_id":"sha256:0eb3fbb7cb03294c79f9cc83330f49c77917db4feb2e9fd3302a74d48f22e473"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CYYI3EXQZEC7ZJSPVFROI3CWW7/bundle.json","state_url":"https://pith.science/pith/CYYI3EXQZEC7ZJSPVFROI3CWW7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CYYI3EXQZEC7ZJSPVFROI3CWW7/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":"2026-08-07T12:16:25Z","links":{"resolver":"https://pith.science/pith/CYYI3EXQZEC7ZJSPVFROI3CWW7","bundle":"https://pith.science/pith/CYYI3EXQZEC7ZJSPVFROI3CWW7/bundle.json","state":"https://pith.science/pith/CYYI3EXQZEC7ZJSPVFROI3CWW7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CYYI3EXQZEC7ZJSPVFROI3CWW7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CYYI3EXQZEC7ZJSPVFROI3CWW7","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":"06ec47536f8f02002d45c64d9e952c6b2183a7311edc24c66a9ca88b458060bb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.AT","submitted_at":"2021-06-28T11:50:06Z","title_canon_sha256":"7057ddfd3c44abdbe7346c8190f25258610e38435b50e6aa9944c2ccf8cc223c"},"schema_version":"1.0","source":{"id":"2106.14587","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.14587","created_at":"2026-07-05T04:32:11Z"},{"alias_kind":"arxiv_version","alias_value":"2106.14587v3","created_at":"2026-07-05T04:32:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.14587","created_at":"2026-07-05T04:32:11Z"},{"alias_kind":"pith_short_12","alias_value":"CYYI3EXQZEC7","created_at":"2026-07-05T04:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"CYYI3EXQZEC7ZJSP","created_at":"2026-07-05T04:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"CYYI3EXQ","created_at":"2026-07-05T04:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:0eb3fbb7cb03294c79f9cc83330f49c77917db4feb2e9fd3302a74d48f22e473","target":"graph","created_at":"2026-07-05T04:32:11Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2106.14587/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Every known artificial deep neural network (DNN) corresponds to an object in a canonical Grothendieck's topos; its learning dynamic corresponds to a flow of morphisms in this topos. Invariance structures in the layers (like CNNs or LSTMs) correspond to Giraud's stacks. This invariance is supposed to be responsible of the generalization property, that is extrapolation from learning data under constraints. The fibers represent pre-semantic categories (Culioli, Thom), over which artificial languages are defined, with internal logics, intuitionist, classical or linear (Girard). Semantic functionin","authors_text":"Daniel Bennequin, Jean-Claude Belfiore","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.AT","submitted_at":"2021-06-28T11:50:06Z","title":"Topos and Stacks of Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.14587","kind":"arxiv","version":3},"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":"sha256:740b30f9f129546b96a285498d810779d1ad31e2c417847317382255c9997980","target":"record","created_at":"2026-07-05T04:32:11Z","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":"06ec47536f8f02002d45c64d9e952c6b2183a7311edc24c66a9ca88b458060bb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.AT","submitted_at":"2021-06-28T11:50:06Z","title_canon_sha256":"7057ddfd3c44abdbe7346c8190f25258610e38435b50e6aa9944c2ccf8cc223c"},"schema_version":"1.0","source":{"id":"2106.14587","kind":"arxiv","version":3}},"canonical_sha256":"16308d92f0c905fca64fa962e46c56b7d00d9a57fbb895700866c0800360de0c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16308d92f0c905fca64fa962e46c56b7d00d9a57fbb895700866c0800360de0c","first_computed_at":"2026-07-05T04:32:11.078042Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:32:11.078042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5jsUJK/SwePgcd1g7myIJ0mCABPH68eaUy+TEjESnDKXPg/5rPIkCWqBuegvzp1wvPNNK7UX0z4RwIv0Tn1MAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:32:11.078515Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.14587","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:740b30f9f129546b96a285498d810779d1ad31e2c417847317382255c9997980","sha256:0eb3fbb7cb03294c79f9cc83330f49c77917db4feb2e9fd3302a74d48f22e473"],"state_sha256":"ed327c2a52b83865d2876f110be737b11e384df5ef8286f13379581def6dab98"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UmHIf17XKUc9WlWkj0b5CR/z88UkO3rPuodM0PXfShNg1UzcjaYorNizZzCCRAYhtPfZCocj23CJojCc4JN6Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T12:16:25.679490Z","bundle_sha256":"b65ccf7215e4888ce0c68408065565bba96b4d2ff4def6287079d3ef71416142"}}