{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XA7RLCTCSUVCS7XKDREDHP4HIK","short_pith_number":"pith:XA7RLCTC","canonical_record":{"source":{"id":"2505.19928","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T12:55:27Z","cross_cats_sorted":[],"title_canon_sha256":"af4ff1b7ec253ffb605511ceb1b76949ac3008fdbbc84bdffd3608bbbbfa9f03","abstract_canon_sha256":"0574d5e63e95050e5d9cd6400d403e8bfcedfa024f190b55a3854cf08d0d38c4"},"schema_version":"1.0"},"canonical_sha256":"b83f158a62952a297eea1c4833bf8742a0d238c9974eaf40bae808b1130f17b8","source":{"kind":"arxiv","id":"2505.19928","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19928","created_at":"2026-07-05T11:09:50Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19928v1","created_at":"2026-07-05T11:09:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19928","created_at":"2026-07-05T11:09:50Z"},{"alias_kind":"pith_short_12","alias_value":"XA7RLCTCSUVC","created_at":"2026-07-05T11:09:50Z"},{"alias_kind":"pith_short_16","alias_value":"XA7RLCTCSUVCS7XK","created_at":"2026-07-05T11:09:50Z"},{"alias_kind":"pith_short_8","alias_value":"XA7RLCTC","created_at":"2026-07-05T11:09:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XA7RLCTCSUVCS7XKDREDHP4HIK","target":"record","payload":{"canonical_record":{"source":{"id":"2505.19928","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T12:55:27Z","cross_cats_sorted":[],"title_canon_sha256":"af4ff1b7ec253ffb605511ceb1b76949ac3008fdbbc84bdffd3608bbbbfa9f03","abstract_canon_sha256":"0574d5e63e95050e5d9cd6400d403e8bfcedfa024f190b55a3854cf08d0d38c4"},"schema_version":"1.0"},"canonical_sha256":"b83f158a62952a297eea1c4833bf8742a0d238c9974eaf40bae808b1130f17b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:50.006683Z","signature_b64":"2yt7Nr3H+k5Os1sjSAvzsZAt8+/VvCmaNLfSxK4JMGb8RyhszNTkk2WCezwmSskQDNY4Xt64B0jYdX8IBeEwAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b83f158a62952a297eea1c4833bf8742a0d238c9974eaf40bae808b1130f17b8","last_reissued_at":"2026-07-05T11:09:50.006166Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:50.006166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.19928","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XMWLRZnx3OuDaXQ2PpUwixX7dcSImG8jQ+Zy8uNaBdLxDZl+8Adeew0khi4bAniDf+xgj1Efsu4VJDuBf/vCAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:29:18.015123Z"},"content_sha256":"3292e71502eec745a4c4fb7831edc97045b7d629e7fd82736328d9e87ce68504","schema_version":"1.0","event_id":"sha256:3292e71502eec745a4c4fb7831edc97045b7d629e7fd82736328d9e87ce68504"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XA7RLCTCSUVCS7XKDREDHP4HIK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CA3D: Convolutional-Attentional 3D Nets for Efficient Video Activity Recognition on the Edge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Claudio Gennaro, Fabrizio Falchi, Gabriele Lagani, Giuseppe Amato","submitted_at":"2025-05-26T12:55:27Z","abstract_excerpt":"In this paper, we introduce a deep learning solution for video activity recognition that leverages an innovative combination of convolutional layers with a linear-complexity attention mechanism. Moreover, we introduce a novel quantization mechanism to further improve the efficiency of our model during both training and inference. Our model maintains a reduced computational cost, while preserving robust learning and generalization capabilities. Our approach addresses the issues related to the high computing requirements of current models, with the goal of achieving competitive accuracy on consu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19928","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.19928/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":"2026-07-05T11:09:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mXldQ7ebP6PWy3gil0KgUAy0aQ7nMI4DU8pZnX7O8Y6uk2n6PrPQUEjpaVCK6PRnfvLy7ZTyspnuudovIkN1Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:29:18.015627Z"},"content_sha256":"2ab99a69ae700506fe4261d6abbd2471b1fe2993508b54c9fdcde1d76ba1cef4","schema_version":"1.0","event_id":"sha256:2ab99a69ae700506fe4261d6abbd2471b1fe2993508b54c9fdcde1d76ba1cef4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XA7RLCTCSUVCS7XKDREDHP4HIK/bundle.json","state_url":"https://pith.science/pith/XA7RLCTCSUVCS7XKDREDHP4HIK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XA7RLCTCSUVCS7XKDREDHP4HIK/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":"2026-08-08T01:29:18Z","links":{"resolver":"https://pith.science/pith/XA7RLCTCSUVCS7XKDREDHP4HIK","bundle":"https://pith.science/pith/XA7RLCTCSUVCS7XKDREDHP4HIK/bundle.json","state":"https://pith.science/pith/XA7RLCTCSUVCS7XKDREDHP4HIK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XA7RLCTCSUVCS7XKDREDHP4HIK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XA7RLCTCSUVCS7XKDREDHP4HIK","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":"0574d5e63e95050e5d9cd6400d403e8bfcedfa024f190b55a3854cf08d0d38c4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T12:55:27Z","title_canon_sha256":"af4ff1b7ec253ffb605511ceb1b76949ac3008fdbbc84bdffd3608bbbbfa9f03"},"schema_version":"1.0","source":{"id":"2505.19928","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19928","created_at":"2026-07-05T11:09:50Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19928v1","created_at":"2026-07-05T11:09:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19928","created_at":"2026-07-05T11:09:50Z"},{"alias_kind":"pith_short_12","alias_value":"XA7RLCTCSUVC","created_at":"2026-07-05T11:09:50Z"},{"alias_kind":"pith_short_16","alias_value":"XA7RLCTCSUVCS7XK","created_at":"2026-07-05T11:09:50Z"},{"alias_kind":"pith_short_8","alias_value":"XA7RLCTC","created_at":"2026-07-05T11:09:50Z"}],"graph_snapshots":[{"event_id":"sha256:2ab99a69ae700506fe4261d6abbd2471b1fe2993508b54c9fdcde1d76ba1cef4","target":"graph","created_at":"2026-07-05T11:09:50Z","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/2505.19928/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce a deep learning solution for video activity recognition that leverages an innovative combination of convolutional layers with a linear-complexity attention mechanism. Moreover, we introduce a novel quantization mechanism to further improve the efficiency of our model during both training and inference. Our model maintains a reduced computational cost, while preserving robust learning and generalization capabilities. Our approach addresses the issues related to the high computing requirements of current models, with the goal of achieving competitive accuracy on consu","authors_text":"Claudio Gennaro, Fabrizio Falchi, Gabriele Lagani, Giuseppe Amato","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T12:55:27Z","title":"CA3D: Convolutional-Attentional 3D Nets for Efficient Video Activity Recognition on the Edge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19928","kind":"arxiv","version":1},"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":"sha256:3292e71502eec745a4c4fb7831edc97045b7d629e7fd82736328d9e87ce68504","target":"record","created_at":"2026-07-05T11:09:50Z","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":"0574d5e63e95050e5d9cd6400d403e8bfcedfa024f190b55a3854cf08d0d38c4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T12:55:27Z","title_canon_sha256":"af4ff1b7ec253ffb605511ceb1b76949ac3008fdbbc84bdffd3608bbbbfa9f03"},"schema_version":"1.0","source":{"id":"2505.19928","kind":"arxiv","version":1}},"canonical_sha256":"b83f158a62952a297eea1c4833bf8742a0d238c9974eaf40bae808b1130f17b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b83f158a62952a297eea1c4833bf8742a0d238c9974eaf40bae808b1130f17b8","first_computed_at":"2026-07-05T11:09:50.006166Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:50.006166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2yt7Nr3H+k5Os1sjSAvzsZAt8+/VvCmaNLfSxK4JMGb8RyhszNTkk2WCezwmSskQDNY4Xt64B0jYdX8IBeEwAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:50.006683Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19928","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3292e71502eec745a4c4fb7831edc97045b7d629e7fd82736328d9e87ce68504","sha256:2ab99a69ae700506fe4261d6abbd2471b1fe2993508b54c9fdcde1d76ba1cef4"],"state_sha256":"eacb11da3fd72432c4db10d8fcfe43818b1fd0dcd6cd95e1aba250b78b1a9624"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XPfxFbt6UtppRAqBJnFxQTXzKoKIjaOI678oWBdK1UyUkGEHUcpkJnJ0rtK9THQuQxkhjATHWEdxT7sbXcwBAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T01:29:18.020618Z","bundle_sha256":"ae6cc9c4404de052bf46b5c4a2c9e491f91ac5c4068bfc350f0de645bd0aa6bc"}}