{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:WEEDQWDP36HQ2X6JTIVREZ7YF4","short_pith_number":"pith:WEEDQWDP","canonical_record":{"source":{"id":"1902.10640","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-02-27T17:13:17Z","cross_cats_sorted":[],"title_canon_sha256":"00b35cc88540e2e4b61d9fe3442e329b9ed9a1ecdb2555e0e3cb18856346f0b3","abstract_canon_sha256":"ac458d87c6161cb73f36af898a43768720e6141e522a71e5f469f09a3d487872"},"schema_version":"1.0"},"canonical_sha256":"b10838586fdf8f0d5fc99a2b1267f82f18cae3e3b7f882f523036b70131d80fb","source":{"kind":"arxiv","id":"1902.10640","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.10640","created_at":"2026-05-17T23:52:30Z"},{"alias_kind":"arxiv_version","alias_value":"1902.10640v1","created_at":"2026-05-17T23:52:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10640","created_at":"2026-05-17T23:52:30Z"},{"alias_kind":"pith_short_12","alias_value":"WEEDQWDP36HQ","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"WEEDQWDP36HQ2X6J","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"WEEDQWDP","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:WEEDQWDP36HQ2X6JTIVREZ7YF4","target":"record","payload":{"canonical_record":{"source":{"id":"1902.10640","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-02-27T17:13:17Z","cross_cats_sorted":[],"title_canon_sha256":"00b35cc88540e2e4b61d9fe3442e329b9ed9a1ecdb2555e0e3cb18856346f0b3","abstract_canon_sha256":"ac458d87c6161cb73f36af898a43768720e6141e522a71e5f469f09a3d487872"},"schema_version":"1.0"},"canonical_sha256":"b10838586fdf8f0d5fc99a2b1267f82f18cae3e3b7f882f523036b70131d80fb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:30.340964Z","signature_b64":"RzdAgwJxpmD+1mAnZi811Mxnw8TfIj36Ij21a0JIhQ1ZowLlHYofH09IUfAWafU6F+kSgPgVmMvEPcH8AKFyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b10838586fdf8f0d5fc99a2b1267f82f18cae3e3b7f882f523036b70131d80fb","last_reissued_at":"2026-05-17T23:52:30.340439Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:30.340439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.10640","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":"2026-05-17T23:52:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zHoW4EapKbm3F9GMTQP3Eeu0+7mETYBO0PCWN4AOxuo0K08edPiw1rxnUbQ++wY991UxHu9rLbW52Adz4rGDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T20:28:50.028958Z"},"content_sha256":"9f251b38b75d525e424237d29f56d6791636e5e2db8bc70d4017e3c81cd2bc3e","schema_version":"1.0","event_id":"sha256:9f251b38b75d525e424237d29f56d6791636e5e2db8bc70d4017e3c81cd2bc3e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:WEEDQWDP36HQ2X6JTIVREZ7YF4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Video Classification Using Fewer Frames","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mitesh M. Khapra, Mukundhan Srinivasan, Shweta Bhardwaj","submitted_at":"2019-02-27T17:13:17Z","abstract_excerpt":"Recently,there has been a lot of interest in building compact models for video classification which have a small memory footprint (<1 GB). While these models are compact, they typically operate by repeated application of a small weight matrix to all the frames in a video. E.g. recurrent neural network based methods compute a hidden state for every frame of the video using a recurrent weight matrix. Similarly, cluster-and-aggregate based methods such as NetVLAD, have a learnable clustering matrix which is used to assign soft-clusters to every frame in the video. Since these models look at every"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10640","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":""},"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":"2026-05-17T23:52:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nfKWUsbAZbc2E5wocrbo0rZCo2U+B6hB6NVJpr+mpJo4qng5gNqmGYppAH6skXI9h+KmWz/6yUhjKFarwMM1AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T20:28:50.029306Z"},"content_sha256":"6bae0aa09be02b27190fd6b87966a3ea32a4304a3698917f73529cdf93905061","schema_version":"1.0","event_id":"sha256:6bae0aa09be02b27190fd6b87966a3ea32a4304a3698917f73529cdf93905061"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WEEDQWDP36HQ2X6JTIVREZ7YF4/bundle.json","state_url":"https://pith.science/pith/WEEDQWDP36HQ2X6JTIVREZ7YF4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WEEDQWDP36HQ2X6JTIVREZ7YF4/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":"2026-05-30T20:28:50Z","links":{"resolver":"https://pith.science/pith/WEEDQWDP36HQ2X6JTIVREZ7YF4","bundle":"https://pith.science/pith/WEEDQWDP36HQ2X6JTIVREZ7YF4/bundle.json","state":"https://pith.science/pith/WEEDQWDP36HQ2X6JTIVREZ7YF4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WEEDQWDP36HQ2X6JTIVREZ7YF4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:WEEDQWDP36HQ2X6JTIVREZ7YF4","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":"ac458d87c6161cb73f36af898a43768720e6141e522a71e5f469f09a3d487872","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-02-27T17:13:17Z","title_canon_sha256":"00b35cc88540e2e4b61d9fe3442e329b9ed9a1ecdb2555e0e3cb18856346f0b3"},"schema_version":"1.0","source":{"id":"1902.10640","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.10640","created_at":"2026-05-17T23:52:30Z"},{"alias_kind":"arxiv_version","alias_value":"1902.10640v1","created_at":"2026-05-17T23:52:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10640","created_at":"2026-05-17T23:52:30Z"},{"alias_kind":"pith_short_12","alias_value":"WEEDQWDP36HQ","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"WEEDQWDP36HQ2X6J","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"WEEDQWDP","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:6bae0aa09be02b27190fd6b87966a3ea32a4304a3698917f73529cdf93905061","target":"graph","created_at":"2026-05-17T23:52:30Z","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":"Recently,there has been a lot of interest in building compact models for video classification which have a small memory footprint (<1 GB). While these models are compact, they typically operate by repeated application of a small weight matrix to all the frames in a video. E.g. recurrent neural network based methods compute a hidden state for every frame of the video using a recurrent weight matrix. Similarly, cluster-and-aggregate based methods such as NetVLAD, have a learnable clustering matrix which is used to assign soft-clusters to every frame in the video. Since these models look at every","authors_text":"Mitesh M. Khapra, Mukundhan Srinivasan, Shweta Bhardwaj","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-02-27T17:13:17Z","title":"Efficient Video Classification Using Fewer Frames"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10640","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":"sha256:9f251b38b75d525e424237d29f56d6791636e5e2db8bc70d4017e3c81cd2bc3e","target":"record","created_at":"2026-05-17T23:52:30Z","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":"ac458d87c6161cb73f36af898a43768720e6141e522a71e5f469f09a3d487872","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-02-27T17:13:17Z","title_canon_sha256":"00b35cc88540e2e4b61d9fe3442e329b9ed9a1ecdb2555e0e3cb18856346f0b3"},"schema_version":"1.0","source":{"id":"1902.10640","kind":"arxiv","version":1}},"canonical_sha256":"b10838586fdf8f0d5fc99a2b1267f82f18cae3e3b7f882f523036b70131d80fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b10838586fdf8f0d5fc99a2b1267f82f18cae3e3b7f882f523036b70131d80fb","first_computed_at":"2026-05-17T23:52:30.340439Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:30.340439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RzdAgwJxpmD+1mAnZi811Mxnw8TfIj36Ij21a0JIhQ1ZowLlHYofH09IUfAWafU6F+kSgPgVmMvEPcH8AKFyBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:30.340964Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.10640","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f251b38b75d525e424237d29f56d6791636e5e2db8bc70d4017e3c81cd2bc3e","sha256:6bae0aa09be02b27190fd6b87966a3ea32a4304a3698917f73529cdf93905061"],"state_sha256":"632e2ebbbf2280af2e989268fa9fa34f03acc8c4736b5978c9a517ad89b9db47"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n8Fw9ILnWvIZt8HdppdMCAfV2QN7AV2Q4DWT3DLTSXo5+K5Hc+PSk4L4dlEXpX3hzZrfibjILirioBKpDtGTBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T20:28:50.031808Z","bundle_sha256":"bb45ed21faf10d69224207e24a44010902a92fa29ef0cf3bf2fd2ad3a605dfeb"}}