{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:7NGH3HZ2TFXALEJYQMYE4GZFSG","short_pith_number":"pith:7NGH3HZ2","canonical_record":{"source":{"id":"2002.03844","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-07T06:42:12Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"6e2af06cf9c7715a34233d9495348c9e07d7bf326b051845fbdde554b03a9d5d","abstract_canon_sha256":"ae4094d7c0e6249bdd79501d17dd4820af5244be970f04d2abe055a04a0b1487"},"schema_version":"1.0"},"canonical_sha256":"fb4c7d9f3a996e05913883304e1b2591996680f9df6700d9815fe9980e4ce900","source":{"kind":"arxiv","id":"2002.03844","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.03844","created_at":"2026-07-05T01:08:27Z"},{"alias_kind":"arxiv_version","alias_value":"2002.03844v2","created_at":"2026-07-05T01:08:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.03844","created_at":"2026-07-05T01:08:27Z"},{"alias_kind":"pith_short_12","alias_value":"7NGH3HZ2TFXA","created_at":"2026-07-05T01:08:27Z"},{"alias_kind":"pith_short_16","alias_value":"7NGH3HZ2TFXALEJY","created_at":"2026-07-05T01:08:27Z"},{"alias_kind":"pith_short_8","alias_value":"7NGH3HZ2","created_at":"2026-07-05T01:08:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:7NGH3HZ2TFXALEJYQMYE4GZFSG","target":"record","payload":{"canonical_record":{"source":{"id":"2002.03844","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-07T06:42:12Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"6e2af06cf9c7715a34233d9495348c9e07d7bf326b051845fbdde554b03a9d5d","abstract_canon_sha256":"ae4094d7c0e6249bdd79501d17dd4820af5244be970f04d2abe055a04a0b1487"},"schema_version":"1.0"},"canonical_sha256":"fb4c7d9f3a996e05913883304e1b2591996680f9df6700d9815fe9980e4ce900","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:08:27.621970Z","signature_b64":"GgdNX70R/rjpjif1RsIpxPC8+kTYbrYnAk6Fj4iEiahxDPyUIybj2KyQJy9a32XTCvzfpJRaZQhIlfVzZc0bBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb4c7d9f3a996e05913883304e1b2591996680f9df6700d9815fe9980e4ce900","last_reissued_at":"2026-07-05T01:08:27.621562Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:08:27.621562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.03844","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":"2026-07-05T01:08:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x56LLomsIcp/qLyuapSH1StVCkDgdup2l4kJOhTeLpeXeuo2c6SvBQmrOm+8ZPISuTMEGbbcpQGz5R+kjpMGDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:43:03.691951Z"},"content_sha256":"76fed18b4cb57a5c1695a2988e889bb11f4c15b273caaed875270236b3b95e31","schema_version":"1.0","event_id":"sha256:76fed18b4cb57a5c1695a2988e889bb11f4c15b273caaed875270236b3b95e31"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:7NGH3HZ2TFXALEJYQMYE4GZFSG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploiting Temporal Coherence for Multi-modal Video Categorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Chul Lee, Palash Goyal, Saurabh Sahu, Shalini Ghosh","submitted_at":"2020-02-07T06:42:12Z","abstract_excerpt":"Multimodal ML models can process data in multiple modalities (e.g., video, images, audio, text) and are useful for video content analysis in a variety of problems (e.g., object detection, scene understanding). In this paper, we focus on the problem of video categorization by using a multimodal approach. We have developed a novel temporal coherence-based regularization approach, which applies to different types of models (e.g., RNN, NetVLAD, Transformer). We demonstrate through experiments how our proposed multimodal video categorization models with temporal coherence out-perform strong state-o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.03844","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/2002.03844/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":"2026-07-05T01:08:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oKpbhsDg96mmRQMhCU8MvYCO4/yswjsIoAIcyNcdWnwJ3sxpbolocjae2OxQtIf2dmInfLeFgDVpz3ud1BRGCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:43:03.692334Z"},"content_sha256":"857d78dff2cf1c7bef1779d5eb64cb758c9cd8d957d8aee08d4ab789991e0496","schema_version":"1.0","event_id":"sha256:857d78dff2cf1c7bef1779d5eb64cb758c9cd8d957d8aee08d4ab789991e0496"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7NGH3HZ2TFXALEJYQMYE4GZFSG/bundle.json","state_url":"https://pith.science/pith/7NGH3HZ2TFXALEJYQMYE4GZFSG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7NGH3HZ2TFXALEJYQMYE4GZFSG/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":"2026-07-06T18:43:03Z","links":{"resolver":"https://pith.science/pith/7NGH3HZ2TFXALEJYQMYE4GZFSG","bundle":"https://pith.science/pith/7NGH3HZ2TFXALEJYQMYE4GZFSG/bundle.json","state":"https://pith.science/pith/7NGH3HZ2TFXALEJYQMYE4GZFSG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7NGH3HZ2TFXALEJYQMYE4GZFSG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7NGH3HZ2TFXALEJYQMYE4GZFSG","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":"ae4094d7c0e6249bdd79501d17dd4820af5244be970f04d2abe055a04a0b1487","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-07T06:42:12Z","title_canon_sha256":"6e2af06cf9c7715a34233d9495348c9e07d7bf326b051845fbdde554b03a9d5d"},"schema_version":"1.0","source":{"id":"2002.03844","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.03844","created_at":"2026-07-05T01:08:27Z"},{"alias_kind":"arxiv_version","alias_value":"2002.03844v2","created_at":"2026-07-05T01:08:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.03844","created_at":"2026-07-05T01:08:27Z"},{"alias_kind":"pith_short_12","alias_value":"7NGH3HZ2TFXA","created_at":"2026-07-05T01:08:27Z"},{"alias_kind":"pith_short_16","alias_value":"7NGH3HZ2TFXALEJY","created_at":"2026-07-05T01:08:27Z"},{"alias_kind":"pith_short_8","alias_value":"7NGH3HZ2","created_at":"2026-07-05T01:08:27Z"}],"graph_snapshots":[{"event_id":"sha256:857d78dff2cf1c7bef1779d5eb64cb758c9cd8d957d8aee08d4ab789991e0496","target":"graph","created_at":"2026-07-05T01:08:27Z","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/2002.03844/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal ML models can process data in multiple modalities (e.g., video, images, audio, text) and are useful for video content analysis in a variety of problems (e.g., object detection, scene understanding). In this paper, we focus on the problem of video categorization by using a multimodal approach. We have developed a novel temporal coherence-based regularization approach, which applies to different types of models (e.g., RNN, NetVLAD, Transformer). We demonstrate through experiments how our proposed multimodal video categorization models with temporal coherence out-perform strong state-o","authors_text":"Chul Lee, Palash Goyal, Saurabh Sahu, Shalini Ghosh","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-07T06:42:12Z","title":"Exploiting Temporal Coherence for Multi-modal Video Categorization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.03844","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":"sha256:76fed18b4cb57a5c1695a2988e889bb11f4c15b273caaed875270236b3b95e31","target":"record","created_at":"2026-07-05T01:08:27Z","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":"ae4094d7c0e6249bdd79501d17dd4820af5244be970f04d2abe055a04a0b1487","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-07T06:42:12Z","title_canon_sha256":"6e2af06cf9c7715a34233d9495348c9e07d7bf326b051845fbdde554b03a9d5d"},"schema_version":"1.0","source":{"id":"2002.03844","kind":"arxiv","version":2}},"canonical_sha256":"fb4c7d9f3a996e05913883304e1b2591996680f9df6700d9815fe9980e4ce900","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb4c7d9f3a996e05913883304e1b2591996680f9df6700d9815fe9980e4ce900","first_computed_at":"2026-07-05T01:08:27.621562Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:08:27.621562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GgdNX70R/rjpjif1RsIpxPC8+kTYbrYnAk6Fj4iEiahxDPyUIybj2KyQJy9a32XTCvzfpJRaZQhIlfVzZc0bBg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:08:27.621970Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.03844","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76fed18b4cb57a5c1695a2988e889bb11f4c15b273caaed875270236b3b95e31","sha256:857d78dff2cf1c7bef1779d5eb64cb758c9cd8d957d8aee08d4ab789991e0496"],"state_sha256":"1d6bb1cdd81a9bd77cadb3a82fb110d4d162c3f050650334137171ad059fe555"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EzDPDDRWMeHZaQpEDQeoFsJ2m2jkkEwGfX0eyWPEe7tc9kza4jP/BshR0+hLCrUzEu6/RAnyHHM9SAQxM4fACw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:43:03.694300Z","bundle_sha256":"e15694169ec9fe1c92b317227db282c721aff8a456d3ba91331ed8d099951793"}}