{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:PFMAONOMUTJVJ4MXHWIPDV3HOE","short_pith_number":"pith:PFMAONOM","canonical_record":{"source":{"id":"2003.03501","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-07T03:21:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d39fbad5d678fc8a79c679a11247a4f98f4ab4128b755aed1e1d0b437f552510","abstract_canon_sha256":"be14dbf141c8e3b74116af8136c03d9f91a47211f8afcb2795ff92b3c1d0d8a1"},"schema_version":"1.0"},"canonical_sha256":"79580735cca4d354f1973d90f1d767712652f4df0eb5af83e27623cc5dee8955","source":{"kind":"arxiv","id":"2003.03501","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.03501","created_at":"2026-07-05T01:08:28Z"},{"alias_kind":"arxiv_version","alias_value":"2003.03501v3","created_at":"2026-07-05T01:08:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.03501","created_at":"2026-07-05T01:08:28Z"},{"alias_kind":"pith_short_12","alias_value":"PFMAONOMUTJV","created_at":"2026-07-05T01:08:28Z"},{"alias_kind":"pith_short_16","alias_value":"PFMAONOMUTJVJ4MX","created_at":"2026-07-05T01:08:28Z"},{"alias_kind":"pith_short_8","alias_value":"PFMAONOM","created_at":"2026-07-05T01:08:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:PFMAONOMUTJVJ4MXHWIPDV3HOE","target":"record","payload":{"canonical_record":{"source":{"id":"2003.03501","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-07T03:21:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d39fbad5d678fc8a79c679a11247a4f98f4ab4128b755aed1e1d0b437f552510","abstract_canon_sha256":"be14dbf141c8e3b74116af8136c03d9f91a47211f8afcb2795ff92b3c1d0d8a1"},"schema_version":"1.0"},"canonical_sha256":"79580735cca4d354f1973d90f1d767712652f4df0eb5af83e27623cc5dee8955","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:08:28.518901Z","signature_b64":"d6NTVIsywfVZ2DA4r5TgjpP7o+IjXP5GRNC3WFLX4ZDaaCKWzBSw1KURDUWIgMpNG5R3W/2pgA0v30HX6LNKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79580735cca4d354f1973d90f1d767712652f4df0eb5af83e27623cc5dee8955","last_reissued_at":"2026-07-05T01:08:28.518338Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:08:28.518338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.03501","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":"2026-07-05T01:08:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4JLaY4Se9E7xF9JJEE12pcoe757jGVvM9XOVHU+t5YeuLSUP2LlXxs/k01V9R7pPCP+ih+sd0Xi3jzeBgNMDCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:07:26.040617Z"},"content_sha256":"c82101ac67bf0a2f3a8e080c5769a94d98e2707800bff19e49919a0da76ebaf7","schema_version":"1.0","event_id":"sha256:c82101ac67bf0a2f3a8e080c5769a94d98e2707800bff19e49919a0da76ebaf7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:PFMAONOMUTJVJ4MXHWIPDV3HOE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross-modal Learning for Multi-modal Video Categorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chul Lee, Palash Goyal, Saurabh Sahu, Shalini Ghosh","submitted_at":"2020-03-07T03:21:15Z","abstract_excerpt":"Multi-modal machine learning (ML) models can process data in multiple modalities (e.g., video, audio, text) and are useful for video content analysis in a variety of problems (e.g., object detection, scene understanding, activity recognition). In this paper, we focus on the problem of video categorization using a multi-modal ML technique. In particular, we have developed a novel multi-modal ML approach that we call \"cross-modal learning\", where one modality influences another but only when there is correlation between the modalities -- for that, we first train a correlation tower that guides t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.03501","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/2003.03501/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":"2026-07-05T01:08:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1ZeZch/9fP6za6fLnrKiXNJUdDjzgM6R+zcRAYXmRsWaNUHik1MwD5O0oYegSQLSWgEtNLUbxQ97v0XYgL1ODQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:07:26.040996Z"},"content_sha256":"a5105c71d63cc0f9962abf5eb623d61dc61fa0d04ae1c7a6a5fa015e9c38f7f8","schema_version":"1.0","event_id":"sha256:a5105c71d63cc0f9962abf5eb623d61dc61fa0d04ae1c7a6a5fa015e9c38f7f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PFMAONOMUTJVJ4MXHWIPDV3HOE/bundle.json","state_url":"https://pith.science/pith/PFMAONOMUTJVJ4MXHWIPDV3HOE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PFMAONOMUTJVJ4MXHWIPDV3HOE/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":"2026-07-06T19:07:26Z","links":{"resolver":"https://pith.science/pith/PFMAONOMUTJVJ4MXHWIPDV3HOE","bundle":"https://pith.science/pith/PFMAONOMUTJVJ4MXHWIPDV3HOE/bundle.json","state":"https://pith.science/pith/PFMAONOMUTJVJ4MXHWIPDV3HOE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PFMAONOMUTJVJ4MXHWIPDV3HOE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PFMAONOMUTJVJ4MXHWIPDV3HOE","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":"be14dbf141c8e3b74116af8136c03d9f91a47211f8afcb2795ff92b3c1d0d8a1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-07T03:21:15Z","title_canon_sha256":"d39fbad5d678fc8a79c679a11247a4f98f4ab4128b755aed1e1d0b437f552510"},"schema_version":"1.0","source":{"id":"2003.03501","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.03501","created_at":"2026-07-05T01:08:28Z"},{"alias_kind":"arxiv_version","alias_value":"2003.03501v3","created_at":"2026-07-05T01:08:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.03501","created_at":"2026-07-05T01:08:28Z"},{"alias_kind":"pith_short_12","alias_value":"PFMAONOMUTJV","created_at":"2026-07-05T01:08:28Z"},{"alias_kind":"pith_short_16","alias_value":"PFMAONOMUTJVJ4MX","created_at":"2026-07-05T01:08:28Z"},{"alias_kind":"pith_short_8","alias_value":"PFMAONOM","created_at":"2026-07-05T01:08:28Z"}],"graph_snapshots":[{"event_id":"sha256:a5105c71d63cc0f9962abf5eb623d61dc61fa0d04ae1c7a6a5fa015e9c38f7f8","target":"graph","created_at":"2026-07-05T01:08:28Z","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/2003.03501/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal machine learning (ML) models can process data in multiple modalities (e.g., video, audio, text) and are useful for video content analysis in a variety of problems (e.g., object detection, scene understanding, activity recognition). In this paper, we focus on the problem of video categorization using a multi-modal ML technique. In particular, we have developed a novel multi-modal ML approach that we call \"cross-modal learning\", where one modality influences another but only when there is correlation between the modalities -- for that, we first train a correlation tower that guides t","authors_text":"Chul Lee, Palash Goyal, Saurabh Sahu, Shalini Ghosh","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-07T03:21:15Z","title":"Cross-modal Learning for Multi-modal Video Categorization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.03501","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:c82101ac67bf0a2f3a8e080c5769a94d98e2707800bff19e49919a0da76ebaf7","target":"record","created_at":"2026-07-05T01:08:28Z","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":"be14dbf141c8e3b74116af8136c03d9f91a47211f8afcb2795ff92b3c1d0d8a1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-07T03:21:15Z","title_canon_sha256":"d39fbad5d678fc8a79c679a11247a4f98f4ab4128b755aed1e1d0b437f552510"},"schema_version":"1.0","source":{"id":"2003.03501","kind":"arxiv","version":3}},"canonical_sha256":"79580735cca4d354f1973d90f1d767712652f4df0eb5af83e27623cc5dee8955","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79580735cca4d354f1973d90f1d767712652f4df0eb5af83e27623cc5dee8955","first_computed_at":"2026-07-05T01:08:28.518338Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:08:28.518338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d6NTVIsywfVZ2DA4r5TgjpP7o+IjXP5GRNC3WFLX4ZDaaCKWzBSw1KURDUWIgMpNG5R3W/2pgA0v30HX6LNKDg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:08:28.518901Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.03501","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c82101ac67bf0a2f3a8e080c5769a94d98e2707800bff19e49919a0da76ebaf7","sha256:a5105c71d63cc0f9962abf5eb623d61dc61fa0d04ae1c7a6a5fa015e9c38f7f8"],"state_sha256":"14a69d85d4ee4d0f757fec02d0ab283717baf1fa2e296714ba542d6075da5cd6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"odmBFtJpoXOcoz1hJ5TmPjNCnm9JNPeUbb5vAzly0WY8g71kARh3rgJYt17Po8o76jhErje+JPEe7+lb7N3XAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:07:26.043126Z","bundle_sha256":"cc4192e910d9f9e69cd8bd5410655161f7c6691ddae65732da75935b00e4f58c"}}