{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:M5NHT5SFPDTT734B3SPCYB5KZC","short_pith_number":"pith:M5NHT5SF","canonical_record":{"source":{"id":"1906.03857","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-10T09:15:52Z","cross_cats_sorted":[],"title_canon_sha256":"aa5655a528c9725c848ee8d111ecd0d4a18788700615364688c87d9fb99cac42","abstract_canon_sha256":"637a453e1729e858e24576ae9f7c22ee32f26c85a49188b4be51a1a29f66f4c4"},"schema_version":"1.0"},"canonical_sha256":"675a79f64578e73fef81dc9e2c07aac88f5984c2df6e4c36e5e78955a5d0f862","source":{"kind":"arxiv","id":"1906.03857","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03857","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03857v2","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03857","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"pith_short_12","alias_value":"M5NHT5SFPDTT","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"M5NHT5SFPDTT734B","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"M5NHT5SF","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:M5NHT5SFPDTT734B3SPCYB5KZC","target":"record","payload":{"canonical_record":{"source":{"id":"1906.03857","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-10T09:15:52Z","cross_cats_sorted":[],"title_canon_sha256":"aa5655a528c9725c848ee8d111ecd0d4a18788700615364688c87d9fb99cac42","abstract_canon_sha256":"637a453e1729e858e24576ae9f7c22ee32f26c85a49188b4be51a1a29f66f4c4"},"schema_version":"1.0"},"canonical_sha256":"675a79f64578e73fef81dc9e2c07aac88f5984c2df6e4c36e5e78955a5d0f862","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:32.446745Z","signature_b64":"vL577t1HNE+FX97Lg0y4IaoVi/odrVwe7UeBj1k98rHhF0n6WgidCIqSsebdkl+GM7UllrfjZEyws7H9yy8BAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"675a79f64578e73fef81dc9e2c07aac88f5984c2df6e4c36e5e78955a5d0f862","last_reissued_at":"2026-05-17T23:43:32.446312Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:32.446312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.03857","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":"2026-05-17T23:43:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mI1+MQXmxjPRTN14LhIOfsXOKrjlKZYMDMYA8seRB5RjHGGpbAZ7Zg7mJEoBJQXwhYFFRMqQ8E9XazcWUxCWCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T05:03:11.065413Z"},"content_sha256":"954af956f4538dd0e66eaec16c87e2d5262643ef54b1cfda40287e28017b00aa","schema_version":"1.0","event_id":"sha256:954af956f4538dd0e66eaec16c87e2d5262643ef54b1cfda40287e28017b00aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:M5NHT5SFPDTT734B3SPCYB5KZC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UniDual: A Unified Model for Image and Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Du Tran, Lorenzo Torresani, Yufei Wang","submitted_at":"2019-06-10T09:15:52Z","abstract_excerpt":"Although a video is effectively a sequence of images, visual perception systems typically model images and videos separately, thus failing to exploit the correlation and the synergy provided by these two media. While a few prior research efforts have explored the benefits of leveraging still-image datasets for video analysis, or vice-versa, most of these attempts have been limited to pretraining a model on one type of visual modality and then adapting it via finetuning on the other modality. In contrast, in this paper we introduce a framework that enables joint training of a unified model on m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03857","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":""},"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":"2026-05-17T23:43:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mGW8HDcZWPvagKWK1pcn1/lcf7xQIPJvLVgLjrwm0b+2EbuI3u85w1km+EeL7lHNgMfNCdTxx1Er0SJ866uUBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T05:03:11.065772Z"},"content_sha256":"332bc80d18582ea5cde6f600b2af070a36d377d204a59bed39405bd0e9474abb","schema_version":"1.0","event_id":"sha256:332bc80d18582ea5cde6f600b2af070a36d377d204a59bed39405bd0e9474abb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M5NHT5SFPDTT734B3SPCYB5KZC/bundle.json","state_url":"https://pith.science/pith/M5NHT5SFPDTT734B3SPCYB5KZC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M5NHT5SFPDTT734B3SPCYB5KZC/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":"2026-06-02T05:03:11Z","links":{"resolver":"https://pith.science/pith/M5NHT5SFPDTT734B3SPCYB5KZC","bundle":"https://pith.science/pith/M5NHT5SFPDTT734B3SPCYB5KZC/bundle.json","state":"https://pith.science/pith/M5NHT5SFPDTT734B3SPCYB5KZC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M5NHT5SFPDTT734B3SPCYB5KZC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:M5NHT5SFPDTT734B3SPCYB5KZC","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":"637a453e1729e858e24576ae9f7c22ee32f26c85a49188b4be51a1a29f66f4c4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-10T09:15:52Z","title_canon_sha256":"aa5655a528c9725c848ee8d111ecd0d4a18788700615364688c87d9fb99cac42"},"schema_version":"1.0","source":{"id":"1906.03857","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03857","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03857v2","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03857","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"pith_short_12","alias_value":"M5NHT5SFPDTT","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"M5NHT5SFPDTT734B","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"M5NHT5SF","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:332bc80d18582ea5cde6f600b2af070a36d377d204a59bed39405bd0e9474abb","target":"graph","created_at":"2026-05-17T23:43:32Z","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":"Although a video is effectively a sequence of images, visual perception systems typically model images and videos separately, thus failing to exploit the correlation and the synergy provided by these two media. While a few prior research efforts have explored the benefits of leveraging still-image datasets for video analysis, or vice-versa, most of these attempts have been limited to pretraining a model on one type of visual modality and then adapting it via finetuning on the other modality. In contrast, in this paper we introduce a framework that enables joint training of a unified model on m","authors_text":"Du Tran, Lorenzo Torresani, Yufei Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-10T09:15:52Z","title":"UniDual: A Unified Model for Image and Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03857","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":"sha256:954af956f4538dd0e66eaec16c87e2d5262643ef54b1cfda40287e28017b00aa","target":"record","created_at":"2026-05-17T23:43:32Z","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":"637a453e1729e858e24576ae9f7c22ee32f26c85a49188b4be51a1a29f66f4c4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-10T09:15:52Z","title_canon_sha256":"aa5655a528c9725c848ee8d111ecd0d4a18788700615364688c87d9fb99cac42"},"schema_version":"1.0","source":{"id":"1906.03857","kind":"arxiv","version":2}},"canonical_sha256":"675a79f64578e73fef81dc9e2c07aac88f5984c2df6e4c36e5e78955a5d0f862","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"675a79f64578e73fef81dc9e2c07aac88f5984c2df6e4c36e5e78955a5d0f862","first_computed_at":"2026-05-17T23:43:32.446312Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:32.446312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vL577t1HNE+FX97Lg0y4IaoVi/odrVwe7UeBj1k98rHhF0n6WgidCIqSsebdkl+GM7UllrfjZEyws7H9yy8BAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:32.446745Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.03857","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:954af956f4538dd0e66eaec16c87e2d5262643ef54b1cfda40287e28017b00aa","sha256:332bc80d18582ea5cde6f600b2af070a36d377d204a59bed39405bd0e9474abb"],"state_sha256":"4fe857db70cb12e46553db8b2d53a4b56ec77e0340d7e3ee862457de039ce093"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Iw91WDu+SkyrM6yVLk09jMR3iEsyqGx49k99BYwdA+YQdtK/pK1yyi+HY1WAc0LhRW7M6i/UFSLkadIGB9liCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T05:03:11.067669Z","bundle_sha256":"35b4f5bab339e9f4e2c02964ccd61fe5b3414bb199f32ff8e405cd1c896f60a7"}}