{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:PTX5EIIXVI3H2FVAZBYBSTFCO3","short_pith_number":"pith:PTX5EIIX","schema_version":"1.0","canonical_sha256":"7cefd22117aa367d16a0c870194ca276e1058e5b34b23349d854f1abdfb32d34","source":{"kind":"arxiv","id":"1701.08435","version":3},"attestation_state":"computed","paper":{"title":"Transformation-Based Models of Video Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Anitha Kannan, Arthur Szlam, Du Tran, Joost van Amersfoort, Marc'Aurelio Ranzato, Soumith Chintala","submitted_at":"2017-01-29T21:39:05Z","abstract_excerpt":"In this work we propose a simple unsupervised approach for next frame prediction in video. Instead of directly predicting the pixels in a frame given past frames, we predict the transformations needed for generating the next frame in a sequence, given the transformations of the past frames. This leads to sharper results, while using a smaller prediction model. In order to enable a fair comparison between different video frame prediction models, we also propose a new evaluation protocol. We use generated frames as input to a classifier trained with ground truth sequences. This criterion guarant"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1701.08435","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-01-29T21:39:05Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"18985f30d55cf69db47b75b99bf32e88467d8d61599fe1ff729b6411b2f47eab","abstract_canon_sha256":"646d432ff0bbaf3f6ed2b59d06f040b0db8ee207570588f613eecb4cab96a702"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:59.212163Z","signature_b64":"ZVW0BKeXb4P9W4VluYO+XXX/3i/O+epyV9PhfdVd8hcV0sDhj10VjyXf5v4DxidfgHPAHbur2UVLW/egnKYmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cefd22117aa367d16a0c870194ca276e1058e5b34b23349d854f1abdfb32d34","last_reissued_at":"2026-07-05T05:38:59.211751Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:59.211751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformation-Based Models of Video Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Anitha Kannan, Arthur Szlam, Du Tran, Joost van Amersfoort, Marc'Aurelio Ranzato, Soumith Chintala","submitted_at":"2017-01-29T21:39:05Z","abstract_excerpt":"In this work we propose a simple unsupervised approach for next frame prediction in video. Instead of directly predicting the pixels in a frame given past frames, we predict the transformations needed for generating the next frame in a sequence, given the transformations of the past frames. This leads to sharper results, while using a smaller prediction model. In order to enable a fair comparison between different video frame prediction models, we also propose a new evaluation protocol. We use generated frames as input to a classifier trained with ground truth sequences. This criterion guarant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.08435","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/1701.08435/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1701.08435","created_at":"2026-07-05T05:38:59.211809+00:00"},{"alias_kind":"arxiv_version","alias_value":"1701.08435v3","created_at":"2026-07-05T05:38:59.211809+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.08435","created_at":"2026-07-05T05:38:59.211809+00:00"},{"alias_kind":"pith_short_12","alias_value":"PTX5EIIXVI3H","created_at":"2026-07-05T05:38:59.211809+00:00"},{"alias_kind":"pith_short_16","alias_value":"PTX5EIIXVI3H2FVA","created_at":"2026-07-05T05:38:59.211809+00:00"},{"alias_kind":"pith_short_8","alias_value":"PTX5EIIX","created_at":"2026-07-05T05:38:59.211809+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00932","citing_title":"FIction: 4D Future Interaction Prediction from Video","ref_index":98,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PTX5EIIXVI3H2FVAZBYBSTFCO3","json":"https://pith.science/pith/PTX5EIIXVI3H2FVAZBYBSTFCO3.json","graph_json":"https://pith.science/api/pith-number/PTX5EIIXVI3H2FVAZBYBSTFCO3/graph.json","events_json":"https://pith.science/api/pith-number/PTX5EIIXVI3H2FVAZBYBSTFCO3/events.json","paper":"https://pith.science/paper/PTX5EIIX"},"agent_actions":{"view_html":"https://pith.science/pith/PTX5EIIXVI3H2FVAZBYBSTFCO3","download_json":"https://pith.science/pith/PTX5EIIXVI3H2FVAZBYBSTFCO3.json","view_paper":"https://pith.science/paper/PTX5EIIX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1701.08435&json=true","fetch_graph":"https://pith.science/api/pith-number/PTX5EIIXVI3H2FVAZBYBSTFCO3/graph.json","fetch_events":"https://pith.science/api/pith-number/PTX5EIIXVI3H2FVAZBYBSTFCO3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PTX5EIIXVI3H2FVAZBYBSTFCO3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PTX5EIIXVI3H2FVAZBYBSTFCO3/action/storage_attestation","attest_author":"https://pith.science/pith/PTX5EIIXVI3H2FVAZBYBSTFCO3/action/author_attestation","sign_citation":"https://pith.science/pith/PTX5EIIXVI3H2FVAZBYBSTFCO3/action/citation_signature","submit_replication":"https://pith.science/pith/PTX5EIIXVI3H2FVAZBYBSTFCO3/action/replication_record"}},"created_at":"2026-07-05T05:38:59.211809+00:00","updated_at":"2026-07-05T05:38:59.211809+00:00"}