{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:53EX3UAA4O53ROQVTUBK75SYVM","short_pith_number":"pith:53EX3UAA","schema_version":"1.0","canonical_sha256":"eec97dd000e3bbb8ba159d02aff658ab25cd11fa81f9e29baa6427875b05fbac","source":{"kind":"arxiv","id":"2607.24789","version":1},"attestation_state":"computed","paper":{"title":"NEXT: Reasoning-Driven Video Recommendation via a Vision-Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.MM"],"primary_cat":"cs.IR","authors_text":"Bokai Cao, Ellie Zhu, Harrison Zhao, Hongye Yang, Lei Huang, Lizhu Zhang, Xiangjun Fan, Yuming Liu","submitted_at":"2026-06-27T06:51:58Z","abstract_excerpt":"We present NEXT (Next-interest EXploration Transformer), a reasoning-driven video recommendation framework that reasons over the video a user has just watched, infers the viewer's next intent, and retrieves concrete follow-up videos. Explicit continuations such as episodes are linked directly; implicit cases are handled by generating intent queries and searching for matching candidates. This Item-to-Intent-to-Item formulation produces directed recommendations beyond co-engagement correlation or semantic similarity.\n  To make this framework reliable at scale, we train NEXT-8B, a purpose-trained"},"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":"2607.24789","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-27T06:51:58Z","cross_cats_sorted":["cs.CV","cs.LG","cs.MM"],"title_canon_sha256":"c4c789c3d7322ff142d9c23a21d9369b78f8aea330f4482d008ab9f8e1d14c5a","abstract_canon_sha256":"706f2227ee80969873d5973d7fa20fe6baacfba93d6b98c0feae515074839657"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T00:24:44.233580Z","signature_b64":"+nViF7Mm0h022JtsdzFUXbxtlsfAeeo1GtJdt6C9IsIf9wLbbGGalqH1j/dAQuV45VC7aJwjO3CVuhTEved+Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eec97dd000e3bbb8ba159d02aff658ab25cd11fa81f9e29baa6427875b05fbac","last_reissued_at":"2026-07-29T00:24:44.232759Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T00:24:44.232759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NEXT: Reasoning-Driven Video Recommendation via a Vision-Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.MM"],"primary_cat":"cs.IR","authors_text":"Bokai Cao, Ellie Zhu, Harrison Zhao, Hongye Yang, Lei Huang, Lizhu Zhang, Xiangjun Fan, Yuming Liu","submitted_at":"2026-06-27T06:51:58Z","abstract_excerpt":"We present NEXT (Next-interest EXploration Transformer), a reasoning-driven video recommendation framework that reasons over the video a user has just watched, infers the viewer's next intent, and retrieves concrete follow-up videos. Explicit continuations such as episodes are linked directly; implicit cases are handled by generating intent queries and searching for matching candidates. This Item-to-Intent-to-Item formulation produces directed recommendations beyond co-engagement correlation or semantic similarity.\n  To make this framework reliable at scale, we train NEXT-8B, a purpose-trained"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24789","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.24789/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":"2607.24789","created_at":"2026-07-29T00:24:44.233178+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24789v1","created_at":"2026-07-29T00:24:44.233178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24789","created_at":"2026-07-29T00:24:44.233178+00:00"},{"alias_kind":"pith_short_12","alias_value":"53EX3UAA4O53","created_at":"2026-07-29T00:24:44.233178+00:00"},{"alias_kind":"pith_short_16","alias_value":"53EX3UAA4O53ROQV","created_at":"2026-07-29T00:24:44.233178+00:00"},{"alias_kind":"pith_short_8","alias_value":"53EX3UAA","created_at":"2026-07-29T00:24:44.233178+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/53EX3UAA4O53ROQVTUBK75SYVM","json":"https://pith.science/pith/53EX3UAA4O53ROQVTUBK75SYVM.json","graph_json":"https://pith.science/api/pith-number/53EX3UAA4O53ROQVTUBK75SYVM/graph.json","events_json":"https://pith.science/api/pith-number/53EX3UAA4O53ROQVTUBK75SYVM/events.json","paper":"https://pith.science/paper/53EX3UAA"},"agent_actions":{"view_html":"https://pith.science/pith/53EX3UAA4O53ROQVTUBK75SYVM","download_json":"https://pith.science/pith/53EX3UAA4O53ROQVTUBK75SYVM.json","view_paper":"https://pith.science/paper/53EX3UAA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24789&json=true","fetch_graph":"https://pith.science/api/pith-number/53EX3UAA4O53ROQVTUBK75SYVM/graph.json","fetch_events":"https://pith.science/api/pith-number/53EX3UAA4O53ROQVTUBK75SYVM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/53EX3UAA4O53ROQVTUBK75SYVM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/53EX3UAA4O53ROQVTUBK75SYVM/action/storage_attestation","attest_author":"https://pith.science/pith/53EX3UAA4O53ROQVTUBK75SYVM/action/author_attestation","sign_citation":"https://pith.science/pith/53EX3UAA4O53ROQVTUBK75SYVM/action/citation_signature","submit_replication":"https://pith.science/pith/53EX3UAA4O53ROQVTUBK75SYVM/action/replication_record"}},"created_at":"2026-07-29T00:24:44.233178+00:00","updated_at":"2026-07-29T00:24:44.233178+00:00"}