{"paper":{"title":"AURA 2.0: From User-Driven Responses to Model-Initiated Conversations in Streaming Video","arxiv_id":"2611.17048","primary_cat":"cs.CV","submitted_at":"2026-11-12T16:31:54+00:00","version_compiled":"v1"},"notice":"Every quoted sentence is the authors' text from the arXiv listing abstract. Labels and probabilities are the outputs of classifier-1.13.0 on the question bank abstract-p1-20260923, exactly as returned. No sentence in this record was written by a language model.","schema":"pith.compiled-record/v0","status":"compiled","abstract":{"source":"arXiv listing abstract v1","sentences":[{"i":0,"p":0.68,"id":"s0","own":false,"role":"background","text":"Most AI assistants respond only when prompted, remaining silent even when events in the video stream offer meaningful opportunities for conversation.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.05,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.13,"role_probabilities":{"gap":0.32,"method":0.0,"result":0.0,"background":0.68,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":1.0,"id":"s1","own":true,"role":"contribution","text":"To move beyond purely user-driven interaction, we present AURA 2.0, a streaming video large language model that introduces three core upgrades to AURA.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.88,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.28,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":1.0,"interpretation":0.0}},{"i":2,"p":0.95,"id":"s2","own":true,"role":"contribution","text":"The key advance is Model-Initiated Conversation (MIC), which enables the model to identify topics worth discussing in the evolving visual stream and initiate conversations at appropriate moments without a user query.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.76,"main_claim_p":0.25,"quantitative":false,"quantitative_p":0.07,"role_probabilities":{"gap":0.0,"method":0.05,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.95,"interpretation":0.0}},{"i":3,"p":0.69,"id":"s3","own":true,"role":"contribution","text":"Stream-Aware Tool Calling (SATC) enables the model to invoke external tools using the current visual and conversational context and incorporate returned information into the ongoing interaction.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.81,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.31,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.69,"interpretation":0.0}},{"i":4,"p":0.86,"id":"s4","own":true,"role":"contribution","text":"Interactive Visual Grounding (IVG) supports visual grounding in both user inputs and model outputs.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.65,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.14,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.86,"interpretation":0.0}},{"i":5,"p":0.61,"id":"s5","own":true,"role":"method","text":"The model can identify objects marked by users on video frames and produce frame-aligned bounding boxes to link its responses to specific objects and regions.","hedge":{"p":0.95,"label":"asserted"},"own_p":0.75,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.1,"role_probabilities":{"gap":0.0,"method":0.61,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.39,"interpretation":0.0}},{"i":6,"p":0.99,"id":"s6","own":true,"role":"method","text":"To develop these capabilities, we construct a dedicated streaming interaction dataset and adopt a three-stage training scheme to integrate the new behaviors with AURA's existing streaming interaction abilities.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.96,"main_claim_p":0.03,"quantitative":true,"quantitative_p":0.54,"role_probabilities":{"gap":0.0,"method":0.99,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.0}},{"i":7,"p":0.59,"id":"s7","own":true,"role":"method","text":"We further incorporate Long-Horizon Interaction Memory (LHIM) to maintain contextual continuity over extended video streams.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.92,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.59,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.41,"interpretation":0.0}},{"i":8,"p":1.0,"id":"s8","own":true,"role":"result","text":"Evaluations on public streaming benchmarks show that AURA 2.0 achieves leading performance among open-source streaming models, while targeted evaluations further validate its new interaction capabilities.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.64,"quantitative":true,"quantitative_p":0.88,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":9,"p":0.95,"id":"s9","own":true,"role":"contribution","text":"We open-source the model weights and inference code.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.94,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.02,"role_probabilities":{"gap":0.0,"method":0.01,"result":0.01,"background":0.0,"limitation":0.0,"future_work":0.03,"contribution":0.95,"interpretation":0.0}}]},"compiled":{"main_claim":{"p":0.99,"text":"Evaluations on public streaming benchmarks show that AURA 2.0 achieves leading performance among open-source streaming models, while targeted evaluations further validate its new interaction capabilities.","location":"abstract s8","hedge_strength":{"p":1.0,"label":"asserted"}},"provenance":{"route":{"via":"TypeSafe API","model":"classifier-1.13.0","endpoint":"https://api.typesafe.ai/v1/systemone","provider":"TypeSafe"},"packing":"one request per paper","requests":1,"input_tokens":7500,"cost_usd_reported":0.0},"compiled_at":"2026-11-13","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.07,"states_limitation":0.09,"human_participants":0.2,"controlled_comparison":0.18,"randomized_assignment":0.01,"states_quantitative_result":0.06,"compares_with_prior_results":0.85,"mentions_code_or_data_availability":0.98},"evidential_basis":{"p":0.97,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.0,"observation_or_experiment":0.97,"simulation_or_computation":0.03}},"contribution_type":{"p":1.0,"value":"method or tool","probabilities":{"review":0.0,"method_or_tool":1.0,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":0.51,"text":"To move beyond purely user-driven interaction, we present AURA 2.0, a streaming video large language model that introduces three core upgrades to AURA.","location":"abstract s1"}},"coverage":{"tier":"abstract","levels_run":["P abstract"],"not_examined":["full text","figures and tables","references and citing sentences","relations to other papers"],"sources_read":["arXiv listing abstract v1"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":10,"sentences_in_abstract":10},"measured_accuracy":{"url":"https://pith.science/accuracy","measured_on":"2026-10-02","method":"two independent model families labelled a fresh random sample blind; the figure is how often the published label matches their consensus","sentence_role_agreement":0.92,"main_claim_agreement":0.908,"typed_citation_agreement":0.933,"typed_citation_agreement_95_interval":[0.917,0.945],"review_comments_accurate":0.758,"review_comments_accurate_95_interval":[0.684,0.82],"review_caught_admitted_error_found_or_related":0.448,"review_comments_judged":{"judged_by":["gpt-5.6-luna","grok-4.7"],"judged_against":"Pith's own text copy of each paper: text extracted from the PDF, the first 90,000 characters","measured_on":"2026-10-04","accurate":113,"decided":149,"sampled_reviews":200,"split_by_lane":false,"by_lane":"https://pith.science/accuracy#by-lane"}}}