An Agent Centered Approach to Conversational Context
Bibliographic record
Abstract
Characterizing the context of a conversation is a complex endeavor. In this paper we present some of the key elements that sustain the conversational context. We suggest that a conversation can be viewed as a negotiation game in which participants negotiate on several levels: some of these levels are used to manage the communication (communication channel, information transfer, turn taking) while others (negotiation and environmental sub-contexts) are used to transfer concepts or mental states relative to various spatio-temporal situations between agents. The social and reasoning sub-contexts also play an important role in the characterization of the conversational context. We concentrate on the elements of the negotiation and environmental sub-contexts which make up a core model for the conversational context. We present the key ingredients of those sub-contexts: the agent's perspective that characterizes an agent's temporal position when uttering a sentence; the agent's positioning that specifies the action applied to mental states when an agent plays a move in the negotiation game; mental states and their relations with temporal situations evoked in agents' utterances. We show that all those knowledge structures are temporally situated with respect to a temporal frame of reference whose main reference points are specified relative to agent's perspectives or deictically specified. We emphasize the role of deictic phenomena in the characterization of agents' orientations within the conversational context and thus, the importance of accounting for them in a model of context.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.004 | 0.008 |
| Scholarly communication | 0.012 | 0.014 |
| Open science | 0.003 | 0.008 |
| Research integrity | 0.003 | 0.005 |
| Insufficient payload (model declined to judge) | 0.006 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".